WO2021051959A1 - 车辆控制的方法、装置、控制器和智能汽车 - Google Patents
车辆控制的方法、装置、控制器和智能汽车 Download PDFInfo
- Publication number
- WO2021051959A1 WO2021051959A1 PCT/CN2020/100089 CN2020100089W WO2021051959A1 WO 2021051959 A1 WO2021051959 A1 WO 2021051959A1 CN 2020100089 W CN2020100089 W CN 2020100089W WO 2021051959 A1 WO2021051959 A1 WO 2021051959A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- speed
- collision
- smart car
- potential energy
- obstacles
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/085—Taking automatic action to adjust vehicle attitude in preparation for collision, e.g. braking for nose dropping
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18109—Braking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
- B60W50/023—Avoiding failures by using redundant parts
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/04—Monitoring the functioning of the control system
- B60W50/045—Monitoring control system parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4049—Relationship among other objects, e.g. converging dynamic objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/801—Lateral distance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/802—Longitudinal distance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/803—Relative lateral speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/804—Relative longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/805—Azimuth angle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
- B60W2554/806—Relative heading
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2720/00—Output or target parameters relating to overall vehicle dynamics
- B60W2720/10—Longitudinal speed
Definitions
- This application relates to the automotive field, and in particular to a smart/intelligent car (smart/intelligent car) anti-collision method, device, controller and smart car.
- the vehicle-mounted sensor is used to collect the information of the vehicle in front, and the vehicle-mounted controller determines whether a collision has occurred based on the braking distance and the minimum braking time. Once the controller determines that a collision will occur, the braking operation of the smart car is implemented.
- the aforementioned anti-collision scheme only decides whether to brake or not based on the distance between the vehicle and the vehicle and the minimum braking time, which may easily cause misjudgment or missed judgment, resulting in personal injury or vehicle damage.
- This application provides a vehicle control method, device, controller, and smart car, which are applied to smart cars, which can realize a more effective smart car anti-collision function and improve the safety of smart cars during automatic driving.
- a vehicle control method includes: obtaining a first speed at which the smart car is planned to travel in a first area; the first area is a section of the area during which the smart car is traveling to a destination. Obtain the second speed at which the smart car is planned to travel in the first area; the second speed is obtained according to the collision potential energy; wherein, the first speed and the second speed include a direction and a magnitude, respectively; The first speed, the second speed, and the risk of collision between the smart car and surrounding obstacles are used to determine the optimal speed of the smart car, and the optimal speed includes a magnitude and a direction.
- the smart car can plan the first speed and the second speed for the smart car in the same area through the dual-channel redundant design, and then determine the optimal speed according to the risk of collision between the smart car and surrounding obstacles, and then Realize that the smart car avoids surrounding obstacles at the optimal speed, avoid collisions between the self-car and surrounding obstacles, reduce the damage of the occupants and vehicles in the smart car, and improve the safety of the smart car in the automatic driving process.
- the collision potential energy is used to identify the tendency of the surrounding obstacles of the smart car to collide with the smart car.
- the safety channel can identify obstacles that collide with the self-car through the collision potential energy, and further determine the first speed based on the collision potential energy. Controlling the smart car to drive at the first speed can effectively realize the obstacle avoidance process.
- the optimal speed of the intelligent car against collision is determined according to the first speed, the second speed, and the collision risk of the intelligent car with surrounding obstacles, and the optimal speed is Speed includes size and direction.
- a speed control instruction is received, and the smart car is controlled to travel by the speed control instruction.
- the smart car can present the first speed and the second speed to the driver in the form of an interface display screen, etc., and the driver can choose the first speed or the second speed to control the driving of the smart car.
- the speed selected by the operator can be sent to the controller of the smart car in the form of a speed control command, and the controller of the smart car controls the driving of the smart car according to the speed control command.
- the driver can also switch the driving mode to manual driving through the interface display screen, and control the smart car to drive according to the current driver's operation.
- the interface display screen prompts the driver of the risk of collision, and the driver can directly take over the control of the smart car, thereby realizing artificial control of the smart car.
- the optimal speed is the first speed; wherein, the first preset condition is any surrounding
- the collision potential energy of the obstacle is less than the first threshold.
- the speed of the smart car can be determined by the collision potential energy of the obstacle.
- the vehicle can be controlled at the speed determined by the working channel Driving. That is to say, when there is a preset risk of collision with obstacles, the vehicle can be controlled at the speed determined by the working channel to realize the obstacle avoidance process and improve the safety of the smart car.
- the optimal speed is the second speed; where the second preset condition is any surrounding obstacle
- the collision potential energy is greater than or equal to the first threshold.
- the collision potential of the obstacle and the self-car is judged according to the collision potential energy of the surrounding obstacles.
- the safety is adopted.
- the second speed determined by the channel controls the driving of the smart car. That is to say, when any surrounding obstacle reaches the preset risk of collision, the vehicle is controlled at the speed determined by the safe passage to realize the obstacle avoidance process and improve the safety of the smart car.
- the smart car may prompt the smart car to have a collision risk by at least one of the following ways: the smart car’s on-board display interface prompts the smart car to have a collision risk with the surrounding obstacles through text , The first speed and the second speed; or, in the smart car, the smart car is prompted by voice to indicate the risk of collision with the surrounding obstacles, the first speed and the second speed; or, in the smart car, the seat vibration prompts the smart car to There is a risk of collision with surrounding obstacles; or, in the smart car, the flashing lights of the smart car indicate that the smart car and the surrounding obstacles are at risk of collision.
- the message interaction between the smart car and the driver can be realized, the driver can be promptly reminded of potential risks for dangerous situations, and the driver is allowed to take over or control the driving process of the smart car, thereby reducing the driver’s ignorance. Bring fear, enhance the driving experience.
- the final optimal speed of the vehicle may also be presented to the driver, so that the driver can understand the obstacle avoidance process and speed planned by the vehicle, increase the human-vehicle interaction process, and improve the user experience.
- the vehicle control method provided by this application can plan the speed in the first area from the safety channel and the working channel respectively, and the controller selects a speed as the optimal speed, or the controller receives the speed selected by the driver , And then control the vehicle to travel according to the optimal speed or the speed selected by the driver to realize an effective obstacle avoidance process and improve the safety of smart cars.
- the vehicle control method provided by the present application can be based on the collision potential energy of obstacles, using the potential energy decomposition and merging method to obtain the optimal speed that meets the high functional safety requirements in any area, and then verify through the feasible area, and finally determine the intelligence The optimal speed of the car to avoid obstacles.
- the distance and relative speed between the surrounding obstacles and the self-vehicle comprehensively consider the possibility of collision between the self-vehicle and the obstacle, and better identify the risk of collision between vehicles, so as to solve the traditional technology based on the judgment of braking distance and minimum braking time.
- the method provided by the present application can not only avoid collisions with vehicles from the front of the own vehicle, but also avoid collisions from the rear and side of the own vehicle. Compared with the traditional technical method, it can only prevent the collision from the own vehicle.
- the collision of the vehicle in front enhances the obstacle avoidance ability of the smart car.
- the obstacle avoidance direction and speed provided by the method provided by the present application are more accurate, which can ensure that the smart car realizes obstacle avoidance according to the most safe direction and speed at the current moment, and avoid collisions between its own car and surrounding vehicles.
- the present application provides another vehicle control method, the method comprising: calculating the collision potential energy of the surrounding obstacles of the smart car according to first perception data, the first perception data including the surrounding obstacles and the The relative speed and relative distance of the smart car; determining the safe speed of the smart car driving in a first area according to the collision potential energy of the surrounding obstacles, the first area being a section of the planned path of the smart car; Controlling the smart car to drive at the safe speed in the first area.
- the above method provided in this application can use the collision potential energy of surrounding obstacles to determine a safe speed, and use this safe speed to control the smart car to drive in the first area, so as to realize the obstacle avoidance process of the smart car and reduce the damage to the occupants and the vehicle. Improve the safety of smart cars.
- the collision potential energy is used to identify the collision tendency between the surrounding obstacle and the smart car.
- k, ⁇ , ⁇ are constant coefficients
- C is a constant
- ⁇ is the relative speed of the first obstacle relative to the smart car
- d is the relative distance of the first obstacle relative to the smart car
- An obstacle is any one of the surrounding obstacles of the smart car.
- the collision risk level of each surrounding obstacle is determined according to the collision potential energy of the surrounding obstacles and a preset threshold, and the collision risk level includes safety, early warning, and danger; select All surrounding obstacles of a preset collision risk level; the safe speed is determined according to the collision potential energy of all surrounding obstacles of the selected preset collision risk level.
- the controller can select some surrounding obstacles among all surrounding obstacles according to the preset collision risk level, and further determine the safe speed of avoiding obstacles according to the collision potential energy of each obstacle, which can reduce the calculation amount and processing time of the controller.
- first perceptual data is acquired, and the first perceptual data is data obtained by analyzing and processing the initial data detected by the perceptual device of the smart car; establishing the smart car Is the coordinate system of the origin; calculates the position of the surrounding obstacles in the coordinate system according to the first perception data, and the position is used to indicate the coordinates and quadrants of each obstacle in the coordinate system .
- the self-car coordinate system of the smart car may be a coordinate system with the centroid of the self-car as the origin and the driving direction as the positive X-axis.
- the coordinate system may also take the center point of the front or the rear of the vehicle as the origin.
- the maximum safety angle in the area with no obstacles is identified, and the angle bisector direction of the maximum safety angle As the direction of the safe speed, the size greater than or equal to the maximum speed of the surrounding vehicles is the size of the safe speed.
- the sum of the collision potential energy of all obstacles of the preset safety risk level in the same quadrant is calculated respectively. ; Determine the orthogonality of the collision potential energy sum in each quadrant; remove the collision potential energy sum and/or the orthogonality of the collision potential energy sum of all obstacles in the quadrant with obstacles; calculate the collision potential energy sum and/or in the obstacle-free quadrant
- the orthogonality of the collision potential energy combination, the cooperation of all directions in the collision potential energy combination and/or the orthogonality of the collision potential energy combination in the obstacle-free quadrant is the direction of the safe speed, which will be greater than or equal to the maximum speed of the surrounding vehicles as The size of the safe speed.
- the direction of the sum of the collision potential energy in the two quadrants is the direction of the safe speed, and the sum of the collision potential energy in the two quadrants is the magnitude of the safe speed;
- the sum of the collision potential energy Or the orthogonality of the collision potential energy combination includes any one of the following two situations: the orthogonality of the collision potential energy combination and the collision potential energy combination, the collision potential energy combination or the orthogonality of the collision potential energy combination.
- the collision potential energy of all surrounding obstacles of the preset collision risk level in the same quadrant are calculated respectively And determine the orthogonal direction of each collision potential energy; remove the orthogonal direction in the quadrant with obstacles; calculate the orthogonal direction of the collision potential energy in the quadrant without obstacles to be the direction of the safe speed.
- the maximum speed of all surrounding vehicles that is greater than or equal to the preset collision risk level is the safe speed.
- the collision potential energy of all surrounding vehicles of the preset collision risk level in the same quadrant is calculated.
- determine the orthogonality of each collision potential energy combination remove the orthogonality of the collision potential energy combination in the quadrant with obstacles; compare the collision potential energy combination of the obstacles in the two quadrants in the obstacle-free quadrant, and when the two quadrants collide
- the potential energy sum is equal, the sum of the collision potential energy in the two quadrants is calculated, and the cooperation of the collision potential energy in the two quadrants is taken as the safe speed.
- the orthogonal magnitude of the collision potential energy sum is the magnitude of the collision potential energy sum
- the direction is the direction perpendicular to the collision potential energy sum.
- the collisions of all surrounding obstacles of the preset collision risk level in the same quadrant are calculated respectively.
- Potential energy combination and determine the orthogonality of each collision potential energy combination; calculate the orthogonal combination of the collision potential energy combination belonging to the same quadrant, in any one direction of the orthogonal combination of the collision potential energy combination of the same quadrant Is the magnitude of the safe speed, and the magnitude greater than or equal to the maximum speed in the surrounding vehicles is the magnitude of the safe speed.
- the collision potential energy sum of all surrounding vehicles of the preset collision risk level is calculated to be orthogonal to the collision potential energy sum.
- the direction is the direction of the safe speed, and the magnitude greater than or equal to the maximum speed of the surrounding vehicles is the magnitude of the safe speed.
- the feasible range is an area that meets the following criteria: no collision with dynamic obstacles, no collision with static obstacles, no Violation of traffic rules, where dynamic obstacles include motor vehicles, pedestrians, and animals; static obstacles include barriers, guardrails, paths, street lights and other infrastructure; traffic rules include retrograde, running red lights; when the direction of the safe speed belongs to the When the feasible range is available, the smart car is controlled to drive at the safe speed in the first area.
- the safest direction can also be selected as the direction of the second speed according to the degree of collision risk with the obstacle, where the degree of collision risk Including one or more of the probability of collision with an obstacle, the degree of damage caused by the collision, etc.
- the degree of damage caused by a collision can be calibrated according to the size, relative speed and relative distance of the obstacle, the larger the obstacle, the relative speed The faster and the shorter the relative distance, the higher the degree of damage in a collision.
- the present application provides a device for controlling a vehicle.
- the device includes various modules for executing the vehicle control method in the first aspect or any one of the possible implementations of the first aspect.
- the present application provides a vehicle control device.
- the device includes various modules for executing the vehicle control method in the second aspect or any one of the possible implementation manners of the second aspect.
- the present application provides a controller for vehicle control.
- the controller includes a processor, a memory, a communication interface, and a bus.
- the processor, the memory, and the communication interface are connected by a bus and communicate with each other.
- the memory is used to store computer-executable instructions, and when the controller is running, the processor executes the computer-executable instructions in the memory to execute the first aspect or the first aspect using hardware resources in the controller.
- the present application provides a controller for vehicle control.
- the controller includes a processor, a memory, a communication interface, and a bus.
- the processor, the memory, and the communication interface are connected by a bus and complete mutual communication.
- the memory is used to store computer-executable instructions, and when the controller is running, the processor executes the computer-executable instructions in the memory to execute the second aspect or the second aspect using hardware resources in the controller.
- the present application provides a smart car, the smart car includes a controller, and the controller is configured to implement the functions implemented by the controller in the fifth aspect and any one of the possible implementation manners of the fifth aspect, Or the foregoing controller is used to implement the function implemented by the controller in the sixth aspect and any one of the possible implementation manners of the sixth aspect.
- the present application provides a computer-readable storage medium having instructions stored in the computer-readable storage medium, which when run on a computer, cause the computer to execute the methods or functions described in the above aspects.
- this application provides a computer program product containing instructions, which when run on a computer, causes the computer to execute the methods or functions described in the above aspects.
- FIG. 1 is a schematic diagram of the architecture of a smart car provided by this application.
- FIG. 2 is a schematic diagram of another smart car architecture provided by this application.
- FIG. 3 is a schematic flowchart of a vehicle control method provided by this application.
- FIG. 4 is a schematic flowchart of another vehicle control method provided by this application.
- Figure 5 is a schematic diagram of a smart car coordinate system provided by this application.
- Fig. 6 is a schematic diagram of a method for calculating the relative speed of an obstacle and a self-vehicle provided by this application;
- FIG. 7 is a schematic diagram of an obstacle collision collision risk classification provided by this application.
- FIG. 8 is a schematic diagram of obstacles distributed in four quadrants provided by this application.
- FIG. 9 is a schematic diagram of obstacles distributed in three quadrants provided by this application.
- FIG. 10 is a schematic diagram of obstacles distributed in two adjacent quadrants provided by this application.
- FIG. 11 is a schematic diagram of obstacles distributed in two non-adjacent quadrants provided by this application.
- FIG. 12 is a schematic diagram of a kind of obstacles distributed in the same quadrant provided by this application.
- FIG. 13 is a schematic diagram of a human-computer interaction system in a smart car provided by this application.
- FIG. 14 is a schematic structural diagram of a vehicle control device provided by this application.
- FIG. 15 is a schematic structural diagram of another vehicle control device provided by this application.
- FIG. 16 is a schematic structural diagram of a controller provided by this application.
- FIG. 1 is a schematic diagram of the architecture of a smart car provided by this application.
- the smart car 100 includes a controller 101, a sensing device 102, an interactive system 103, and an execution system 104.
- the sensing device 102 is used to obtain information about obstacles such as vehicles, people, and infrastructure around the smart car through sensors, including obstacle images and detection information.
- the detection information can be different according to different types of sensing devices, for example, When the sensing device is a lidar, the lidar can emit a detection signal (for example, a laser beam) to the target, and then compare the received signal (for example, the target echo) from the target with the transmitted signal, and make appropriate After processing, the relevant detection information of the target can be obtained, such as the target's distance, azimuth, height, speed, attitude, and even shape parameters.
- the above obstacle information will be sent to the controller 101, and the controller 101 will further determine the driving track of the smart car to the destination based on the obstacle information, and then send the control command including the speed to the execution system 104, and the execution system 104 controls the smart The car is driving.
- speed is a vector, including size and direction, and the size of speed can also be called velocity.
- the redundant dual-channel design can be used in the controller 101 to calculate the speeds of driving in the same segment respectively.
- the controller may include a working channel and a safety channel.
- the working channel is used to plan the speed of the smart car using artificial intelligence algorithms;
- the safety channel defines a potential function between the smart car itself and the obstacle, based on the potential energy Decomposition and merging methods plan the speed of smart cars to avoid obstacles to prevent collisions.
- the controller 101 can use the working channel and the safety channel to respectively determine the speed of driving in the same section of the driving track, and then the controller 101 determines the final speed to be selected according to preset conditions.
- the final speed selected by the controller 101 may also be referred to as an optimal speed
- the potential energy decomposition and combination method may also be referred to as a vector decomposition and combination method.
- Figure 1 also includes an interactive system 103, which is used to implement message interaction between the smart car 100 and the driver, so that the driver can send operation instructions to the smart car through the interactive system 103, and learn about the smart car through the interactive system 103 Current status.
- an interactive system 103 which is used to implement message interaction between the smart car 100 and the driver, so that the driver can send operation instructions to the smart car through the interactive system 103, and learn about the smart car through the interactive system 103 Current status.
- the smart car 100 in addition to the speed determined by the controller 101 selecting the working channel or the safe channel according to preset conditions as the optimal speed for the smart car, the smart car 100 also includes an arbitrator 105, which respectively The speed planned by the working channel 1011 and the speed planned by the safe channel 1012 are received, and the arbitrator 105 selects the optimal speed of the smart car according to preset conditions.
- FIG. 2 is a schematic diagram of the architecture of another smart car provided by this application. As shown in the figure, FIG. 2 further shows the logical structure of each part of the smart car 100 in FIG. 1.
- the sensing device 102 includes one or more of sensors capable of detecting and recognizing surrounding objects, such as an image acquisition device 1021, a laser radar 1022, and a millimeter wave radar 1023.
- the number of sensors of the same type deployed in the same smart car does not constitute a limitation on the technical solution to be protected by this application.
- the controller 101 includes a dual-channel redundant design of a working channel 1011 and a safety channel 1012.
- the working channel 1011 is used to use artificial intelligence algorithms for perception, decision-making, and path planning, and output the safe direction and speed of the smart car, so that the smart car can meet quality management (QM) requirements.
- the working channel 1011 includes a first perception module 10111 and a decision module 10112.
- the first perception module 10111 is used to collect the obstacle information around the smart vehicle collected by the perception device, and process the obstacle information to obtain road condition information, such as obstacle type, speed, size, road and other infrastructure conditions (such as current direction Number of lanes, traffic signs, etc.).
- the decision module 10112 is configured to further determine the direction and speed of driving in a certain area according to the road condition information provided by the first perception module 10111.
- the safe passage 1012 includes a second perception module 10112 and a decision-making and anti-collision module 10122.
- the decision-making and collision avoidance module 10122 is used for the obstacle information provided by the second perception module 10112, such as the distance and relative speed of the obstacle relative to the self-vehicle.
- the potential energy decomposition and combination method is used to further determine the direction and speed of driving in a certain area, so that the driving of the smart car can meet the safety level and meet the requirements of the ASIL D level of automotive safety integrity level.
- the ASIL level is the automotive safety integrity level, which is used to describe the probability of a component or system achieving the established safety goal.
- the ASIL level is determined by three basic elements: severity (Severity, S), exposure (E), and controllability (C). Severity, used to indicate the severity of damage to the lives and property of people in the car once a risk occurs; exposure rate, used to refer to the probability of damage to personnel or property; controllability, used to describe how the driver can when the risk becomes a reality The extent to which proactive measures are taken to avoid damage.
- ASIL levels can be divided into four levels D, C, B, and A from high to low. Level D has the least safety risk, and Level A has the greatest safety risk. In addition to the four safety levels, there is a quality management requirement. The directive management requires no safety requirements. For the autonomous driving mode, the safety risk is greater than ASIL.
- the first sensing module 10111 and the second sensing module 10112 in FIG. 2 can be combined into one sensing module.
- the combined sensing module obtains obstacle information from the sensing device 102, and accordingly The information further calculates road condition information such as the distance of the obstacle relative to the smart car and the relative speed of the obstacle relative to the smart car, and according to the information required by the decision-making module 10112 and the decision-making and anti-collision module 10122, the required content is sent to them respectively.
- the first perception module 10111, the decision module 10112, the second perception module 10121, the decision and anti-collision module 10122, and the arbitration module 105 in the controller shown in FIG. 2 can be implemented by hardware, software, or a combination of hardware and software. Realize the corresponding function.
- FIG. 1 and FIG. 2 are only schematic diagrams of the architecture of a smart car provided by this application, and the arbiter may be implemented by software or hardware in the controller.
- the arbiter can also be implemented by an independent processor to select redundant channels.
- the following description of the present application takes the arbiter as a module in the controller as an example for description.
- the following embodiments are described by taking the surrounding obstacles as surrounding vehicles as an example.
- FIG. 3 is a schematic flowchart of a vehicle control method provided by this application.
- the method consists of the decision-making module 10112, the decision-making and anti-collision module 10122, and the arbitration module 105 in the controller 101 of the smart car in FIG. 2, and the control of the smart car
- the system 104 executes. As shown in the figure, the method includes:
- the decision-making module obtains the first perception data of the smart car learned by the first perception module.
- the first perception module can obtain information of vehicles around the smart car through the perception device, such as the type, state, speed, size, road sign, etc. of the obstacle.
- the sensing device includes an image acquisition device
- information about surrounding obstacles can be acquired by acquiring images, and the first perception module can analyze the type, size, road signs, etc. of the obstacles according to the image.
- the sensing device is a lidar
- the beam will return to the lidar through diffuse reflection after hitting an object.
- the first sensing module can multiply the speed of light according to the time interval of the lidar sending and receiving signals, and then divide by 2. Can calculate the distance between the lidar and the object.
- the moving distance of the obstacle relative to the smart car can be obtained through two or more beams, and the relative speed of the obstacle relative to the smart car can be further calculated by combining the transmission time of the two beams of light.
- the first perception module may send the first perception data including the distance between the obstacle and the smart car and the speed of the obstacle relative to the smart car to the decision-making module.
- the decision-making module calculates the first speed of driving in the first area.
- the decision-making module During the driving process of the smart car, the entire path planning of the smart car to the destination will be planned according to the destination, the driving habits of the driver and the map. However, due to the complex road conditions during the driving process, the decision-making module also needs to plan the driving trajectory of the smart car according to the road conditions of the driving area at the current moment. For example, the decision-making module will learn a segment of the entire path planning in real time or periodically based on the first perception data. Regional road conditions. For ease of description, the following embodiments of the present application take this area as the first area as an example for description, where the length of the first area is determined by the range of obstacles that can be detected by the sensing device and the computing capability of the decision-making module in the smart car. Decided.
- the decision-making module can determine the location of the obstacle and the relative speed with the smart car according to the first perception data, and the target speed of the smart car to determine the direction and speed of the smart car.
- the direction and speed determined by the working channel in the controller can be called the first speed or the working speed.
- the first speed is taken as an example in the following embodiments as the direction and speed determined by the decision module in the working channel Be explained.
- the decision-making module can plan the first speed of the smart car in the first area according to the destination specified by the driver, the on-board map, the positioning system, and the information of surrounding obstacles.
- This application does not limit the method for the decision-making module to confirm the speed of the first party.
- an adaptive method can be used to determine the first speed according to business requirements.
- the decision-making module sends the first speed to the arbitration module.
- the decision-making and anti-collision module acquires the second perception data of the smart car sent by the second perception module.
- the decision-making and anti-collision module can also obtain second perception data from the second perception module using a method similar to step S210, where the second perception data includes the relative distance, relative speed, and relative position of the surrounding vehicle and the self-vehicle.
- the position can be calculated according to the angle and relative distance of the speed of light received by the sensing device. For example, the angle at which the sensor device obtains the speed of light from the obstacle is 30 degrees, and the decision and collision avoidance module can determine the obstacle based on the angle and relative distance.
- the position in the self-car coordinate system is a method similar to step S210, where the second perception data includes the relative distance, relative speed, and relative position of the surrounding vehicle and the self-vehicle.
- the position can be calculated according to the angle and relative distance of the speed of light received by the sensing device. For example, the angle at which the sensor device obtains the speed of light from the obstacle is 30 degrees, and the decision and collision avoidance module can determine the obstacle based on the angle and relative distance.
- the decision-making and anti-collision module calculates the second party speed of the smart car traveling in the first area.
- the decision-making and anti-collision module can find the speed of obstacle avoidance of smart cars based on the method of decomposition and combination of potential energy.
- the speed determined by the safe channel in the controller may be referred to as the second speed or the safe speed.
- the following embodiments take the second speed as the speed determined by the decision module in the working channel as an example for description.
- FIG 4 is a schematic flow diagram of another vehicle control method provided by this application.
- This figure is specifically a schematic flow diagram of a method for the decision-making and anti-collision module to plan a second speed of a smart car driving in a first area, such as As shown in the figure, the method includes:
- the self-vehicle coordinate system may also be a coordinate system with a non-centroid as the origin, for example, the center position in front of the self-vehicle is the origin, or the midpoint of the central axis of the self-vehicle is the origin.
- the self-car coordinate system can also be a three-dimensional coordinate system, in which the Z-axis coordinates of each obstacle in the self-car coordinate system can take any value, or it can be converted to the self-car according to the coordinates of the coordinate system where other vehicles are located. The value obtained by the coordinate system.
- the positive direction of the X-axis can also be set in other ways, for example, the heading direction of the self-car is the positive X-axis direction.
- the decision-making and anti-collision module calculates the collision potential energy of each surrounding vehicle and the smart car according to the relative distance and relative speed of each surrounding vehicle to the self-vehicle.
- Fig. 5 is a schematic diagram of a smart car coordinate system provided by this application. As shown in Fig. 5, the center of mass of the smart car is taken as the origin, and the driving speed of the smart car is the positive direction of the X axis to establish a two-dimensional coordinate system. Among them, the center of mass of the smart car may be the center of a rectangular parallelepiped based on the length, width, and height of the vehicle.
- Fig. 6 is a schematic diagram of a method for calculating the relative speed of an obstacle and a self-vehicle provided by this application.
- the speed of the vehicle is
- the obstacle speed is
- the obstacle speed is projected as
- the obstacle may collide with the self-car only when it is in the same direction as the self-car and the speed is close.
- Calculating the projection of the obstacle along the speed direction of the smart car is to confirm the speed component of the possible collision between the obstacle and the self-car.
- the projection of the obstacle in the direction of the speed of the smart car is used to indicate the tendency of the obstacle to collide with the self-vehicle when the obstacle moves in the direction of the speed of the self-vehicle.
- the projection of the obstacle along the speed direction of the smart car is taken as the relative speed of the obstacle relative to the smart car.
- the collision potential energy f(O) of the obstacle O is used to describe the tendency of the obstacle O to collide with the smart car, or it is called the escape potential energy of the smart car to avoid the collision of the obstacle.
- k, ⁇ , and ⁇ are constant coefficients
- C is a constant. The value of C can be flexibly set according to simulation results and actual experience. Because the speed ⁇ is the speed of the obstacle relative to the smart car, it is a vector with both magnitude and direction. Therefore, f is also a vector and the direction is the same as that of v.
- v x and v y are the coordinates of ⁇ on the X axis and the Y axis, respectively.
- the collision potential energy of the obstacle can also be calculated using formula (5) or formula (6):
- the decision-making and collision avoidance module can determine the position of each surrounding vehicle in the coordinate system shown in FIG. 5 according to the relative position of the surrounding vehicle and the self-vehicle.
- the coordinate system is a two-dimensional coordinate system.
- the projection position of the surrounding vehicles in the two-dimensional coordinate system is regarded as the position of the surrounding vehicles. position.
- the method for determining the position of the surrounding vehicles in the own vehicle coordinate system further includes: converting the coordinates of the surrounding vehicles in the geodetic coordinate system into a two-dimensional coordinate system.
- the method of traditional technology can be used to realize the surrounding vehicles in the two-dimensional coordinate system.
- the coordinate conversion in a coordinate system is not limited in this application.
- S302 (optionally): Determine the collision risk level to which each surrounding vehicle belongs based on the collision potential energy of each surrounding vehicle.
- All obstacles detected by the sensing equipment can be calculated by using any one of the above formulas (4)-(6) to calculate their collision potential energy.
- the preset condition finds out obstacles with a higher potential collision risk, and then determines the second speed according to the collision potential energy of these obstacles. For example, as shown in Fig. 7, the application classifies the risk of collision between surrounding vehicles and the self-vehicle into three levels: safety, early warning, and danger.
- the controller can prompt the driver to operate manually through the interactive system to realize obstacle avoidance; when the obstacle is at a dangerous level At the time, the controller can take over the control of the smart car in an emergency, and avoid the collision of its own car with other vehicles in an emergency situation during the execution of other modules of the smart car.
- the controller actively takes over only when the smart car is in the automatic driving mode, and other modules perform calculation or data processing.
- the operation of the smart car is fully controlled by the driver, and the controller does not interfere with the driving process of the smart car.
- the method provided in the present application may not distinguish the collision risk level, and directly determine the second speed based on the collision potential energy of all the surrounding obstacles of the smart car.
- the following embodiments of the present application are divided into obstacles Take the collision risk level of objects as an example.
- the collision risk level shown in Figure 7 can be preset according to the obstacle avoidance ability of the smart car (such as performance and size), respectively, the collision potential energy
- the decision-making and anti-collision module may only determine the risk of collision with the self-vehicle based on the collision potential energy of the surrounding vehicles of the warning and/or danger level.
- the decision-making and anti-collision module can also calculate the collision potential energy of all obstacles at the same time, and determine the risk of collision between other surrounding vehicles and its own vehicle based on all the collision potential energy.
- the decision-making and anti-collision module After the decision-making and anti-collision module calculates the potential energy of obstacles and confirms the quadrant to which each obstacle belongs in the coordinate system of the smart car, the decision-making and anti-collision module prioritizes whether the surrounding vehicles with the preset collision risk level are distributed in four Quadrants, and then, step by step judge whether the surrounding vehicles with preset collision risk levels are distributed in three quadrants, two quadrants and one quadrant. That is to say, the decision-making and anti-collision modules follow the order of the risk of collision with the self-vehicle from high to low. Judge level by level.
- the decision-making and anti-collision module can also directly determine the quadrants of the distribution of all obstacles, and use different methods to confirm the second speed according to the different quadrants of their distribution. That is to say, the decision-making and anti-collision module can not judge the collision risk level of the obstacle and the self-car collision step by step, but directly consider the quadrant of the obstacle distribution, and use different methods to confirm the second according to various situations. speed.
- the decision-making and anti-collision module determines the second speed anti-collision method according to the collision risk level:
- S303 Determine whether all surrounding vehicles with a preset collision risk level are distributed in four different quadrants.
- the decision-making and anti-collision module can first according to the preset angle ⁇ and preset radius Determine that the arc area with the origin as the center and ⁇ as the included angle is the assumed driving range of the surrounding vehicles, It is the farthest distance that can be traveled per unit time determined according to the performance of each vehicle.
- the boundary of the travel area of two adjacent obstacles constitutes a new area, as shown in the figure, when each of the four quadrants includes a surrounding vehicle, and the four vehicle assumed travel ranges are divided according to the preset angle and preset radius At the same time, four areas are divided into area 1, area 2, area 3, and area 4. These four areas are all safe areas without obstacles.
- the decision-making and anti-collision module can select the area with the largest included angle, and use the direction of the bisector of the largest included angle as the direction of the second speed of the obstacle avoidance of the smart car, and use the direction greater than or equal to the maximum speed of the surrounding vehicles as the first Two speed.
- the included angle ⁇ of area 1 is the area with the four largest included angles
- the direction of the angle bisector of the included angle is the direction of the second speed, which is greater than or equal to obstacle 1, obstacle 2, and obstacle
- the size of the maximum speed of the object 3 and the obstacle 4 is used as the size of the second speed.
- the preset angle and the preset radius can be preset according to the model, size and performance of different surrounding vehicles, and the decision-making and anti-collision module can obtain the hypothetical driving range of the surrounding vehicles according to the preset rule.
- S305 When all surrounding vehicles of the preset collision risk level are not distributed in four different quadrants, determine whether all surrounding vehicles of the preset collision risk level are distributed in three different quadrants.
- the decision and collision avoidance module can then determine whether the above-mentioned surrounding vehicles are distributed in three different quadrants. When all surrounding vehicles with a preset collision risk level are distributed in three different quadrants, the decision-making and collision avoidance module can further determine the safe direction of the self-vehicle to avoid obstacles in combination with the potential energy decomposition and combination method provided in this application.
- the decision-making and anti-collision module first calculates the collision potential energy sum of all obstacles in the same quadrant; then, determines the orthogonality of the collision potential energy sum of different quadrants; then calculates the sum of all directions in the quadrant without obstacles, and combines them with
- the combined direction of all directions in the quadrant without obstacles is the direction of the second speed, and a magnitude greater than or equal to the maximum speed of the surrounding vehicles is the magnitude of the second speed.
- Figure 9 is a schematic diagram of a preset collision risk level of all surrounding vehicles distributed in three different quadrants provided by this application. As shown in the figure, surrounding vehicles O 1 , O 2 , O 3 and O 4 are respectively distributed in the first Quadrant, second quadrant and third quadrant, where the first quadrant includes O 1 and O 2 .
- the potential energy of each obstacle can be obtained by calculation in step S301, and the potential energy has a direction and a magnitude.
- the decision-making and anti-collision module can determine the second speed according to the following steps:
- the decision-making and anti-collision module needs to calculate the sum of the collision potential energy of O 1 and O 2 in the first quadrant. Since the speed directions of O 1 and O 2 are both directed to the self-vehicle, the parallel movement of the potential energy in different quadrants does not change the magnitude of the potential energy. And direction.
- V 1 and V 2 of the collision potential energy of the original O 1 and O 2 are moved in parallel with the origin as the starting point in the third quadrant. At this time, O 1 The potential energy of O 2 is combined with the diagonal V* of the parallelogram established by V 1 and V 2 with the origin as the starting point.
- the collision potential energy of the quadrant is the collision potential energy of the obstacle.
- the collision potential energy of O 3 can be moved in parallel to the fourth quadrant, and the collision potential energy of O 4 can be moved in parallel to the first quadrant.
- the orthogonal direction of the collision potential energy is the direction perpendicular to the collision potential energy.
- the collision potential energy of the obstacles in the first quadrant in Fig. 9 is summed as V *
- the orthogonal direction perpendicular to V * is V** . Accordingly, the orthogonal direction of the second quadrant potential obstacle O 3 is bonded to V '3, the third quadrant orthogonal direction potential obstacle O 4 is laminated V' 4.
- the orthogonal directions of the combined potential energy of O 3 in the second quadrant are distributed in the first quadrant and the third quadrant, and both quadrants have obstacles. At this time, only the first quadrant needs to be considered.
- the orthogonal direction of the collision potential energy and the orthogonal direction of the collision potential energy of the third quadrant are sufficient.
- V a is the direction that is the second speed.
- the decision-making and anti-collision module can also determine the maximum speed according to the speeds of all surrounding vehicles with preset collision risk levels, and use a magnitude greater than or equal to the maximum speed as the magnitude of the second speed.
- the second speed can also compare the collision potential energy sum of the obstacles in the two quadrants in the obstacle-free quadrant.
- the combination of the collision potential energy in the two quadrants is the second speed, wherein the direction of the combination of the collision potential energy in the two quadrants is the direction of the safe speed, and the collision potential in the two quadrants is the direction of the safe speed.
- the sum of the potential energy is the size of the safe speed; when the collision potential energy in the two quadrants is not equal, the orthogonal sum of the collision potential energy in the two quadrants is calculated, and the collision potential energy in the two quadrants is combined.
- the orthogonal cooperation is the second speed.
- the orthogonal magnitude of the collision potential energy sum is the magnitude of the collision potential energy sum
- the direction is the direction perpendicular to the collision potential energy sum.
- the decision-making and anti-collision module determines the second speed according to the following steps:
- Figure 10 is an example of a preset collision risk level of all vehicles distributed in two adjacent quadrants provided by this application.
- surrounding vehicles O 1 and O 2 are distributed in the first quadrant
- O 3 and O 4 are distributed in the second quadrant.
- the potential energies of O 1 and O 2 are combined as V*
- the potential energies of O 3 and O 4 are combined as V ⁇ .
- the orthogonal directions of V * and V ⁇ are determined as V ** and V ⁇ .
- V * and then compare the magnitude of V ⁇ , and when V ⁇ V * ranging calculation of V ⁇ V ** and V a potential engagement, a direction V a as the direction of the second velocity, V a is the The speed is used as the second speed.
- V * and V ⁇ are equal, then calculate the sum of V * and V ⁇ , taking the direction of the combined potential energy of V * and V ⁇ as the direction of the second speed, and the combined magnitude of the potential energy of V * and V ⁇ as the second The size of the speed.
- FIG. 10 only takes the process of confirming the second speed when V* and V ⁇ are not equal as an example, and FIG. 10 does not show the process of confirming the second speed when V* and V ⁇ are equal.
- FIG. 11 is an example of a preset collision risk level provided by this application in which all surrounding vehicles are not distributed in two adjacent quadrants.
- surrounding vehicles O 1 and O 2 are distributed in the first quadrant.
- O 3 and O 4 are respectively distributed in the third quadrant.
- the potential energies of O 1 and O 2 are combined as V*
- the potential energies of O 3 and O 4 are combined as V ⁇ .
- the orthogonal directions of V * and V ⁇ are determined as V ** and V ⁇ . Calculate the sum V a and V b of V ** and V ⁇ , and use any direction as the direction of the second speed, and further, use a magnitude greater than or equal to the maximum speed of the surrounding vehicles as the magnitude of the second speed.
- Fig. 12 is an example of a preset collision risk level of all surrounding vehicles distributed in the same quadrant provided by this application.
- surrounding vehicles O 1 , O 2 , O 3 and O 4 are distributed in the first quadrant.
- collision decision module calculates four potential combined collision obstacle, and a direction orthogonal to the potential impact of any one engagement direction as the direction of the second velocity, V a and V b as a first quadrant obstacle
- the decision and anti-collision module can select any direction as the direction of the second speed.
- the orthogonal direction of the collision potential energy is taken as the direction of the second speed
- the magnitude greater than or equal to the maximum speed of the surrounding vehicles is taken as the magnitude of the second speed.
- Figure 12 lists the various possibilities for the decision-making and anti-collision control module to determine the second speed when obstacles are distributed in different quadrants.
- the decision-making and anti-collision control module determines the preset collision risk level When all surrounding vehicles meet any one of the possibilities, the second speed can be determined according to the steps of the above method.
- the obstacle avoidance speed can also be determined in other ways.
- the maximum speed in the surrounding obstacles can be used as the second speed. N times the speed is used as a reference to limit the second speed.
- the probability of collision between the obstacle and the self-vehicle can be calculated according to the type, relative speed, and relative distance of the obstacle, and the calculated results can be calculated in turn.
- the probabilities are sorted according to the size, and the direction of the obstacle with the smallest probability is first selected as the direction of the second speed.
- multiple selectable speed directions are displayed on the on-board display screen, and the probability of collision is prompted.
- the driver selects a speed direction, and the controller controls the smart car to drive according to the direction selected by the driver.
- the decision-making and anti-collision module sends the second speed to the arbitration module.
- the arbitration module selects the first speed as the speed of the smart car.
- the speed determined by the arbitration module can also be called the optimal speed, which can realize the effective obstacle avoidance process of the smart car, ensure that the smart car does not collide with the surrounding obstacles, and reduce the possibility of the smart car colliding with the surrounding obstacles Improve the safety of the autonomous driving process of smart cars.
- the arbitration module sends a first control instruction to the execution system, where the first control instruction includes the first speed.
- the execution system controls the smart car to drive according to the first speed.
- the arbitration module selects the first speed as the driving speed of the smart car, it can further determine whether the direction of the first speed is within the feasible range.
- the direction of the first speed obtained by the potential energy decomposition and merging method is a theoretically safe speed, which should also be verified according to the actual situation, so as to improve the safety of the smart car during the driving process.
- the criteria for the arbitration module to determine whether the direction of the first speed is feasible include: not colliding with dynamic obstacles (such as motor vehicles, non-motorized vehicles, pedestrians, animals, falling goods in movement, etc.), and not colliding with static obstacles (Isolation belts, guardrails, roadbeds, street lights and other infrastructure) collisions, not violating traffic rules (such as retrograde, running red lights).
- the arbitration module can obtain the obstacle data collected by the sensing device from the first perception module, and use the above data to build a world model around the smart car driving environment, and filter the physical space in the world model using the above criteria to obtain All feasible areas.
- the arbitration module sends a control instruction to the execution system to instruct the execution system to control the smart car to drive at the first speed. If the direction of the first speed is not in the feasible area, the arbitration module confirms that the direction of the first speed has a safety risk. At this time, the arbitration module only executes the braking command to avoid collision or reduce collision loss.
- the arbitration module can also obtain the collision potential energy of all surrounding vehicles with a preset collision risk level.
- the arbitration module selects the first speed as the driving speed of the smart car and sends it to the execution system.
- the first control instruction is sent, and the execution system controls the smart car to drive in the first area at the first speed. That is, the first preset condition is that the collision potential energy of all surrounding vehicles with the preset collision risk level is less than the first threshold.
- the arbitration module will control the smart car to drive according to the speed determined by the working channel.
- the arbitration module in the foregoing steps S217 to S218 may also directly send the first control instruction to the execution system without judging whether the direction of the first speed belongs to the feasible range.
- the arbitration module selects the second speed as the driving speed of the smart car.
- the arbitration module judges whether the direction of the second speed belongs to the feasible range.
- the execution system controls the smart car to drive according to the second speed.
- the arbitration module determines that the collision potential energy of all surrounding vehicles of the preset collision risk level is greater than or equal to the first threshold, the arbitration module selects the second speed as the driving speed of the smart car. That is, the second preset condition is that the collision potential energy of all surrounding vehicles of the preset collision risk level is greater than or equal to the first threshold. At this time, the arbitration module will control the smart car to drive at the speed determined by the safe passage.
- the arbitration module will further determine whether the direction of the second speed is within the feasible range.
- the direction of the second speed obtained by the potential energy decomposition and merging method is a theoretically safe speed, which should also be verified according to the actual situation, so as to improve the safety of the driving process of the smart car.
- the criteria for the arbitration module to determine whether the direction of the second speed is feasible include: not colliding with dynamic obstacles (such as motor vehicles, non-motorized vehicles, pedestrians, animals, falling goods in movement, etc.), and not colliding with static obstacles (Isolation belts, guardrails, roadbeds, street lights and other infrastructure) collisions, not violating traffic rules (such as retrograde, running red lights).
- the arbitration module can obtain the obstacle data collected by the sensing device from the first perception module, and use the above data to build a world model around the smart car driving environment, and filter the physical space in the world model using the above criteria to obtain All feasible areas. If the direction of the second speed is in the feasible region, the arbitration module sends a control command to the execution system to instruct the execution system to control the smart car to drive at the second speed. If the direction of the second speed is not located in the feasible area, the arbitration module confirms that the direction of the second speed has a safety risk. At this time, the arbitration module only executes the brake command to avoid collision or reduce collision loss.
- step S210 to S212 and steps S213 to S215 can be executed in parallel.
- step S216 to step S219 and step S220 to step 223 are also two independent judgment branches.
- the arbitration module can further determine whether the direction of the first speed belongs to the feasible range, or directly send the first speed to the execution system, and then control the smart car to control the vehicle to travel at the speed confirmed by the working channel.
- the arbitration module further determines whether the direction of the second speed belongs to the feasible range.
- this application does not limit the method for establishing the world model, and a model that reflects the surrounding vehicle obstacles can be established according to business requirements during specific implementation.
- the smart car obstacle avoidance method provided in this application is a process of actively and continuously implementing effective obstacle avoidance in a collision risk scenario.
- the above process is an iterative process in the driving process of a smart car, as long as the collision potential energy of any obstacle If it is greater than or equal to the first threshold, the above process will be continuously executed in a loop. In other words, as long as there is a risk of collision, the safe passage will calculate the collision potential energy of the obstacle, and then determine the second speed based on the collision potential energy.
- the collision avoidance method provided by this application can obtain the optimal speed that meets the high functional safety requirements in any area based on the potential energy decomposition and combination method, and further verify through the feasible area, and finally determine the obstacle avoidance of the smart car Optimal speed.
- This application can comprehensively judge the possibility of collision between the self-vehicle and the obstacle based on the distance and relative speed of the surrounding obstacles and the self-vehicle, and better identify the collision risk of the self-vehicle, so as to solve the traditional technology based on only braking distance and minimum braking.
- the problem of misjudgment or omission caused by the time judgment method is a problem of misjudgment or omission caused by the time judgment method.
- the method provided by the present application can not only avoid collisions with vehicles from the front of the vehicle, but also avoid collisions with vehicles from the rear and sides of the vehicle. Compared with traditional technical methods, it can only prevent collisions with vehicles from the vehicle.
- the collision of the vehicle in front of the car improves the obstacle avoidance ability of the smart car. It can not only control the smart car to decelerate, but also control the smart car to accelerate and avoid obstacles in the determined obstacle avoidance direction, so that the smart car can realize obstacle avoidance in all directions Effect.
- the obstacle avoidance direction and speed provided by the method provided by this application are more accurate, which can ensure that the smart car realizes obstacle avoidance according to the most safe direction and speed at the current moment, and avoid collisions between its own car and surrounding vehicles.
- FIG. 13 is a schematic diagram of an interactive system provided by this application.
- the interactive system can remind the driver to pay attention to the surrounding vehicles in various forms.
- the driver takes over the smart car or sends execution instructions to the smart car to control the driving of the smart car.
- execution instructions For example, audio prompts, seat vibration prompts, flashing lights in the car prompts.
- the human-computer interaction system can also use different colors or backgrounds to identify different levels and regions.
- At least one of the following ways can be used to realize the human-computer interaction process between the smart car and the driver:
- Method 1 On the on-board display interface of the smart car, a text prompts that the smart car has a collision risk with surrounding obstacles, as well as the first speed and the second speed.
- Va and Vb in FIG. 13 are optional obstacle avoidance directions, and the driver can choose any one as the direction in which the vehicle travels.
- different signs can also be used to indicate the risk of collision when driving in the direction of obstacles. For example, in the direction of obstacles O1 and O2 in Figure 13, use the five-pointed star logo and text Prompt "danger".
- Method 2 In the smart car, it is prompted by voice that the smart car has a collision risk with the surrounding obstacles, the first speed and the second speed; in the smart car, the seat vibration is used to prompt the smart car and the surrounding obstacles. Risk of collision.
- Method 3 In the smart car, the flashing lights of the car lights indicate that the smart car is at risk of collision with surrounding obstacles. For dangerous situations, the driver's attention can also be reminded by means of fast flashing lights.
- the original driving trajectory determined by the decision-making module may be changed, and the original driving trajectory needs to be further re-planned or adjusted according to the current road conditions of the smart car. , And then ensure that the smart car reaches the destination designated by the driver smoothly.
- the smart car can also receive a speed selected by the driver through an interface or voice. After receiving the aforementioned speed control instruction, the smart car can be controlled to drive at this speed.
- the human-computer interaction system can also allow the driver to understand the environment of the smart car, reducing the driver’s fear of not being able to know the driving area of the smart car in an emergency. In an emergency, the driver can also decide whether to switch the driving mode to the manual driving mode through the situation displayed by the manual interaction system, and the driver will take over the control of the smart car.
- the collision risk of the obstacle and the self-vehicle in addition to using the relative speed and distance between the obstacle and the self-vehicle to confirm the collision potential energy, and then confirm the collision risk between the obstacle and the self-vehicle, it is also possible to determine the collision risk of the obstacle and the self-vehicle. Different weights are added to the vehicle, and the specific weights can be set to consider the degree of damage caused by collisions between different types of obstacles and the self-vehicle. Furthermore, the optimal direction and speed of obstacle avoidance are determined based on the above-mentioned collision damage degree.
- other obstacles can also send other vehicle information to the smart car, including other vehicles.
- the trajectory information and the obstacle avoidance process of the smart car can also be combined with the information of the above-mentioned vehicle to realize the obstacle avoidance process of the smart car.
- other obstacles can send information to the smart car through the vehicle to everything (V2X) communication technology.
- V2X vehicle to everything
- the safest direction can also be selected as the direction of the second speed according to the degree of collision risk with the obstacle, where the degree of collision risk Including one or more of the probability of collision with an obstacle, the degree of damage caused by the collision, etc.
- the degree of damage caused by a collision can be calibrated according to the size, relative speed and relative distance of the obstacle, the larger the obstacle, the relative speed The faster and the shorter the relative distance, the higher the degree of damage in a collision.
- the optimal direction can be selected to avoid obstacles according to the degree of collision risk, so as to further improve the safety of automatic driving.
- the aforementioned collision risk level can be displayed to the driver through a human-computer interaction interface, and the driver selects the direction of the final speed, and then controls the vehicle to drive at the speed selected by the driver.
- FIG. 14 is a schematic diagram of a vehicle control device 500 provided by this application.
- the device 500 includes an acquiring unit 501, and the acquiring unit 501 is configured to acquire the first area planned to drive the smart car in the first area.
- a speed; the first area is an area in the process of the smart car driving to the destination; obtaining a second speed planned for the smart car in the first area; the second speed is obtained according to the collision potential energy ;
- the first speed and the second speed respectively include a direction and a magnitude; the first speed, the second speed and the risk of collision of the smart car with surrounding obstacles are used to determine the maximum of the smart car Optimal speed.
- the optimal speed includes size and direction.
- the collision potential energy is used to identify the collision tendency between the surrounding obstacles and the smart car.
- the device 500 further includes a control unit 502, configured to determine, according to the first speed, the second speed, and the risk of collision between the smart car and surrounding obstacles, for determining the anti-collision of the smart car
- the optimal speed, the optimal speed includes size and direction.
- control unit 502 further includes a first decision-making unit 5021, configured to receive a speed control instruction, and use the speed control instruction to control the driving of the smart car.
- a first decision-making unit 5021 configured to receive a speed control instruction, and use the speed control instruction to control the driving of the smart car.
- control unit 502 further includes a second decision unit 5022, configured to: when a first preset condition is satisfied, the optimal speed is the first speed; wherein, the first preset condition is The collision potential energy of any one of the surrounding obstacles is less than the first threshold.
- a second decision unit 5022 configured to: when a first preset condition is satisfied, the optimal speed is the first speed; wherein, the first preset condition is The collision potential energy of any one of the surrounding obstacles is less than the first threshold.
- control unit 502 further includes a second decision unit 5022, which is further configured to: when a second preset condition is satisfied, the optimal speed is the second speed; wherein, the second preset condition Is that the collision potential energy of any one of the surrounding obstacles is greater than or equal to a first threshold.
- the device 500 further includes an interaction unit 503 for prompting the smart car that there is a risk of collision in at least one of the following ways; or, prompting the smart car through text on the on-board display interface of the smart car There is a risk of collision with the surrounding obstacle, and the first speed and the second speed; or, in the smart car, a voice prompts that the smart car has a risk of collision with the surrounding obstacle, and The first speed, the second speed, and the optimal speed; or, in the smart car, the seat vibration prompts the smart car to have a collision risk with the surrounding obstacles; or, in the smart car In the car, the flashing lights of the car lights indicate that the smart car has a collision risk with the surrounding obstacles.
- the first decision unit 5021 is used to implement the function of obtaining the first speed in the working channel in the above method
- the second decision unit 5022 is used to implement the function of obtaining the second speed in the safe channel in the above method.
- the first decision-making unit 5021 and the second decision-making unit 5022 can also be combined into one decision-making unit, and the decision-making unit is used to realize the functions of determining the first speed and the second speed for the safe passage and the working passage respectively.
- the apparatus 500 of the embodiment of the present application may be implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD).
- ASIC application-specific integrated circuit
- PLD programmable logic device
- the above-mentioned PLD may be a complex program logic device. (complex programmable logical device, CPLD), field-programmable gate array (field-programmable gate array, FPGA), general array logic (generic array logic, GAL) or any combination thereof.
- CPLD complex programmable logical device
- FPGA field-programmable gate array
- GAL general array logic
- the vehicle control method shown in FIG. 3 and FIG. 4 can also be implemented by software
- the device 500 and its various modules may also be software modules.
- the device 500 according to the embodiment of the present application may correspond to the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the device 500 are used to implement the respective methods in FIGS. 3 to 4, respectively. For the sake of brevity, the corresponding process will not be repeated here.
- FIG. 15 is a schematic structural diagram of another vehicle control device 600 provided by this application. As shown in the figure, the device 600 includes a calculation unit 601, a decision unit 602, and a control unit 603. Among them,
- the calculation unit 601 is configured to calculate the collision potential energy of the surrounding obstacles of the smart car according to first perception data, where the first perception data includes the relative speed and relative distance between the surrounding obstacles and the smart car;
- the decision-making unit 602 is configured to determine the safe speed of the smart car driving in a first area according to the collision potential energy of the surrounding obstacles, where the first area is a section of the planned path of the smart car;
- the control unit 603 is configured to control the smart car to drive at the safe speed in the first area.
- the collision potential energy is used to identify the collision tendency between the surrounding obstacles and the smart car.
- control unit 603 is further configured to control the smart car to drive at the safe speed in the first area when the collision potential energy of any one of the surrounding obstacles is greater than or equal to a first threshold.
- the calculation unit 601 is further configured to calculate the collision potential energy of the surrounding obstacles by using the following formula:
- k, ⁇ , ⁇ are constant coefficients
- C is a constant
- ⁇ is the relative speed of the first obstacle relative to the smart car
- d is the relative distance of the first obstacle relative to the smart car
- An obstacle is any one of the surrounding obstacles.
- the decision-making unit 602 is further configured to determine the collision risk level of each surrounding obstacle according to the collision potential energy of the surrounding obstacles and a preset threshold, and the collision risk level includes safety, early warning, and Danger; select all surrounding obstacles of a preset collision risk level; determine the safe speed according to the collision potential energy of all surrounding obstacles of the selected preset collision risk level.
- the decision-making unit 602 is further configured to obtain first perception data, the first perception data being the data obtained by analyzing and processing the initial data detected by the perception device of the smart car;
- the smart car is the origin, and the driving direction of the smart car is the X axis;
- the position of the surrounding obstacles in the coordinate system is calculated according to the first perception data, and the position is used to indicate each obstacle The coordinates and the quadrant in the coordinate system.
- the decision-making unit 602 is further configured to identify the maximum safety angle in the area with no obstacles when all surrounding obstacles of the preset safety risk level are distributed in the four quadrants, and use the angle of the maximum safety angle.
- the direction of the bisector is the direction of the safe speed, and the size greater than or equal to the maximum speed of the surrounding vehicles is the size of the safe speed.
- the decision unit 602 is further configured to calculate the collisions of all obstacles of the preset safety risk level in the same quadrant when all surrounding obstacles of the preset safety risk level are distributed in three quadrants.
- the combination of potential energy; determine the orthogonality of the collision potential energy in each quadrant; remove the orthogonality of the collision potential energy sum and/or the collision potential energy sum of all obstacles in the quadrant with obstacles; calculate the collision potential energy sum in the obstacle-free quadrant And/or the orthogonality of the collision potential energy, and the cooperation of all directions in the orthogonality of the collision potential energy and/or the collision potential energy within the obstacle-free quadrant is the direction of the safe speed, which will be greater than or equal to the maximum speed of the surrounding vehicles
- the size of is the size of the safe speed.
- the decision unit 602 is further configured to calculate all surrounding obstacles of the preset collision risk level in the same quadrant when all surrounding obstacles of the preset safety risk level are distributed in two adjacent quadrants. And determine the orthogonal direction of each collision potential energy sum; calculate the orthogonal direction of the collision potential energy sum in the quadrant without obstacles as the direction of the safe speed, which is greater than or equal to the preset collision risk level
- the maximum speed of all surrounding vehicles of all surrounding vehicles is the magnitude of the safe speed.
- the decision-making unit 602 is further configured to calculate that all surrounding vehicles with the preset collision risk level in the same quadrant are in the same quadrant when all surrounding obstacles of the preset safety risk level are distributed in two adjacent quadrants. Collision potential energy sum, and determine the orthogonality of each collision potential energy sum; compare the collision potential energy sum of the obstacles in the two quadrants in the obstacle-free quadrant.
- the collision potential energy sum in the two quadrants calculates the collision in the two quadrants
- the combination of the potential energy is combined with the cooperation of the collision potential energy in the two quadrants as the safe speed; when the collision potential energy in the two quadrants are not equal, the orthogonal combination of the collision potential energy in the two quadrants is calculated, and the The orthogonal cooperation of the collision potential energy in the two quadrants is the safe speed.
- the orthogonal magnitude of the collision potential energy sum is the magnitude of the collision potential energy sum
- the direction is the direction perpendicular to the collision potential energy sum.
- the decision unit 602 is further configured to calculate all surrounding obstacles of the preset collision risk level in the same quadrant when all surrounding obstacles of the preset safety risk level are distributed in two non-adjacent quadrants.
- the collision potential energy of the object is combined, and the orthogonality of each collision potential energy combination is determined; the orthogonal combination of the collision potential energy combination belonging to the same quadrant is calculated, and the orthogonal combination of the collision potential energy combination of the same quadrant is calculated Any one direction is the magnitude of the safe speed, and the magnitude greater than or equal to the maximum speed in the surrounding vehicles is the magnitude of the safe speed.
- the decision-making unit 602 is further configured to calculate the collision potential energy sum of all surrounding vehicles of the preset collision risk level when it is determined that all surrounding vehicles of the preset collision risk level are only distributed in one quadrant, so as to calculate the collision potential energy sum of all surrounding vehicles of the preset collision risk level.
- the orthogonal direction of is the direction of the safe speed, and the magnitude greater than or equal to the maximum speed of the surrounding vehicles is the magnitude of the safe speed.
- the decision unit 602 is further configured to determine whether the direction of the safe speed belongs to a feasible range, and the feasible range is an area that meets the following criteria: no collision with dynamic obstacles, no collision with static obstacles Collision and non-violation of traffic rules.
- dynamic obstacles include motor vehicles, pedestrians, and animals; static obstacles include barriers, guardrails, paths, street lights and other infrastructure; traffic rules include retrograde, running red lights; when the direction of the safe speed When it belongs to the feasible range, the safe speed is sent to the control unit 603, and the control unit 603 controls the smart car to drive at the safe speed in the first area.
- the apparatus 600 of the embodiment of the present application can be implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), and the above-mentioned PLD can be a complex program logic device. (complex programmable logical device, CPLD), field-programmable gate array (field-programmable gate array, FPGA), general array logic (generic array logic, GAL) or any combination thereof.
- ASIC application-specific integrated circuit
- PLD programmable logic device
- CPLD complex programmable logical device
- FPGA field-programmable gate array
- GAL general array logic
- the vehicle control method shown in FIG. 3 and FIG. 4 can also be implemented by software
- the device 600 and its various modules may also be software modules.
- the device 600 may correspond to the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the device 600 are used to implement the respective methods in FIGS. 3 to 4, respectively.
- the decision-making module 602 of the device 600 may correspond to the second decision-making module 5022 in the device 500, and is used to implement the process of determining the second speed by the decision-making and anti-collision module in the safe passage.
- FIG. 16 is a schematic diagram of a controller 700 provided by an embodiment of the application.
- the controller 700 includes a processor 701, a memory 702, a communication interface 703, and a memory 704.
- the processor 701, the memory 702, the communication interface 703, and the memory 704 communicate through the bus 705.
- the memory 702 is used to store instructions, and the processor 701 is used to execute instructions stored in the memory 702.
- the memory 702 stores program codes, and the processor 701 can call the program codes stored in the memory 702 to perform the following operations:
- the first area is an area in the process of the smart car driving to the destination; acquire the first speed at which the smart car is planned to travel in the first area Two speed; the second speed is obtained according to the collision potential energy;
- the first speed and the second speed respectively include a direction and a magnitude; the first speed, the second speed and the collision risk of the smart car with surrounding obstacles are used to determine the optimal value of the smart car Speed, the optimal speed includes size and direction.
- the processor 701 may be a CPU, and the processor 701 may also be other general-purpose processors, digital signal processing (DSP), application-specific integrated circuits (ASIC), on-site Programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- DSP digital signal processing
- ASIC application-specific integrated circuits
- FPGA on-site Programmable gate array
- the general-purpose processor may be a microprocessor or any conventional processor.
- the controller 700 may include multiple processors.
- FIG. 16 includes a processor 701 and a processor 706.
- the processor 701 and the processor 706 may be different types of processors, and each type of processor includes one or more chips.
- the memory 702 may include a read-only memory and a random access memory, and provides instructions and data to the processor 701.
- the memory 702 may also include a non-volatile random access memory.
- the memory 702 may also store device type information.
- the memory 702 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
- the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
- the volatile memory may be random access memory (RAM), which is used as an external cache.
- RAM random access memory
- SRAM static random access memory
- DRAM dynamic random access memory
- SDRAM synchronous dynamic random access memory
- Double data rate synchronous dynamic random access memory double data date SDRAM, DDR SDRAM
- enhanced SDRAM enhanced synchronous dynamic random access memory
- SLDRAM synchronous connection dynamic random access memory
- direct rambus RAM direct rambus RAM
- bus 704 may also include a power bus, a control bus, and a status signal bus. However, for clear description, various buses are marked as bus 704 in the figure.
- the bus 704 may also be a vehicle-mounted Ethernet or controller area network (controller area network, CAN) bus or other internal buses.
- controller may correspond to the device 500 and the device 600 in the embodiment of the present application, and may correspond to the corresponding main body that executes the method shown in FIG. 3 and FIG. 4 in the embodiment of the present application, and
- the foregoing and other operations and/or functions of the various modules in the controller 700 are used to implement the corresponding procedures of the methods in FIGS. 3 to 4, and are not repeated here for brevity.
- processor 701 of the controller 700 shown in FIG. 16 may call the program code stored in the memory 702 to perform the following operations:
- the first perception data including the relative speed and the relative distance between the surrounding obstacles and the smart car
- controller 700 may correspond to the apparatus 500 and the apparatus 600 in the embodiment of the present application, and may correspond to the corresponding main body that executes the method shown in FIG. 3 and FIG. 4 according to the embodiment of the present application.
- the foregoing and other operations and/or functions of each module in the controller 700 are used to implement the corresponding processes of the methods in FIGS. 3 to 4, and are not repeated here for brevity.
- the present application also provides a smart car as shown in FIG. 1 or FIG. 2.
- the smart car includes the controller 700 shown in FIG. 16, and the controller 700 is used to implement the corresponding processes of the above-mentioned methods in FIGS. 3 to 4 , For the sake of brevity, I won’t repeat it here.
- the foregoing embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination.
- the above-mentioned embodiments may be implemented in the form of a computer program product in whole or in part.
- the computer program product includes one or more computer instructions.
- the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
- the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
- the computer instructions may be transmitted from a website, computer, server, or data center.
- the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more sets of available media.
- the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium.
- the semiconductor medium may be a solid state drive (SSD).
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
一种车辆控制的方法,包括:获取在第一区域规划智能汽车行驶的第一速度;获取在该第一区域规划的汽车行驶的第二速度;第二速度是根据碰撞势能获得;第一速度和第二速度分别包括方向和大小;第一速度、第二速度和汽车与周围障碍物的碰撞风险用于确定汽车的最优速度,以此实现汽车有效躲避障碍物,提升汽车行驶的安全性。一种汽车的控制装置、一种汽车的控制器和一种汽车也被公开。
Description
本申请涉及汽车领域,尤其涉及一种智能汽车(smart/intelligent car)防碰撞的方法、装置、控制器和智能汽车。
随着人工智能(artificial intelligent,AI)技术逐步应用于智能汽车领域,越来越多的智能汽车利用以深度学习为代表的人工智能算法实现智能汽车的自动驾驶(automatic driving/ADS)。传统技术中,利用车载传感器收集前方车辆的信息,并由车载控制器基于刹车距离、最小刹车时间判断碰撞是否发生,一旦控制器判断会发生碰撞,则实施智能汽车的制动操作。上述防碰撞方案中仅针对自车与车辆的距离和最小刹车时间决策是否制动,容易引起误判或漏判,造成人员受伤或车辆受损。另外,在复杂场景下,如果有多个方向同时存在碰撞可能或部分车辆逆行,仅执行制动操作可能无法有效避免与其他车辆的碰撞。因此,如何提供一种更有效的躲避障碍物的车辆控制方法成为亟待解决的技术问题。
发明内容
本申请提供了一种车辆控制的方法、装置、控制器和智能汽车,应用于智能汽车,可以实现一种更有效的智能汽车防碰撞功能,提升智能汽车在自动驾驶过程中安全性。
第一方面,提供一种车辆控制的方法,该方法包括:获取在第一区域规划所述智能汽车行驶的第一速度;所述第一区域为所述智能汽车行驶至目的地过程中一段区域;获取在所述第一区域规划所述智能汽车行驶的第二速度;所述第二速度是根据碰撞势能获得;其中,所述第一速度和所述第二速度分别包括方向和大小;所述第一速度、第二速度和所述智能汽车与周围障碍物的碰撞风险用于确定所述智能汽车的最优速度,所述最优速度包括大小和方向。通过上述方法,智能汽车可以通过双通道的冗余设计,分别为智能汽车规划在同一区域行驶的第一速度和第二速度,再根据智能汽车与周围障碍物的碰撞风险确定最优速度,进而实现智能汽车以最优速度躲避周围障碍物,避免出现自车与周围障碍物的碰撞,减少智能汽车中乘车人员和车辆的损伤,提升智能汽车在自动驾驶过程中安全性。
在一种可能的实现方式中,碰撞势能用于标识智能汽车的周围障碍物与所述智能汽车发生碰撞的趋势。本申请中安全通道可以通过碰撞势能识别与自车发生碰撞的障碍物,并以碰撞势能为基础进一步确定第一速度,控制智能汽车以第一速度行驶可以有效实现避障过程。
在另一种可能的实现方式中,根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定所述智能汽车防碰撞的最优速度,所述最优速度包括大小和方向。通过上述方法的描述,本申请提供的车辆控制方法中,可以由智能汽车根据自车与障碍物的碰撞风险从第一速度、第二速度中选择一个速度作为最优速度,并以此速度控制智能汽车行驶,进而实现有效躲避周围障碍物的碰撞,提升智能汽车的安全性。
在另一种可能的实现方式中,接收速度控制指令,以所述速度控制指令控制所述智能汽车行驶。本申请提供的方法中,智能汽车可以将第一速度和第二速度以界面显示屏等方式呈现给驾驶员,由驾驶员选择第一速度或第二速度控制智能汽车的行驶,此时,驾驶员选择的速度可以以速度控制指令的形式发送至智能汽车的控制器,由智能汽车的控制器根据该速度 控制指令控制智能汽车行驶。
可选地,驾驶员也可以通过界面显示屏切换驾驶模式为人工驾驶,并控制智能汽车按照当前驾驶员的操作行驶。本申请中通过界面显示屏向驾驶员提示碰撞风险,驾驶员可以直接接管智能车的控制权,进而实现人为控制智能汽车行驶。
在另一种可能的实现方式中,当智能汽车由控制器控制车辆行驶,且满足第一预设条件时,最优速度为所述第一速度;其中,第一预设条件为任意一个周围障碍物的碰撞势能小于第一阈值。本申请提供的车辆控制方法中,可以通过障碍物的碰撞势能确定智能汽车行驶的速度,当任意一个障碍物与自车碰撞的方向小于第一阈值时,则可以以工作通道确定的速度控制车辆行驶。也就是说,当无障碍物存在预设的碰撞风险时,则可以以工作通道确定的速度控制车辆行驶,以此实现避障过程,提升智能汽车的安全性。
在另一种可能的实现方式中,当智能汽车由控制器控制车辆行驶,且满足第二预设条件时,最优速度为第二速度;其中,第二预设条件为任意一个周围障碍物的碰撞势能大于或等于第一阈值。本申请提供的车辆控制方法中,根据周围障碍物的碰撞势能判断障碍物与自车发生碰撞的趋势,当任意一个自车周围的障碍物的碰撞势能大于或等于第一阈值时,则采用安全通道所确定的第二速度控制智能汽车行驶。也就是说,当存在任意一个周围障碍物达到预设的碰撞风险时,则按照安全通道确定的速度控制车辆行驶,以此实现避障的过程,提升智能汽车的安全性。
在另一种可能的实现方式中,智能汽车可以通过以下方式中至少一种提示所述智能汽车存在碰撞风险:在智能汽车的车载显示界面通过文字提示智能汽车与所述周围障碍物存在碰撞风险,第一速度和第二速度;或者,在智能汽车中通过语音提示智能汽车与周围障碍物存在碰撞风险,第一速度和第二速度;或者,在智能汽车中通过座椅震动提示智能汽车与周围障碍物存在碰撞风险;或者,在智能汽车中通过车灯闪灯提示智能汽车与周围障碍物存在碰撞风险。通过上述方法,可以实现智能汽车与驾驶员的消息交互,对于危险情况可以及时提示驾驶员潜在的风险,并允许驾驶员接管或控制智能汽车的驾驶过程,由此减少驾驶员在无知情况下所带来的恐惧,提升驾驶体验。
可选地,上述提示方式中还可以将最终车辆行驶的最优速度呈现给驾驶员,让驾驶员了解车辆规划的避障过程和速度,增加人车交互过程,提升用户体验。
通过上述内容的描述,本申请提供的车辆控制方法可以由安全通道和工作通道分别规划在第一区域的速度,由控制器选择一个速度作为最优速度,或者控制器接收驾驶员所选择的速度,进而按照最优速度或驾驶员所选择的速度控制车辆行驶,实现有效的避障过程,提升智能汽车的安全性。进一步地,本申请提供的车辆控制方法可以基于障碍物的碰撞势能,利用势能分解合并方法获得在任意一个区域中满足高功能安全要求的最优速度,再通过可行区域进行校验,最终确定智能汽车避障的最优速度。通过周围障碍物与自车的距离和相对速度综合考虑自车与障碍物发生碰撞的可能,更好的识别车辆间的碰撞风险,以此解决传统技术中仅基于刹车距离、最小刹车时间的判断方法所带来的误判或漏判的问题。而且,本申请提供的方法不仅能够避免与来自自车前方的车辆的碰撞,还能避免与来自自车后方、侧方等各个方向的碰撞,相比于传统技术方法中仅能对来自自车前方的车辆的碰撞,提升了智能汽车的避障能力,不仅能够控制智能汽车减速,还能控制智能汽车按照确定的避障方向加速行驶避障,进而使得智能汽车可以实现各个方向的避障的效果。另一方面,本申请提供的方法提供的避障方向和速度更加精准,能够保证智能汽车按照当前时刻最有的安全方向和速度实现避障,避免自车与周围车辆发生碰撞。
第二方面,本申请提供另一种车辆控制的方法,该方法包括:根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能,所述第一感知数据包括所述周围障碍物与所述智能汽车的相对速度和相对距离;根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,所述第一区域为所述智能汽车规划路径中一段区域;控制所述智能汽车在所述第一区域以所述安全速度行驶。本申请提供的上述方法可以利用周围障碍物的碰撞势能确定安全速度,并以此安全速度控制智能汽车在第一区域行驶,以此实现智能汽车的避障过程,减少车载人员和车辆的损伤,提升智能汽车的安全性。
在一种可能的实现方式中,碰撞势能用于标识所述周围障碍物与所述智能汽车的碰撞趋势。
在另一种可能的实现方式中,可以利用如下公式计算所述周围障碍物的碰撞势能:
其中,k、α、β是常系数,C是常量,ν是第一障碍物相对于所述智能汽车的相对速度的大小,d是第一障碍物相对于所述智能汽车的相对距离,第一障碍物是所述智能汽车的周围障碍物中任意一个。
在另一种可能的实现方式中,根据所述周围障碍物的碰撞势能和预设阈值确定所述每个周围的障碍物的碰撞风险等级,所述碰撞风险等级包括安全、预警和危险;选择预设碰撞风险等级的所有周围的障碍物;根据所选择的所述预设碰撞风险等级的所有周围的障碍物的碰撞势能确定所述安全速度。本申请中控制器可以根据预设碰撞风险等级在所有周围障碍物中选择部分周围障碍物,进一步根据各个障碍物的碰撞势能确定避障的安全速度,能够减少控制器的计算量和处理时长。
在另一种可能的实现方式中,获取第一感知数据,所述第一感知数据为所述智能汽车的感知设备探测获得初始数据经过分析和处理后所获得的数据;建立以所述智能汽车为原点的坐标系;根据所述第一感知数据计算所述周围障碍物在所述坐标系中的位置,所述位置用于指示所述每个障碍物在所述坐标系中坐标和所在象限。
在另一种可能的实现方式中,智能汽车的自车坐标系可以是以自车的质心为原点,行驶方向为X轴正向的坐标系。可选地,该坐标系还可以以自车的车头中点或车尾中点作为原点。
在另一种可能的实现方式中,当所述预设安全风险等级的所有周围障碍物分布在四个象限时,识别无障碍物的区域中最大安全角度,以最大安全角度的角平分线方向作为安全速度的方向,大于或等于周围车辆的最大速度的大小为安全速度的大小。
在另一种可能的实现方式中,当所述预设安全风险等级的所有周围障碍物分布在三个象限时,分别计算同一象限内所有预设安全风险等级的所有障碍物的碰撞势能的合;确定每个象限中碰撞势能合的正交;去掉有障碍物的象限内的所有障碍物的碰撞势能合和/或碰撞势能合的正交;计算无障碍物象限内碰撞势能合和/或碰撞势能合的正交,将所述无障碍物象限内碰撞势能合和/或碰撞势能合的正交中所有方向的合作为安全速度的方向,将大于或等于周围车辆的最大速度的大小为安全速度的大小。其中,其中,所述两个象限中碰撞势能合的合的方向为所述安全速度的方向,所述两个象限中碰撞势能合的合的大小为所述安全速度的大小;碰撞势能合和/或碰撞势能合的正交包括以下两种情况的任意一种:碰撞势能合和碰撞势能合的正交、碰撞势能合或碰撞势能合的正交。
在另一种可能的实现方式中,当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定 每个碰撞势能合的正交方向;去掉有障碍物的象限内的正交方向;计算无障碍物的象限内的碰撞势能合的正交方向的合为安全速度的方向,以大于或等于预设碰撞风险等级的所有周围车辆的所有周围车辆最大速度的大小为安全速度的大小。
在另一种可能的实现方式中,当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,计算在同一象限内所有预设碰撞风险等级的周围车辆在碰撞势能合,并确定每个碰撞势能合的正交;去掉有障碍物象限内的碰撞势能合的正交;在无障碍物象限内比较两个象限中障碍物的碰撞势能合,当两个象限中碰撞势能合相等时,计算两个象限中碰撞势能合的合,并以该两个象限中碰撞势能合的合作为安全速度。当两个象限中碰撞势能合不等时,计算两个象限中碰撞势能合的正交的合,并以该两个象限中碰撞势能合的正交的合作为安全速度。其中,碰撞势能合的正交的大小为碰撞势能合的大小,方向为垂直于碰撞势能合的方向。
在另一种可能的实现方式中,当所述预设安全风险等级的所有周围障碍物分布在两个不相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定每个碰撞势能合的正交;计算属于同一象限的所述碰撞势能合的正交的合,以所述同一象限的所述碰撞势能合的正交的合的任意一个方向为所述安全速度的大小,大于或等于周围车辆中最大速度的大小为所述安全速度的大小。
在另一种可能的实现方式中,当判断预设碰撞风险等级的所有周围车辆仅分布在一个象限时,计算所有预设碰撞风险等级的周围车辆的碰撞势能合,以碰撞势能合的正交方向为所述安全速度的方向,大于或等于周围车辆最大速度的大小为所述安全速度的大小。
在另一种可能的实现方式中,判断所述安全速度的方向是否属于可行范围,所述可行范围为满足以下标准的区域:不与动态障碍物发生碰撞、不与静态障碍物发生碰撞、不违背交通规则,其中,动态障碍物包括机动车、行人、动物;静态障碍物包括隔离带、护栏、路径、路灯等基础设施;交通规则包括逆行、闯红灯;当所述安全速度的方向属于所述可行范围时,控制所述智能汽车在所述第一区域以所述安全速度行驶。
作为另一种可能的实现方式,当安全通道确认的第二速度有多个方向时,还可以根据与障碍物的碰撞危险程度选择最安全的方向作为第二速度的方向,其中,碰撞危险程度包括与障碍物发生碰撞的概率、发生碰撞的损伤程度等因素中一种或多种,发生碰撞的损伤程度可以根据障碍物的大小、相对速度和相对距离进行标定,障碍物越大、相对速度越快、相对距离越短,发生碰撞的损伤程度越高。
第三方面,本申请提供一种车辆控制的装置,所述装置包括用于执行所述第一方面或第一方面任一种可能实现方式中的所述车辆控制方法的各个模块。
第四方面,本申请提供一种车辆控制的装置,所述装置包括用于执行第二方面或第二方面任一种可能实现方式中的所述车辆控制方法的各个模块。
第五方面,本申请提供一种车辆控制的控制器,所述控制器包括处理器、存储器、通信接口、总线,所述处理器、存储器和通信接口之间通过总线连接并完成相互间的通信,所述存储器中用于存储计算机执行指令,所述控制器运行时,所述处理器执行所述存储器中的计算机执行指令以利用所述控制器中的硬件资源执行所述第一方面或第一方面任一种可能实现方式中所述方法的操作步骤。
第六方面,本申请提供一种车辆控制的控制器,所述控制器包括处理器、存储器、通信接口、总线,所述处理器、存储器和通信接口之间通过总线连接并完成相互间的通信,所述存储器中用于存储计算机执行指令,所述控制器运行时,所述处理器执行所述存储器中的计 算机执行指令以利用所述控制器中的硬件资源执行第二方面或第二方面任一种可能实现方式中所述方法的操作步骤。
第七方面,本申请提供一种智能汽车,所述智能汽车包括控制器,所述控制器用于实现第五方面及第五方面的任意一种可能的实现方式中所述控制器实现的功能,或者上述控制器用于实现第六方面及第六方面的任意一种可能的实现方式中所述控制器实现的功能。
第八方面,本申请提供一种计算机可读存储介质,所述计算机可读存储介质中存储有指令,当其在计算机上运行时,使得计算机执行上述各方面所述的方法或功能。
第九方面,本申请提供了一种包含指令的计算机程序产品,当其在计算机上运行时,使得计算机执行上述各方面所述的方法或功能。
本申请在上述各方面提供的实现方式的基础上,还可以进行进一步组合以提供更多实现方式。
图1为本申请提供的一种智能汽车的架构示意图;
图2为本申请提供的另一种智能汽车的架构示意图;
图3为本申请提供的一种车辆控制方法的流程示意图;
图4为本申请提供的另一种车辆控制方法的流程示意图;
图5为本申请提供的一种智能汽车坐标系的示意图;
图6为本申请提供的一种计算障碍物与自车的相对速度的方法的示意图;
图7为本申请提供的一种障碍物碰撞碰撞风险等级划分的示意图;
图8为本申请提供的一种障碍物分布在四个象限的示意图;
图9为本申请提供的一种障碍物分布在三个象限的示意图;
图10为本申请提供的一种障碍物分布在相邻的两个象限的示意图;
图11为本申请提供的一种障碍物分布在不相邻的两个象限的示意图;
图12为本申请提供的一种障碍物分布在同一个象限的示意图;
图13为本申请提供的一种智能汽车中人机交互系统的示意图;
图14为本申请提供的一种车辆控制装置的结构示意图;
图15为本申请提供的另一种车辆控制装置的结构示意图;
图16为本申请提供的一种控制器的结构示意图。
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述
图1为本申请提供的一种智能汽车的架构示意图,如图所示,智能汽车100包括控制器101、感知设备102、交互系统103和执行系统104。其中,感知设备102用于通过传感器获取智能汽车周围的车辆、人和基础设施等障碍物的信息,包括障碍物的图像、探测信息,其中,探测信息可以根据感知设备类型不同而不同,例如,当感知设备为激光雷达时,激光雷达可以向目标发射探测信号(例如,激光束),然后,将接收到的从目标反射回来的信号(例如,目标回波)与发射信号进行比较,作适当处理后,就可获得目标的有关探测信息,如目标距离、方位、高度、速度、姿态、甚至形状等参数。上述障碍物的信息会发送给控制器101,由控制器101根据障碍物的信息进一步确定智能汽车到达目的地的行驶轨迹,再向执行系统104发送包括速度的控制指令,由执行系统104控制智能汽车行驶。其中,速度为矢量,包括大 小和方向,速度的大小也可以称为速率。为了满足智能汽车安全行驶的高功能安全要求,控制器101中可以利用冗余的双通道设计,分别计算在同一段区域中行驶的速度。
具体地,控制器可以包括工作通道和安全通道,工作通道用于利用人工智能算法规划智能汽车的行驶的速度;安全通道则定义了一种智能汽车自身与障碍物之间的势函数,基于势能分解合并方法规划智能汽车避障的速度,防止碰撞发生。控制器101可以利用工作通道和安全通道分别确定在行驶轨迹中同一段区域中行驶的速度,再由控制器101根据预设条件确定所要选择的最终速度。其中,由控制器101选择的最终速度也可以称为最优速度,势能分解合并方法也可以称为矢量分解合并方法。
值得说明的是,本申请的以下实施例中,除特殊说明外“速度”均指包含大小和方向。
图1中还包括交互系统103,该交互系统103用于实现智能汽车100与驾驶员的消息交互,使得驾驶员可以通过交互系统103向智能汽车发送操作指示,并通过交互系统103了解智能汽车的当前状态。
作为一个可能的实施例,除了由控制器101根据预设条件选择工作通道或安全通道确定的速度为智能汽车行驶的最优速度之外,智能汽车100还包括仲裁器105,由仲裁器105分别接收工作通道1011规划的速度和安全通道1012规划的速度,并由仲裁器105根据预设条件选择智能汽车行驶的最优速度。
图2为本申请提供的另一种智能汽车的架构示意图,如图所示,图2进一步展示了图1中智能汽车100中各部分的逻辑结构。其中,感知设备102包括图像采集设备1021、激光雷达1022和毫米波雷达1023等具有探测和识别周围物体的能力的传感器中的一种或多种。另外,同一辆智能汽车中部署同一种传感器的数量不构成对本申请所要保护的技术方案的限定。
控制器101包括工作通道1011和安全通道1012的双通道冗余设计。工作通道1011用于利用人工智能算法进行感知、决策和路径规划,输出智能汽车的安全方向和速度,使得智能汽车能够满足质量管理(quality management,QM)要求。工作通道1011,包括第一感知模块10111和决策模块10112。第一感知模块10111用于收集感知设备采集的智能车辆周围的障碍物的信息,并针对障碍物信息进行处理得到路况信息,如障碍物类型、速度、大小、道路等基础设施情况(如当前方向车道数量、交通标识等)。决策模块10112用于根据第一感知模块10111提供的路况信息进一步确定在一段区域内行驶的方向和速度。安全通道1012包括第二感知模块10112、决策和防碰撞模块10122。其中,决策和防碰撞模块10122用于根据第二感知模块10112提供的障碍物的信息,如障碍物相对于自车的距离和相对速度。采用势能分解合并方法进一步确定在一段区域内行驶的方向和速度,使得智能汽车行驶能够满足安全等级满足汽车安全完整性等级ASIL D等级要求。其中,ASIL等级是汽车安全完整性等级,用来描述组件或系统实现既定安全目标的概率。ASIL等级由三个基本要素决定,分别是严重度(severity,S)、暴露率(exposure,E)、可控性(controllability,C)。严重度,用于指示风险一旦发生,车内人员的生命财产遭受损害的严重程度;暴露率,用于指人员或财产遭受损害的概率;可控性,用于描述风险成为现实时驾驶员可在多大程度上采取主动措施避免损害发生。ASIL等级由高到低可分为D、C、B、A四个等级,D级安全风险最小,A级安全风险最大。在四个安全等级之外还有一个质量管理要求,该指令管理要求无安全方面要求,对于自动驾驶模式来说,安全风险相比于ASIL更大。
作为一种可能的实现方式,图2中第一感知模块10111和第二感知模块10112可以合并为一个感知模块,该合并后的感知模块从传感设备102中获得障碍物的信息,并据此信息进一步计算障碍物相对于智能汽车的距离和障碍物相对于智能汽车的相对速度等路况信息,并 根据决策模块10112和决策和防碰撞模块10122所需的信息,分别向其发送所需内容。
图2所示控制器中第一感知模块10111、决策模块10112、第二感知模块10121、决策和防碰撞模块10122和仲裁模块105可以由硬件实现,也可以由软件实现,或者由硬件和软件共同实现相应的功能。
作为一种可能的实现方式,图1和图2仅是本申请提供的一种智能汽车的架构示意图,仲裁器可以由控制器中软件或硬件实现其功能。仲裁器也可以由独立的处理器实现冗余通道选择的作用。为了便于描述,本申请的以下描述中以仲裁器为控制器中一个模块为例进行描述。另外,为了便于描述本申请提供的防碰撞的方法,以下实施例中以周围障碍物为周围车辆为例进行描述。
图3为本申请提供的一种车辆控制方法的流程示意图,该方法由图2中智能汽车的控制器101中的决策模块10112、决策和防碰撞模块10122和仲裁模块105,以及智能汽车的控制系统104执行,如图所示,该方法包括:
S210、决策模块获取第一感知模块获知的智能汽车的第一感知数据。
第一感知模块可以通过感知设备获取智能汽车周围车辆的信息,比如障碍物的类型、状态、速度、大小、道路标识等。示例地,当传感设备包括图像采集设备时,可以通过采集图像获取周围障碍物的信息,第一感知模块可以根据图像分析障碍物的类型、大小、道路标识等。当传感设备为激光雷达时,光束会在碰到物体后经过漫反射返回到激光雷达,第一感知模块则可以根据激光雷达发送和接收信号的时间间隔乘以光速,再除以2,就能计算出激光雷达与物体的距离。通过两束或多束光可以获知障碍物相对智能汽车的移动的距离,再结合两束光速传输的时间可以进一步计算障碍物相对于智能汽车的相对速度。第一感知模块可以将包括上述障碍物与智能汽车的距离和障碍物相对于智能汽车的速度作为第一感知数据,发送给决策模块。
S211、决策模块计算在第一区域中行驶的第一速度。
智能汽车行驶过程中会根据目的地、驾驶员的驾驶习惯和地图规划智能汽车到达目的地的整个路径规划。但是,由于行驶的过程中路况复杂,决策模块还需要根据当前时刻行驶区域的路况对智能汽车的行驶轨迹进行规划,例如,决策模块会根据第一感知数据实时或周期性获知整个路径规划中一段区域的路况。为了便于说明,本申请以下实施例以该段区域为第一区域为例进行说明,其中,第一区域的长度由传感设备所能探测的障碍物的范围和智能汽车中决策模块的计算能力决定。
决策模块可以根据第一感知数据确定障碍物的位置和与智能汽车的相对速度,以及智能汽车目标车速确定智能汽车行驶的方向和速度。控制器中工作通道所确定的方向和速度可以称为第一速度,也可以称为工作速度,为了便于描述,以下实施例中以第一速度为工作通道中决策模块确定的方向和速度为例进行说明。
示例地,决策模块可以根据驾驶员指定的目的地,车载地图、定位系统,以及周围障碍物的信息规划智能汽车在第一区域的第一速度。本申请对决策模块确认第一方速度的方法并不作限定,具体实施时可以根据业务需求采用适应的方法确定第一速度。
S212、决策模块向仲裁模块发送第一速度。
S213、决策和防碰撞模块获取第二感知模块发送的智能汽车的第二感知数据。
决策和防碰撞模块也可以利用与步骤S210类似的方法从第二感知模块获得第二感知数据,其中,第二感知数据包括周围车辆与自车的相对距离、相对速度,相对位置,其中,相对位置可以根据传感设备接收的光速的角度和相对距离计算获得,例如,传感设备获得障碍 物的接收光速的角度为30度,决策和防碰撞模块则可以根据该角度和相对距离确定障碍物在自车坐标系中的位置。
S214、决策和防碰撞模块计算智能汽车在第一区域中行驶的第二方速度。
决策和防碰撞模块可以基于势能分解合并的方法寻找智能汽车避障的速度。控制器中安全通道所确定的速度可以称为第二速度,也可以称为安全速度,为了便于描述,以下实施例中以第二速度为工作通道中决策模块确定的速度为例进行说明。
参见图4,图4为本申请提供的另一种车辆控制方法的流程示意图,该图具体为决策和防碰撞模块规划智能汽车在第一区域中行驶的第二速度的方法的流程示意图,如图所示,该方法包括:
S300、建立以智能汽车的质心为原点、智能汽车行驶速度方向为X轴正向的二维坐标系,并确定每个周围车辆在二维坐标系中位置。
可选地,自车坐标系也可以是以非质心为原点的坐标系,例如,以自车前方中心位置为原点,或者,以自车的中轴的中点为原点。
可选地,自车坐标系也可以是三维坐标系,其中,每个障碍物在自车坐标系中Z轴的坐标可以取任意值,或者,根据其他车辆所在坐标系的坐标转换至自车坐标系所获得的值。
可选地,自车坐标系的X轴除了以速度方向为正向外,还可以以其他方式设置X轴的正向,例如,取自车这头的朝向方向为X轴正向。
S301、决策和防碰撞模块根据每个周围车辆的与自车的相对距离和相对速度分别计算每个周围车辆与智能汽车的碰撞势能。
图5为本申请提供的一种智能汽车坐标系的示意图,如图5所示,以智能汽车的质心为原点,智能汽车行驶速度方向为X轴正向,建立二维坐标系。其中,智能汽车的质心可以是以自车的长、宽和高为基准的长方体的中心。
利用传感设备确定本车与障碍物的相对距离和速度,具体过程如下:
1.T时刻测定障碍物的位置O,T'时刻测定障碍物的位置O′。
3.计算自车与障碍物的相对速度,该速度的方向指向智能汽车。
首先,利用公式(1)计算障碍物自身在Δt时间内移动的距离
然后,利用公式(2)计算速度
再利用公式(3)计算障碍物沿智能汽车速度方向的投影
障碍物只有与自车同向且速度的大小接近时才有可能与自车发生碰撞,计算障碍物沿智 能汽车速度方向的投影即确认障碍物与自车可能发生碰撞的速度分量。换句话说,障碍物沿智能汽车速度方向的投影用于指示障碍物沿自车行驶速度方向移动所造成与自车碰撞的趋势。将障碍物沿智能汽车速度方向的投影作为障碍物相对于智能汽车的相对速度。
4.利用公式(4)计算障碍物的碰撞势能。
障碍物O的碰撞势能f(O)用于描述障碍物O可能与智能汽车发生碰撞的趋势,或称为智能汽车为避免障碍物的碰撞所应有的逃逸势能。例如,自车与障碍物越近逃逸的趋势越强烈,障碍物逼近的越快逃逸的趋势越强烈。上述公式中k、α、β是常系数,C是常量,C的取值可以根据仿真结果、实际经验灵活设定。因为速度ν是障碍物相对智能汽车的速度,是一个既有大小又有方向的矢量。因此,f也是一个矢量且方向与v的方向相同。值得说明的是,计算f(O)的大小时,则取v的大小带入上述公式计算获得障碍物的碰撞势能。f在x、y方向上的投影分别为
其中,v
x和v
y分别是ν在X轴和Y轴的坐标。
可选地,障碍物的碰撞势能也可以利用公式(5)或公式(6)计算获得:
f(O)=f
1(v)+f
2(d)+C 公式(6)
进一步地,决策和防碰撞模块可以根据周围车辆与自车的相对位置确定每个周围车辆在图5所示坐标系中位置。具体地,当以自车为原点的坐标系建立后,该坐标系为二维坐标系,在该二维坐标系的平面中,以周围车辆在该二维坐标系的投影位置作为周围车辆的位置。可选地,确定周围车辆在自车坐标系中位置的方法还包括:将周围车辆在大地坐标系中的坐标转换为二维坐标系,具体实施时可以采用传统技术的方法实现周围车辆在两个坐标系中坐标转换,本申请对此不作限定。
S302(可选地)、根据每个周围车辆的碰撞势能判断每个周围车辆归属的碰撞风险等级。
所有传感设备探测到的障碍物都可以利用上述公式(4)-公式(6)中任意一个公式计算其碰撞势能,但为了节省决策和防碰撞模块的计算能力,提升处理速度,也可以根据预设条件找出存在较高潜在碰撞风险的障碍物,进而根据这些障碍物的碰撞势能确定第二速度。示例地,如图7所示,本申请将周围车辆和自车碰撞的风险划分为三个等级:安全、预警和危险。当障碍物处于安全级别时本车不存在碰撞可能;当障碍物处于预警级别时本车有碰撞可能,控制器可以通过交互系统提示驾驶员手动操作,进而实现避障;当障碍物处于危险级别时,控制器可以在紧急情况接管智能汽车的控制权,避免智能汽车其他模块执行处理中发生紧急情况出现自车与其他车辆碰撞。
值得说明的是,当障碍物处于危险等级时,控制器主动接管的情况仅限于智能汽车处于自动驾驶模式时由其他模块执行计算或数据处理的过程。对于人工驾驶模式,智能汽车的操作由驾驶员完全控制,控制器不干预智能汽车的行驶过程。
可选地,本申请提供的方法也可以不区分碰撞风险等级,直接以所有智能汽车的周围障碍物的碰撞势能为基础确定第二速度,为了便于描述,本申请的以下实施例中以划分障碍物的碰撞风险等级为例进行说明。
图7所示的碰撞风险等级可以根据智能汽车的避障能力(如性能和大小)分别预置碰撞势能|F
1|、|F
2|,当F
2|≤|f|<|F
1|时,障碍物属于预警级别;当|f|≥|F
1|时,障碍物属于危 险级别;当|f|<|F
2|时,障碍物属于安全级别,其中,|F
2|<|F
1|。
可选地,决策和防碰撞模块可以仅针对预警和/或危险等级的周围车辆的碰撞势能确定其与自车发生碰撞的风险。决策和防碰撞模块也可以同时计算所有障碍物的碰撞势能,并基于所有碰撞势能确定其他周围车辆与自车发生碰撞的风险。
在决策和防碰撞模块计算障碍物的势能,以及确认每个障碍物在智能汽车的坐标系下归属的象限后,决策和防碰撞模块优先判断预设碰撞风险等级的周围车辆是否分布在四个象限,然后,逐级判断预设碰撞风险等级的周围车辆是否分布在三个象限、两个象限和一个象限,也就是说决策和防碰撞模块按照与自车碰撞的风险由高至低的顺序逐级判断。可选地,决策和防碰撞模块也可以直接判断所有障碍物分布的象限,根据其分布的不同象限分别利用不同的方法确认第二速度。也就是说,决策和防碰撞模块可以不按照障碍物与自车碰撞的碰撞风险等级逐级进行判断,而是直接考虑障碍物分布的象限,并结合各种情况分别利用不同的方法确认第二速度。
为了便于描述,接下来,结合步骤S303至步骤S311进一步阐述决策和防碰撞模块依据碰撞风险等级确定第二速度的防碰撞方法:
S303、判断预设碰撞风险等级的所有周围车辆是否分布在四个不同象限。
S304、当预设碰撞风险等级的所有周围车辆分布在四个不同象限时,识别最大安全角度,以最大安全角度的角平分线方向作为第二速度的方向,大于或等于周围车辆的最大速度的大小为第二速度的大小。
如图8所示,当预设碰撞风险等级的所有周围车辆分布在四个象限时,理论上来说每个方向均有障碍物存在与自车发生碰撞的风险。决策和防碰撞模块可以先根据预设角度α和预设半径
确定以原点为圆心,α为夹角的弧形区域为周围车辆假设行驶范围,
为根据每个车辆的性能确定的单位时间内可行驶的最远距离。相邻两个障碍物的行驶区域的边界构成新的区域,如图所示,当四个象限中每个象限包括一个周围车辆,且按照预设角度和预设半径划分四个车辆假设行驶范围时,同时还划分了区域1、区域2、区域3和区域4共四个区域,该四个区域均为无障碍物的安全区域。决策和防碰撞模块可以选择夹角最大的区域,并以该最大夹角的角平分线的方向作为智能汽车的避障的第二速度的方向,以大于或等于周围车辆的最大速度方向作为第二速度。例如,图8中假设区域1的夹角β为四个最大夹角的区域,则以该夹角的角平分线方向为第二速度的方向,大于或等于障碍物1、障碍物2、障碍物3和障碍物4的最大速度的大小作为第二速度的大小。其中,预设角度和预设半径可以根据不同周围车辆的型号、大小和性能预先设定,决策和防碰撞模块可以根据该预设规则获得周围车辆假设行驶范围。
S305、当预设碰撞风险等级的所有周围车辆未分布在四个不同象限时,判断预设碰撞风险等级的所有周围车辆是否分布在三个不同象限。
S306、当预设碰撞风险等级的所有周围车辆分布在三个不同象限时,先分别计算同一象限内碰撞势能的合,并确定每个碰撞势能合的正交,去掉有障碍物的象限内的所有障碍物的碰撞势能合或碰撞势能合的正交,再计算无障碍物象限内碰撞势能合和/或碰撞势能合的正交,所有方向的合为第二速度的方向,大于或等于周围车辆的最大速度的大小为第二速度的大小。其中,当同一象限内仅存在一个障碍物时,碰撞势能合为该障碍物的势能。
作为一种可能的实现方式,如果预设碰撞风险等级的所有车辆未分布在四个不同象限,决策和防碰撞模块可以再判断上述周围车辆是否分布在三个不同象限。当预设碰撞风险等级 的所有周围车辆分布在三个不同象限时,决策和防碰撞模块可以结合本申请提供的势能分解合并的方法进一步确定自车避障的安全方向。具体地,决策和防碰撞模块先分别计算同一象限内所有障碍物的碰撞势能合;然后,确定不同象限的碰撞势能合的正交;再计算无障碍物的象限内所有方向的合,并以无障碍物的象限内所有方向的合的方向为第二速度的方向,以大于或等于周围车辆的最大速度的大小为第二速度的大小。
图9为本申请提供的一种预设碰撞风险等级的所有周围车辆分布在三个不同象限的示意图,如图所示,周围车辆O
1、O
2、O
3和O
4分别分布在第一象限、第二象限和第三象限,其中,第一象限包括O
1、O
2。每个障碍物的势能可以通过步骤S301计算获得,势能有方向和大小的量。接下来,决策和防碰撞模块可以按照如下步骤确定第二速度:
1、先计算每个象限中所有预设碰撞风险等级的周围车辆的碰撞势能合。
如图9所示,仅第一象限存在两个障碍物。决策和防碰撞模块需要计算第一象限中O
1和O
2的碰撞势能的合,由于O
1和O
2的速度方向均为指向自车的,势能在不同象限的平行移动不改变势能的大小和方向。为了更清楚的表示O
1和O
2的碰撞势能的合,在第三象限分别建立以原点为起点,平行移动原O
1和O
2的碰撞势能的V
1和V
2,此时,O
1和O
2的势能合即以V
1和V
2建立的平行四边形中以原点为起点的对角线V
*。
而对于第二象限和第三象限中的障碍物,由于每个象限中仅存在一个障碍物,此时,可以理解为该象限的碰撞势能合即为该障碍物的碰撞势能。
2、分别确定每个象限中碰撞势能合的正交方向。
如图9所示,按照势能在不同坐标系中平行移动不改变势能的大小和方向的原则,O
3的碰撞势能可以平行移动至第四象限,O
4的碰撞势能可以平行移动至第一象限。碰撞势能合的正交方向是指垂直于碰撞势能合的方向。图9中第一象限的障碍物的碰撞势能合为V
*,垂直于V
*的正交方向为V
**。相应的,第二象限的障碍物O
3的势能合的正交方向为V’
3,第三象限的障碍物O
4的势能合的正交方向为V’
4。
3、计算无障碍物的象限内碰撞势能合和/或碰撞势能合的正交的合,并以该方向作为第二速度的方向。
如图9所示,第二象限的O
3的势能合的正交方向分别分布在第一象限和第三象限,而这两个象限均有障碍物,此时,仅需要考虑第一象限的碰撞势能合的正交方向和第三象限的碰撞势能合的正交方向即可。具体地,按照上述步骤1中计算碰撞势能合的方法可获知新的碰撞势能合为V
a。也就是说V
a为第二速度的方向。
4、决策和防碰撞模块还可以根据所有预设碰撞风险等级的周围车辆的速度确定最大速度,并以大于或等于该最大速度的大小作为第二速度的大小。
S307、当预设碰撞风险等级的所有周围车辆未分布在三个不同象限时,判断预设预警登记的所有周围车辆是否分布在两个象限。
S308、当预设碰撞风险等级的所有周围车辆是否分布在两个象限时,判断预设碰撞风险等级的所有周围车辆是否分布在相邻的两个象限。
S309、当预设碰撞风险等级的所有周围车辆分布在相邻的两个象限时,先计算所有预设碰撞风险等级的周围车辆在同一象限内碰撞势能合,并确定每个碰撞势能合的正交方向,去掉有障碍物象限内的正交方向,然后,计算无障碍物象限内的正交方向的合为第二速度的方向,以大于或等于预设碰撞风险等级的所有周围车辆的所有周围车辆最大速度的大小为第二速度的大小。
作为一种可能的实现方式,第二速度还可以在无障碍物象限内比较两个象限中障碍物的 碰撞势能合,当两个象限中碰撞势能合相等时,计算两个象限中碰撞势能合的合,并以该两个象限中碰撞势能合的合作为第二速度,其中,所述两个象限中碰撞势能合的合的方向为所述安全速度的方向,所述两个象限中碰撞势能合的合的大小为所述安全速度的大小;当两个象限中碰撞势能合不等时,计算两个象限中碰撞势能合的正交的合,并以该两个象限中碰撞势能合的正交的合作为第二速度。其中,碰撞势能合的正交的大小为碰撞势能合的大小,方向为垂直于碰撞势能合的方向。
作为一种可能的实现方式,当预设碰撞风险等级的所有周围车辆分布在相邻的两个象限时,决策和防碰撞模块则按照如下步骤确定第二速度:
1、计算所有预设碰撞风险等级的周围车辆在同一象限内势能合。
2、确定每个象限的势能合的正交方向。
3、去掉有障碍物象限内的碰撞势能合正交方向。
4、比较两个象限中障碍物的碰撞势能合,当两个象限中碰撞势能合相等时,计算两个象限中碰撞势能合的合,并以该两个象限中碰撞势能合的合作为第二速度;当两个象限中碰撞势能合不等时,计算两个象限中碰撞势能合的正交的合,并以该两个象限中碰撞势能合的正交的合作为第二速度。其中,碰撞势能合的正交方向的大小为碰撞势能合的大小。
图10为本申请提供的一种预设碰撞风险等级的所有车辆分布在相邻的两个象限的示例,如图所示,周围车辆O
1、O
2分布在第一象限,O
3和O
4分别分布在第二象限。O
1和O
2的势能合为V
*,O
3和O
4的势能合为V^。然后,分别确定V
*和V^的正交方向为V
**和V^^。再比较V
*和V^的大小,当V
*和V^不等时,计算V
**和V^^的势能合V
a,将V
a的方向作为第二速度的方向,将V
a的速度作为第二速度。当V
*和V^相等时,再计算V
*和V^的合,将V
*和V^的势能合的方向作为第二速度的方向,V
*和V^的势能合的大小作为第二速度的大小。
值得说明的是,图10中仅以V
*和V^不等时确认第二速度的过程为例,图10中并未示出V
*和V^相等时确认第二速度的过程。
S310、当预设碰撞风险等级的所有周围车辆未分布在相邻的两个象限时,计算所有预设碰撞风险等级的周围车辆的碰撞势能合,列出每个碰撞势能合的正交,再计算属于同一象限的正交方向的合,以正交方向的合的任意一个方向为第二速度的方向,大于或等于周围车辆中最大速度的速度为第二速度的大小。其中,同一象限正交方向的大小为该象限中碰撞势能合。
与步骤S309类似,图11为本申请提供的一种预设碰撞风险等级的所有周围车辆未分布在相邻的两个象限的示例,如图所示,周围车辆O
1、O
2分布在第一象限,O
3和O
4分别分布在第三象限。O
1和O
2的势能合为V
*,O
3和O
4的势能合为V^。然后,分别确定V
*和V^的正交方向为V
**和V^^。计算V
**和V^^的合V
a和V
b,以任意一个方向作为第二速度的方向,进一步地,以大于或等于周围车辆中最大速度的大小为第二速度的大小。
S311、当判断预设碰撞风险等级的所有周围车辆仅分布在一个象限时,计算所有预设碰撞风险等级的周围车辆的碰撞势能合,以碰撞势能合的正交方向为第二速度的方向,大于或等于周围车辆最大速度的大小为第二速度的大小。
图12为本申请提供的一种预设碰撞风险等级的所有周围车辆分布在同一象限的示例,如图所示,周围车辆O
1、O
2、O
3和O
4分布在第一象限。决策和防碰撞模块计算四个障碍物的碰撞势能合,并以该碰撞势能合的正交方向中任意一个方向作为第二速度的方向,如V
a和V
b为第一象限中障碍物的碰撞势能合的正交方向,决策和防碰撞模块可以选择任意一个方向作为第二速度的方向。进一步地,以碰撞势能合的正交方向为第二速度的方向,大于或等于 周围车辆最大速度的大小为第二速度的大小。
值得说明的是,图12中列举了障碍物分布在不同象限时决策和防碰撞控制模块确定第二速度的各种可能,具体实施时,当决策和防碰撞控制模块判断预设碰撞风险等级的所有周围车辆满足任意一种可能时,即可以按照上述方法的步骤确定第二速度。
作为一种可能的实现方式,除了以大于或等于所有周围障碍物中最大速度的大小为第二速度的大小外,还可以以其他方式确定避障的速度,例如,可以以周围障碍物中最大速度的大小的N倍作为参考,以此限定第二速度的大小。
可选地,当决策和防碰撞模块确定多个避障的速度方向时,可以根据障碍物的类型、相对速度、相对距离计算障碍物与自车发生碰撞的概率,并依次对计算获得的各个概率按照大小进行排序,优先选择概率最小的障碍物所在方向作为第二速度的方向。或者,将多个可选的速度的方向显示在车载显示屏幕上,并提示发生碰撞的概率,由驾驶员选择一种速度的方向,控制器按照驾驶员所选择的方向控制智能汽车行驶。
S215、决策和防碰撞模块向仲裁模块发送第二速度。
S216、当满足第一预设条件时,仲裁模块选择第一速度作为智能汽车行驶的速度。
仲裁模块所确定的速度也可以称为最优速度,该最优速度可以实现智能汽车的有效避障过程,保证智能汽车不与周围障碍物发生碰撞,减少智能汽车与周围障碍物发生碰撞的可能性,提升智能汽车自动驾驶过程的安全性。
S217、判断第一速度的方向是否属于可行范围。
S218、当确定第一速度的方向属于可行范围时,仲裁模块向执行系统发送第一控制指令,其中,第一控制指令包括第一速度。
S219、执行系统按照第一速度控制智能汽车行驶。
作为一种可能的实现方式,在仲裁模块选择第一速度作为智能汽车行驶的速度后,还可以进一步判断第一速度的方向是否为可行范围。具体地,通过势能分解合并方法获得的第一速度的方向是理论上的安全速度,还应根据实际情况对其进行校验,以此提高智能汽车行驶过程的安全性。其中,仲裁模块判断第一速度的方向是否可行的标准包括:不与动态障碍物(如机动车、非机动车、行人、动物、移动中掉落的货物等)发生碰撞、不与静态障碍物(隔离带、护栏、路基、路灯等基础设施)发生碰撞、不违背交通规则(如逆行、闯红灯)。仲裁模块可以从第一感知模块中获得感知设备采集的障碍物的数据,并利用上述数据对智能汽车行驶环境建立自车周围的世界模型,在世界模型中利用上述标准对物理空间进行过滤,得到全部可行区域。如果第一速度的方向位于可行范围,仲裁模块则向执行系统发送控制指令,以此指示执行系统按照第一速度控制智能汽车行驶。如果第一速度的方向没有位于可行区域,则仲裁模块确认第一速度的方向存在安全风险,此时,仲裁模块仅执行制动命令以避免碰撞或减小碰撞损失。
可选地,仲裁模块还可以获取预设碰撞风险等级的所有周围车辆的碰撞势能,当判断碰撞势能均小于第一阈值时,仲裁模块选择第一速度作为智能汽车的行驶速度,并向执行系统发送第一控制指令,由执行系统按照第一速度控制智能汽车在第一区域行驶。也就是说,第一预设条件为预设碰撞风险等级的所有周围车辆的碰撞势能均小于第一阈值,此时,仲裁模块会按照工作通道所确定的速度控制智能汽车行驶。
可选地,上述步骤S217至步骤S218中仲裁模块也可以不判断第一速度的方向是否属于可行范围,直接向执行系统发送第一控制指令。
S220、当满足第二预设条件时,仲裁模块选择第二速度作为智能汽车的行驶速度。
S221、仲裁模块判断第二速度的方向是否属于可行范围.
S222、当满足第二速度的方向属于可行范围时,仲裁模块向执行系统发送第二控制指令,第二控制指令中包括第二速度。
S223、执行系统按照第二速度控制智能汽车行驶。
当仲裁模块确定预设碰撞风险等级的所有周围车辆的碰撞势能大于或等于第一阈值时,仲裁模块选择第二速度作为智能汽车的行驶的速度。也就是说,第二预设条件为预设碰撞风险等级的所有周围车辆的碰撞势能大于或等于第一阈值,此时,仲裁模块会按照安全通道所确定的速度控制智能汽车行驶。
进一步地,仲裁模块还会进一步判断第二速度的方向是否为可行范围。具体地,通过势能分解合并方法获得的第二速度的方向是理论上的安全速度,还应根据实际情况对其进行校验,以此提高智能汽车行驶过程的安全性。其中,仲裁模块判断第二速度的方向是否可行的标准包括:不与动态障碍物(如机动车、非机动车、行人、动物、移动中掉落的货物等)发生碰撞、不与静态障碍物(隔离带、护栏、路基、路灯等基础设施)发生碰撞、不违背交通规则(如逆行、闯红灯)。仲裁模块可以从第一感知模块中获得感知设备采集的障碍物的数据,并利用上述数据对智能汽车行驶环境建立自车周围的世界模型,在世界模型中利用上述标准对物理空间进行过滤,得到全部可行区域。如果第二速度的方向位于可行区域,仲裁模块则向执行系统发送控制指令,以此指示执行系统按照第二速度控制智能汽车行驶。如果第二速度的方向没有位于可行区域,则仲裁模块确认第二速度的方向存在安全风险,此时,仲裁模块仅执行刹停命令以避免碰撞或减小碰撞损失。
值得说明的是,安全通道和工作通道确认第一速度和第二速度的过程是两个相互独立的过程,二者无依赖关系,可以并行处理。也就是说,步骤S210至步骤S212和步骤S213至步骤S215可并行执行。另外,步骤S216至步骤S219、步骤S220至步骤223也是两个独立判断分支。当满足第一预设条件时,仲裁模块可以进一步判断第一速度的方向是否属于可行范围,或者直接将第一速度发送给执行系统,进而控制智能汽车按照工作通道确认的速度控制车辆行驶。当满足第二预设条件时,仲裁模块则进一步判断第二速度的方向是否属于可行范围,当第二速度的方向属于可行方向时,则向执行系统发送第二速度,进而控制智能汽车按照安全通道确认的方向和速度控制车辆行驶。另外,本申请对世界模型的建立方法并不作限定,具体实施时可以按照业务需求建立反应周围车辆障碍物情况的模型。
本申请提供的智能汽车避障方法是一个在存在碰撞风险场景中,主动且持续实施有效避障的过程,上述过程在智能汽车行驶过程是一个不断迭代的过程,只要任意一个障碍物的碰撞势能大于或等于第一阈值,上述过程就会不断循环执行。也就是说,只要存在碰撞风险,安全通道就会计算障碍物的碰撞势能,进而根据碰撞势能确定第二速度。
通过上述内容的描述,本申请提供的防碰撞方法可以基于势能分解合并方法获得在任一区域中满足高功能安全要求的最优速度,并进一步通过可行区域进行校验,最终确定智能汽车避障的最优速度。本申请能够通过周围障碍物与自车的距离和相对速度综合判断自车与障碍物发生碰撞的可能,更好的识别自车的碰撞风险,以此解决传统技术中仅基于刹车距离、最小刹车时间的判断方法所带来的误判或漏判的问题。进一步地,本申请提供的方法不仅能够避免与来自自车前方的车辆的碰撞,还能避免与来自自车后方、侧方等各个方向的碰撞,相比于传统技术方法中仅能对来自自车前方的车辆的碰撞,提升了智能汽车的避障能力,不仅能够控制智能汽车减速,还能控制智能汽车按照确定的避障方向加速行驶避障,进而使得智能汽车可以实现各个方向的避障的效果。另一方面,本申请提供的方法提供的避障方向和 速度更加精准,能够保证智能汽车按照当前时刻最有的安全方向和速度实现避障,避免自车与周围车辆发生碰撞。
作为一种可能的实现方式,图13为本申请提供的一种交互系统的示意图。如图所示,该交互系统可以通过多种形式提示驾驶员注意周围车辆情况,由驾驶员接管智能汽车或向智能汽车发送执行指令,以控制智能汽车的行驶。例如,音频提示、座椅震动提示、车内闪灯提示。人机交互系统还可以利用不同颜色或背景标识不同等级和区域。
具体地,可以利用以下方式中至少一种形式实现智能汽车与驾驶员的人机交互过程:
方式1:在智能汽车的车载显示界面通过文字提示该智能汽车与周围障碍物存在碰撞风险,以及第一速度和第二速度。示例地,图13中Va和Vb为可选的避障方向,驾驶员可以选择任意一个作为车辆行驶的方向。另外,除了标注Va和Vb为可选的避障方向外,还可以利用不同标识提示向障碍物方向行驶的碰撞风险,例如,在图13中障碍物O1和O2方向,利用五角星标识和文字提示“危险”。
方式2:在该智能汽车中通过语音提示该智能汽车与所述周围障碍物存在碰撞风险,第一速度和第二速度;在智能汽车中通过座椅震动提示所述智能汽车与周围障碍物存在碰撞风险。
方式3:在智能汽车中通过车灯闪灯提示智能汽车与周围障碍物存在碰撞风险。对于危险情况,还可以通过快速闪灯的方式提示驾驶员的注意。
作为一种可能的实现方式,智能汽车按照上述方法进行躲避障碍物后,可能更改了决策模块所确定的原始行驶轨迹,还需要进一步结合当前时刻智能汽车所处的路况重新规划或调整原始行驶轨迹,进而保证智能汽车顺利到达驾驶员指定的目的地。
可选地,智能汽车除了利用上述控制器确定速度外,也可以接收驾驶员通过界面或语音等形式所选择的速度,在接收上述速度控制指令后,可以以此速度控制智能汽车行驶。
通过上述人机交互系统,能够提升驾驶员的驾驶体验,帮助驾驶员更好的接管和控制智能汽车。另一方面,通过人机交互系统也可以让驾驶员了解智能汽车所处环境的情况,减少驾驶员在紧急情况下无法获知智能汽车行驶区域而产生的恐惧。紧急情况下,驾驶员还可以通过人工交互系统显示的情况决定是否切换驾驶模式为人工驾驶模式,由驾驶员接管智能汽车的控制权。
作为一种可能的实现方式,除了利用障碍物与自车的相对速度和相对距离来确认碰撞势能,进而确认障碍物与自车的碰撞风险外,还可以根据障碍物的类型,对不同类型的车辆添加不同权值,具体权值的设置可以考虑不同类型的障碍物与自车发生碰撞的损伤程度。再进一步结合上述碰撞损伤程度确定避障的最优方向和速度。
作为另一种可能的实现方式,控制器除了依赖于其所在智能汽车的传感设备探测周围障碍物的感知数据外,也可以由其他障碍物向智能汽车发送其他车辆的信息,包括其他车辆的轨迹信息,智能汽车自车的避障过程也可以结合上述车辆的信息实现智能汽车的避障过程。其中,其他障碍物可以通过车外网(vehicle to everything,V2X)通信技术向智能汽车发送信息。当存在两个或多个避障方向时,还可以根据障碍物的类型、与自车的距离和相对速度确认其与自车发生碰撞的改了,并通过界面显示躲避障碍物的概率,驾驶员可以通过界面选择任意一个可行方向作为避障方向。
作为另一种可能的实现方式,当安全通道确认的第二速度有多个方向时,还可以根据与障碍物的碰撞危险程度选择最安全的方向作为第二速度的方向,其中,碰撞危险程度包括与障碍物发生碰撞的概率、发生碰撞的损伤程度等因素中一种或多种,发生碰撞的损伤程度可 以根据障碍物的大小、相对速度和相对距离进行标定,障碍物越大、相对速度越快、相对距离越短,发生碰撞的损伤程度越高。通过上述方式,当存在多个第二速度的方向时,可以根据碰撞风险程度选择最优的方向躲避障碍物,进一步提升自动驾驶的安全性。而且,上述碰撞风险程度可以通过人机交互界面显示给驾驶员,由驾驶员选择最终速度的方向,进而控制车辆按照驾驶员选择的速度行驶。
值得说明的是,对于上述方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作并不一定是本申请所必须的。
本领域的技术人员根据以上描述的内容,能够想到的其他合理的步骤组合,也属于本申请的保护范围内。其次,本领域技术人员也应该熟悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作并不一定是本申请所必须的。
上文中结合图1至图13,详细描述了根据本申请所提供的防碰撞的方法,下面将结合图14至图16,描述根据本申请所提供的车辆控制装置、控制器和智能汽车。
图14为本申请提供的一种车辆控制装置500的示意图,如图所示,所示装置500包括获取单元501,该获取单元501,用于获取在第一区域规划所述智能汽车行驶的第一速度;所述第一区域为所述智能汽车行驶至目的地过程中一段区域;获取在所述第一区域规划所述智能汽车行驶的第二速度;所述第二速度是根据碰撞势能获得;其中,所述第一速度和所述第二速度分别包括方向和大小;所述第一速度、第二速度和所述智能汽车与周围障碍物的碰撞风险用于确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
可选地,所述碰撞势能用于标识所述周围障碍物与所述智能汽车的碰撞趋势。
可选地,所述装置500还包括控制单元502,用于根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定用于确定所述智能汽车防碰撞的最优速度,所述最优速度包括大小和方向。
可选地,所述控制单元502还包括第一决策单元5021,用于接收速度控制指令,以所述速度控制指令控制所述智能汽车行驶。
可选地,所述控制单元502还包括第二决策单元5022,用于当满足第一预设条件时,所述最优速度为所述第一速度;其中,所述第一预设条件为任意一个所述周围障碍物的碰撞势能小于第一阈值。
可选地,所述控制单元502还包括第二决策单元5022,还用于当满足第二预设条件时,所述最优速度为所述第二速度;其中,所述第二预设条件为所述任意一个所述周围障碍物的碰撞势能大于或等于第一阈值。
可选地,所述装置500还包括交互单元503,用于以以下方式中至少一种提示所述智能汽车存在碰撞风险;或,在所述智能汽车的车载显示界面通过文字提示所述智能汽车与所述周围障碍物存在碰撞风险,以及所述第一速度、所述第二速度;或,在所述智能汽车中通过语音提示所述智能汽车与所述周围障碍物存在碰撞风险,以及所述第一速度、所述第二速度和所述最优速度;或,在所述智能汽车中通过座椅震动提示所述智能汽车与所述周围障碍物存在碰撞风险;或,在所述智能汽车中通过车灯闪灯提示所述智能汽车与所述周围障碍物存在碰撞风险。
可选地,第一决策单元5021用于实现上述方法中工作通道中获得第一速度的功能,而第二决策单元5022则用于实现上述方法中安全通道中获得第二速度的功能。第一决策单元5021 和第二决策单元5022也可以合并为一个决策单元,该决策单元用于分别实现安全通道和工作通道确定第一速度和第二速度的功能。
应理解的是,本申请实施例的装置500可以通过专用集成电路(application-specific integrated circuit,ASIC)实现,或可编程逻辑器件(programmable logic device,PLD)实现,上述PLD可以是复杂程序逻辑器件(complex programmable logical device,CPLD),现场可编程门阵列(field-programmable gate array,FPGA),通用阵列逻辑(generic array logic,GAL)或其任意组合。也可以通过软件实现图3和图4所示的车辆控制方法时,装置500及其各个模块也可以为软件模块。
根据本申请实施例的装置500可对应于执行本申请实施例中描述的方法,并且装置500中的各个单元的上述和其它操作和/或功能分别为了实现图3至图4中的各个方法的相应流程,为了简洁,在此不再赘述。
图15为本申请提供的另一种车辆控制装置600的结构示意图,如图所示,装置600包括计算单元601、决策单元602和控制单元603,其中,
所述计算单元601,用于根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能,所述第一感知数据包括所述周围障碍物与所述智能汽车的相对速度和相对距离;
所述决策单元602、用于根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,所述第一区域为所述智能汽车规划路径中一段区域;
所述控制单元603,用于控制所述智能汽车在所述第一区域以所述安全速度行驶。
可选地,所述碰撞势能用于标识所述周围障碍物与所述智能汽车的碰撞趋势。
可选地,所述控制单元603,还用于当任意一个所述周围障碍物的碰撞势能大于或等于第一阈值时,控制所述智能汽车在所述第一区域以所述安全速度行驶。
可选地,所述计算单元601,还用于利用下述公式计算所述周围障碍物的碰撞势能:
其中,k、α、β是常系数,C是常量,ν是第一障碍物相对于所述智能汽车的相对速度的大小,d是第一障碍物相对于所述智能汽车的相对距离,第一障碍物是周围障碍物中任意一个。
可选地,所述决策单元602,还用于根据所述周围障碍物的碰撞势能和预设阈值确定所述每个周围的障碍物的碰撞风险等级,所述碰撞风险等级包括安全、预警和危险;选择预设碰撞风险等级的所有周围的障碍物;根据所选择的所述预设碰撞风险等级的所有周围的障碍物的碰撞势能确定所述安全速度。
可选地,所述决策单元602,还用于获取第一感知数据,所述第一感知数据为所述智能汽车的感知设备探测获得初始数据经过分析和处理后所获得的数据;建立以所述智能汽车为原点,所述智能汽车行驶方向为X轴;根据所述第一感知数据计算所述周围障碍物在所述坐标系中的位置,所述位置用于指示所述每个障碍物在所述坐标系中坐标和所在象限。
可选地,所述决策单元602,还用于当所述预设安全风险等级的所有周围障碍物分布在四个象限时,识别无障碍物的区域中最大安全角度,以最大安全角度的角平分线方向作为安全速度的方向,大于或等于周围车辆的最大速度的大小为安全速度的大小。
可选地,所述决策单元602,还用于当所述预设安全风险等级的所有周围障碍物分布在三个象限时,分别计算同一象限内所有预设安全风险等级的所有障碍物的碰撞势能的合;确定每个象限中碰撞势能合的正交;去掉有障碍物的象限内的所有障碍物的碰撞势能合和/或碰 撞势能合的正交;计算无障碍物象限内碰撞势能合和/或碰撞势能合的正交,将所述无障碍物象限内碰撞势能合和/或碰撞势能合的正交中所有方向的合作为安全速度的方向,将大于或等于周围车辆的最大速度的大小为安全速度的大小。
可选地,所述决策单元602,还用于当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定每个碰撞势能合的正交方向;计算无障碍物的象限内的碰撞势能合的正交方向的合为安全速度的方向,以大于或等于预设碰撞风险等级的所有周围车辆的所有周围车辆最大速度的大小为安全速度的大小。
可选地,所述决策单元602,还用于当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,计算在同一象限内所有预设碰撞风险等级的周围车辆在碰撞势能合,并确定每个碰撞势能合的正交;在无障碍物象限内比较两个象限中障碍物的碰撞势能合,当两个象限中碰撞势能合相等时,计算两个象限中碰撞势能合的合,并以该两个象限中碰撞势能合的合作为安全速度;当两个象限中碰撞势能合不等时,计算两个象限中碰撞势能合的正交的合,并以该两个象限中碰撞势能合的正交的合作为安全速度。其中,碰撞势能合的正交的大小为碰撞势能合的大小,方向为垂直于碰撞势能合的方向。
可选地,所述决策单元602,还用于当所述预设安全风险等级的所有周围障碍物分布在两个不相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定每个碰撞势能合的正交;计算属于同一象限的所述碰撞势能合的正交的合,以所述同一象限的所述碰撞势能合的正交的合的任意一个方向为所述安全速度的大小,大于或等于周围车辆中最大速度的大小为所述安全速度的大小。
可选地,所述决策单元602,还用于当判断预设碰撞风险等级的所有周围车辆仅分布在一个象限时,计算所有预设碰撞风险等级的周围车辆的碰撞势能合,以碰撞势能合的正交方向为所述安全速度的方向,大于或等于周围车辆最大速度的大小为所述安全速度的大小。
可选地,所述决策单元602,还用于判断所述安全速度的方向是否属于可行范围,所述可行范围为满足以下标准的区域:不与动态障碍物发生碰撞、不与静态障碍物发生碰撞、不违背交通规则,其中,动态障碍物包括机动车、行人、动物;静态障碍物包括隔离带、护栏、路径、路灯等基础设施;交通规则包括逆行、闯红灯;当所述安全速度的方向属于所述可行范围时,向所述控制单元603发送所述安全速度,由所述控制单元603控制所述智能汽车在所述第一区域以所述安全速度行驶。
应理解的是,本申请实施例的装置600可以通过专用集成电路(application-specific integrated circuit,ASIC)实现,或可编程逻辑器件(programmable logic device,PLD)实现,上述PLD可以是复杂程序逻辑器件(complex programmable logical device,CPLD),现场可编程门阵列(field-programmable gate array,FPGA),通用阵列逻辑(generic array logic,GAL)或其任意组合。也可以通过软件实现图3和图4所示的车辆控制方法时,装置600及其各个模块也可以为软件模块。
根据本申请实施例的装置600可对应于执行本申请实施例中描述的方法,并且装置600中的各个单元的上述和其它操作和/或功能分别为了实现图3至图4中的各个方法的相应流程,为了简洁,在此不再赘述。另外,装置600的决策模块602可以与装置500中第二决策模块5022对应,用于实现安全通道中决策和防碰撞模块确定第二速度的过程。
图16为本申请实施例提供的一种控制器700的示意图,如图所示,所述控制器700包括处理器701、存储器702、通信接口703和内存704。其中,处理器701、存储器702、通信 接口703和内存704通过总线705进行通信。该存储器702用于存储指令,该处理器701用于执行该存储器702存储的指令。该存储器702存储程序代码,且处理器701可以调用存储器702中存储的程序代码执行以下操作:
获取在第一区域规划所述智能汽车行驶的第一速度;所述第一区域为所述智能汽车行驶至目的地过程中一段区域;获取在所述第一区域规划所述智能汽车行驶的第二速度;所述第二速度是根据碰撞势能获得;
其中,所述第一速度和所述第二速度分别包括方向和大小;所述第一速度、第二速度和所述智能汽车与周围障碍物的碰撞风险用于确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
应理解,在本申请实施例中,该处理器701可以是CPU,该处理器701还可以是其他通用处理器、数字信号处理器(digital signal processing,DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。
可选地,控制器700中可以包括多个处理器,示例地,图16中包括处理器701和处理器706。其中,处理器701和处理器706可以是不同类型的处理器,而且,每种处理器中包括一个或多个芯片。
该存储器702可以包括只读存储器和随机存取存储器,并向处理器701提供指令和数据。存储器702还可以包括非易失性随机存取存储器。例如,存储器702还可以存储设备类型的信息。
该存储器702可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM,DR RAM)。
该总线704除包括数据总线之外,还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见,在图中将各种总线都标为总线704。可选地,该总线704还可以是车载以太或控制器局域网(controller area network,CAN)总线或其他内部总线。
应理解,根据本申请实施例的控制器可对应于本申请实施例中的装置500和装置600,并可以对应于执行根据本申请实施例中图3和图4所示方法的相应主体,并且控制器700中的各个模块的上述和其它操作和/或功能分别为了实现图3至图4中的各个方法的相应流程,为了简洁,在此不再赘述。
作为另一种可能的实现方式,图16所示的控制器700的处理器701可以调用存储器702中存储的程序代码执行以下操作:
根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能,所述第一感知数据包括所述周围障碍物与所述智能汽车的相对速度和相对距离;
根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,所述第一区域为所述智能汽车规划路径中一段区域;
控制所述智能汽车在所述第一区域以所述安全速度行驶。
应理解,根据本申请实施例的控制器700可对应于本申请实施例中的装置500和装置600,并可以对应于执行根据本申请实施例中图3和图4所示方法的相应主体,并且控制器700中的各个模块的上述和其它操作和/或功能分别为了实现图3至图4中的各个方法的相应流程,为了简洁,在此不再赘述。
本申请还提供一种如图1或图2所示的智能汽车,该智能汽车包括图16所示的控制器700,并且该控制器700用于实现上述图3至图4各个方法的相应流程,为了简洁,在此不再赘述。
上述实施例,可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时,上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载或执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质。半导体介质可以是固态硬盘(solid state drive,SSD)。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
以上所述,仅为本申请的具体实施方式。熟悉本技术领域的技术人员根据本申请提供的具体实施方式,可想到变化或替换,都应涵盖在本申请的保护范围之内。
Claims (26)
- 一种车辆控制方法,应用于智能汽车,其特征在于,所述方法包括:获取在第一区域规划所述智能汽车行驶的第一速度;所述第一区域为所述智能汽车行驶至目的地过程中一段区域;获取在所述第一区域规划所述智能汽车行驶的第二速度;所述第二速度是根据碰撞势能获得;其中,所述第一速度和所述第二速度分别包括方向和大小;所述第一速度、第二速度和所述智能汽车与周围障碍物的碰撞风险用于确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
- 根据权利要求1所述的方法,其特征在于,所述碰撞势能用于标识所述周围障碍物与所述智能汽车发生碰撞的趋势。
- 根据权利要求1或2所述的方法,其特征在于,所述方法还包括:根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
- 根据权利要求1或2所述的方法,其特征在于,所述方法还包括:接收速度控制指令,以所述速度控制指令控制所述智能汽车行驶。
- 根据权利要求3所述方法,其特征在于,根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定所述智能汽车防碰撞的最优速度,包括:当满足第一预设条件时,所述最优速度为所述第一速度;其中,所述第一预设条件为任意一个所述周围障碍物的碰撞势能小于第一阈值。
- 根据权利要求3所述方法,其特征在于,根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定所述智能汽车防碰撞的最优速度,包括:当满足第二预设条件时,所述最优速度为所述第二速度;其中,所述第二预设条件为所述任意一个所述周围障碍物的碰撞势能大于或等于第一阈值。
- 根据权利要求1至6中任一所述方法,其特征在于,所述方法还包括:所述智能汽车可以通过以下方式中至少一种提示所述智能汽车存在碰撞风险:在所述智能汽车的车载显示界面通过文字提示所述智能汽车与所述周围障碍物存在碰撞风险,以及所述第一速度、所述第二速度;或,在所述智能汽车中通过语音提示所述智能汽车与所述周围障碍物存在碰撞风险,以及所述第一速度、所述第二速度;或,在所述智能汽车中通过座椅震动提示所述智能汽车与所述周围障碍物存在碰撞风险;或,在所述智能汽车中通过车灯闪灯提示所述智能汽车与所述周围障碍物存在碰撞风险。
- 一种车辆控制的方法,应用于智能汽车,其特征在于,所述方法包括:根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能,所述第一感知数据包括 所述周围障碍物与所述智能汽车的相对速度和相对距离;根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,所述第一区域为所述智能汽车规划路径中一段区域;控制所述智能汽车在所述第一区域以所述安全速度行驶。
- 根据权利要求8所述方法,其特征在于,所述碰撞势能用于标识所述周围障碍物与所述智能汽车的碰撞趋势。
- 根据权利要求8或9所述方法,其特征在于,控制所述智能汽车在所述第一区域以所述安全速度行驶,包括:当任意一个所述周围障碍物的碰撞势能大于或等于第一阈值时,控制所述智能汽车在所述第一区域以所述安全速度行驶。
- 根据权利要求8至11任一所述方法,其特征在于,在控制所述智能汽车在所述第一区域以所述安全速度行驶之前,所述方法还包括:根据所述周围障碍物的碰撞势能和预设阈值确定所述每个周围的障碍物的碰撞风险等级,所述碰撞风险等级包括安全、预警和危险;则所述控制所述智能汽车在所述第一区域以所述安全速度行驶,包括:选择预设碰撞风险等级的所有周围的障碍物;根据所选择的所述预设碰撞风险等级的所有周围的障碍物的碰撞势能确定所述安全速度。
- 根据权利要求8至12任一所述方法,其特征在于,在根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能之前,所述方法还包括:获取第一感知数据,所述第一感知数据为所述智能汽车的感知设备探测获得初始数据经过分析和处理后所获得的数据;建立以所述智能汽车为原点的坐标系;根据所述第一感知数据计算所述周围障碍物在所述坐标系中的位置,所述位置用于指示所述每个障碍物在所述坐标系中坐标和所在象限。
- 根据权利要求8至13任一所述方法,其特征在于,根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,包括:当所述预设安全风险等级的所有周围障碍物分布在四个象限时,识别无障碍物的区域中 最大安全角度,以最大安全角度的角平分线方向作为安全速度的方向,大于或等于周围车辆的最大速度的大小为安全速度的大小。
- 根据权利要求8至13中任一所述方法,其特征在于,所述方法还包括:当所述预设安全风险等级的所有周围障碍物分布在三个象限时,分别计算同一象限内所有预设安全风险等级的所有障碍物的碰撞势能的合;确定每个象限中碰撞势能合的正交;计算无障碍物象限内碰撞势能合和/或碰撞势能合的正交,将所述无障碍物象限内碰撞势能合和/或碰撞势能合的正交中所有方向的合作为安全速度的方向,将大于或等于周围车辆的最大速度的大小为安全速度的大小。
- 根据权利要求8至13中任一所述方法,其特征在于,所述方法还包括:当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定每个碰撞势能合的正交方向;计算无障碍物的象限内的碰撞势能合的正交方向的合为安全速度的方向,以大于或等于预设碰撞风险等级的所有周围车辆的所有周围车辆最大速度的大小为安全速度的大小。
- 根据权利要求8至13中任一所述方法,其特征在于,所述方法还包括:当所述预设安全风险等级的所有周围障碍物分布在两个相邻象限时,计算在同一象限内所有预设碰撞风险等级的周围车辆在碰撞势能合,并确定每个碰撞势能合的正交;在无障碍物象限内比较两个象限中障碍物的碰撞势能合,当两个象限中碰撞势能合相等时,计算两个象限中碰撞势能合的合,并以所述两个象限中碰撞势能合的合作为所述安全速度,其中,所述两个象限中碰撞势能合的合的方向为所述安全速度的方向,所述两个象限中碰撞势能合的合的大小为所述安全速度的大小;当两个象限中碰撞势能合不等时,计算两个象限中碰撞势能合的正交的合,并以该两个象限中碰撞势能合的正交的合作为所述安全速度;其中,所述碰撞势能合的正交的大小为碰撞势能合的大小,所述碰撞势能合的正交的方向为垂直于碰撞势能合的方向。
- 根据权利要求8至13中任一所述方法,其特征在于,所述方法还包括:当所述预设安全风险等级的所有周围障碍物分布在两个不相邻象限时,分别计算同一象限内所有预设碰撞风险等级的周围障碍物的碰撞势能合,并确定每个碰撞势能合的正交;计算属于同一象限的所述碰撞势能合的正交的合,以所述同一象限的所述碰撞势能合的正交的合的任意一个方向为所述安全速度的大小,大于或等于周围车辆中最大速度的大小为所述安全速度的大小。
- 根据权利要求8至13中任一所述方法,其特征在于,所述方法还包括:当判断预设碰撞风险等级的所有周围车辆仅分布在一个象限时,计算所有预设碰撞风险等级的周围车辆的碰撞势能合,以碰撞势能合的正交方向为所述安全速度的方向,大于或等于周围车辆最大速度的大小为所述安全速度的大小。
- 根据权利要求8至19任一所述方法,其特征在于,所述方法还包括:判断所述安全速度的方向是否属于可行范围,所述可行范围为满足以下标准的区域:不与动态障碍物发生碰撞、不与静态障碍物发生碰撞、不违背交通规则,其中,动态障碍物包括机动车、行人、动物;静态障碍物包括隔离带、护栏、路径、路灯等基础设施;交通规则包括逆行、闯红灯;当所述安全速度的方向属于所述可行范围时,控制所述智能汽车在所述第一区域以所述安全速度行驶。
- 一种车辆控制的装置,其特征在于,所述装置包括获取单元:所述获取单元,用于获取在第一区域规划所述智能汽车行驶的第一速度;所述第一区域为所述智能汽车行驶至目的地过程中一段区域;获取在所述第一区域规划所述智能汽车行驶的第二速度;所述第二速度是根据碰撞势能获得;其中,所述第一速度和所述第二速度分别包括方向和大小;所述第一速度、第二速度和所述智能汽车与周围障碍物的碰撞风险用于确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
- 根据权利要求21所述的装置,其特征在于,所述装置还包括控制单元,所述控制单元,用于根据所述第一速度、所述第二速度和所述智能汽车与周围障碍物的碰撞风险确定所述智能汽车的最优速度,所述最优速度包括大小和方向。
- 一种车辆控制的装置,其特征在于,所述装置包括计算单元、决策单元和控制单元;所述计算单元,用于根据第一感知数据计算所述智能汽车的周围障碍物的碰撞势能,所述第一感知数据包括所述周围障碍物与所述智能汽车的相对速度和相对距离;所述决策单元,用于根据所述周围障碍物的碰撞势能确定所述智能汽车在第一区域行驶的安全速度,所述第一区域为所述智能汽车规划路径中一段区域;所述控制单元,用于控制所述智能汽车在所述第一区域以所述安全速度行驶。
- 一种车辆控制的控制器,所述控制器包括处理器和存储器,所述存储器中存储计算机程序指令,当所述控制器运行时,所述处理器执行上述计算机程序指令用于实现上述权利要求1至7中任一所述方法的操作步骤。
- 一种车辆控制的控制器,所述控制器包括处理器和存储器,所述存储器中存储计算机程序指令,当所述控制器运行时,所述处理器执行上述计算机程序指令用于实现上述权利要求8至20任一所述方法的操作步骤。
- 一种智能汽车,其特征在于,所述智能汽车包括控制器,所述控制器用于实现上述权利要求24或24所述控制器的任一所述操作步骤。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP20866454.0A EP4043309A4 (en) | 2019-09-16 | 2020-07-03 | VEHICLE CONTROL METHOD, DEVICE, CONTROL AND INTELLIGENT VEHICLE |
| US17/696,545 US12233856B2 (en) | 2019-09-16 | 2022-03-16 | Vehicle control method |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872276 | 2019-09-16 | ||
| CN201910872276.1 | 2019-09-16 | ||
| CN201911417586.0A CN112590778B (zh) | 2019-09-16 | 2019-12-31 | 车辆控制的方法、装置、控制器和智能汽车 |
| CN201911417586.0 | 2019-12-31 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US17/696,545 Continuation US12233856B2 (en) | 2019-09-16 | 2022-03-16 | Vehicle control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021051959A1 true WO2021051959A1 (zh) | 2021-03-25 |
Family
ID=74883983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/100089 Ceased WO2021051959A1 (zh) | 2019-09-16 | 2020-07-03 | 车辆控制的方法、装置、控制器和智能汽车 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US12233856B2 (zh) |
| EP (1) | EP4043309A4 (zh) |
| CN (1) | CN114834443B (zh) |
| WO (1) | WO2021051959A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113561892A (zh) * | 2021-05-20 | 2021-10-29 | 东风汽车集团股份有限公司 | 一种汽车开门智能防撞系统及方法 |
| US20220324484A1 (en) * | 2021-04-01 | 2022-10-13 | Volkswagen Aktiengesellschaft | Method for determining a trajectory of an at least partially assisted operated motor vehicle, computer program and assistance system |
| CN115257738A (zh) * | 2022-08-15 | 2022-11-01 | 合肥工业大学 | 一种考虑相邻车辆切入风险的智能车辆跟驰模型 |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102935853B1 (ko) * | 2021-03-08 | 2026-03-09 | 현대모비스 주식회사 | 차량의 승객 보호 장치 및 방법 |
| CN115027504B (zh) * | 2022-07-19 | 2024-09-24 | 重庆长安汽车股份有限公司 | 自动驾驶车辆的安全控制方法及装置 |
| CN116311894A (zh) * | 2022-12-30 | 2023-06-23 | 博泰车联网科技(上海)股份有限公司 | 车辆碰撞预警方法、电子设备及存储介质 |
| CN116572991B (zh) * | 2023-06-21 | 2025-09-12 | 重庆长安汽车股份有限公司 | 驾驶规划方法及系统、车辆 |
| CN117533304B (zh) * | 2023-11-30 | 2024-12-10 | 湖南大学苏州研究院 | 一种基于人体损伤势场的乘员保护系统及控制方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150096924A (ko) * | 2014-02-17 | 2015-08-26 | 주식회사 만도 | 전방 충돌 차량 선정 방법 및 시스템 |
| US20150353082A1 (en) * | 2014-06-05 | 2015-12-10 | Carnegie Mellon University | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver |
| KR20180006635A (ko) * | 2016-07-11 | 2018-01-19 | 주식회사 만도 | 교차로 충돌 회피 시스템 및 그 제어 방법 |
| CN108202740A (zh) * | 2016-12-16 | 2018-06-26 | 奥迪股份公司 | 防碰撞辅助系统和方法 |
| WO2019000391A1 (zh) * | 2017-06-30 | 2019-01-03 | 华为技术有限公司 | 车辆的控制方法、装置及设备 |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6917305B2 (en) * | 2002-09-26 | 2005-07-12 | Ford Global Technologies, Llc | Vehicle collision severity estimation system |
| US9327726B2 (en) | 2004-10-05 | 2016-05-03 | Vision Works Ip Corporation | Absolute acceleration sensor for use within moving vehicles |
| JP2011118482A (ja) * | 2009-11-30 | 2011-06-16 | Fujitsu Ten Ltd | 車載装置および認知支援システム |
| US9047780B2 (en) * | 2012-11-16 | 2015-06-02 | Robert Bosch Gmbh | Collision mitigation systems and methods using driver attentiveness |
| JP2014193691A (ja) | 2013-03-29 | 2014-10-09 | Hitachi Automotive Systems Ltd | 車両の運動制御装置 |
| CN103921790A (zh) | 2014-05-12 | 2014-07-16 | 李质勇 | 汽车主动安全智能系统与控制方法 |
| DE102015117976A1 (de) * | 2015-10-22 | 2017-04-27 | Knorr-Bremse Systeme für Nutzfahrzeuge GmbH | Verfahren und Vorrichtung zum Steuern eines Warnmoduls |
| US9720415B2 (en) | 2015-11-04 | 2017-08-01 | Zoox, Inc. | Sensor-based object-detection optimization for autonomous vehicles |
| JP6504042B2 (ja) * | 2015-12-17 | 2019-04-24 | 株式会社デンソー | 制御装置、制御方法 |
| CN105869438A (zh) * | 2016-04-12 | 2016-08-17 | 深圳市中天安驰有限责任公司 | 一种车辆防碰撞预警系统 |
| JP6371329B2 (ja) | 2016-05-16 | 2018-08-08 | トヨタ自動車株式会社 | 車両の運転支援制御装置 |
| US10246090B2 (en) * | 2016-11-07 | 2019-04-02 | Ford Global Technologies, Llc | Vehicle collision severity mitigation |
| JP6881219B2 (ja) * | 2017-10-18 | 2021-06-02 | トヨタ自動車株式会社 | 衝突前制御装置及び衝突前制御方法 |
| WO2019139815A1 (en) * | 2018-01-12 | 2019-07-18 | Duke University | Apparatus, method and article to facilitate motion planning of an autonomous vehicle in an environment having dynamic objects |
| JP6972503B2 (ja) * | 2018-01-30 | 2021-11-24 | マツダ株式会社 | 車両制御装置 |
| DE112019000065B4 (de) * | 2018-02-02 | 2025-01-09 | Nvidia Corporation | Sicherheitsprozeduranalyse zur hindernisvermeidung in einem autonomen fahrzeug |
| WO2019231455A1 (en) * | 2018-05-31 | 2019-12-05 | Nissan North America, Inc. | Trajectory planning |
| CN109002041B (zh) * | 2018-08-09 | 2021-03-19 | 北京智行者科技有限公司 | 一种车辆避障方法 |
| US11215997B2 (en) * | 2018-11-30 | 2022-01-04 | Zoox, Inc. | Probabilistic risk assessment for trajectory evaluation |
| DE102019201888A1 (de) * | 2019-02-13 | 2020-08-13 | Robert Bosch Gmbh | Verfahren und Steuergerät zur Begrenzung eines Unfallrisikos |
| ES3041273T3 (en) * | 2019-05-23 | 2025-11-11 | Streetscope Inc | Apparatus and method for processing vehicle signals to compute a behavioral hazard measure |
| CN112590778B (zh) * | 2019-09-16 | 2022-05-10 | 华为技术有限公司 | 车辆控制的方法、装置、控制器和智能汽车 |
-
2019
- 2019-12-31 CN CN202210301333.2A patent/CN114834443B/zh active Active
-
2020
- 2020-07-03 EP EP20866454.0A patent/EP4043309A4/en not_active Withdrawn
- 2020-07-03 WO PCT/CN2020/100089 patent/WO2021051959A1/zh not_active Ceased
-
2022
- 2022-03-16 US US17/696,545 patent/US12233856B2/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150096924A (ko) * | 2014-02-17 | 2015-08-26 | 주식회사 만도 | 전방 충돌 차량 선정 방법 및 시스템 |
| US20150353082A1 (en) * | 2014-06-05 | 2015-12-10 | Carnegie Mellon University | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver |
| KR20180006635A (ko) * | 2016-07-11 | 2018-01-19 | 주식회사 만도 | 교차로 충돌 회피 시스템 및 그 제어 방법 |
| CN108202740A (zh) * | 2016-12-16 | 2018-06-26 | 奥迪股份公司 | 防碰撞辅助系统和方法 |
| WO2019000391A1 (zh) * | 2017-06-30 | 2019-01-03 | 华为技术有限公司 | 车辆的控制方法、装置及设备 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP4043309A4 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220324484A1 (en) * | 2021-04-01 | 2022-10-13 | Volkswagen Aktiengesellschaft | Method for determining a trajectory of an at least partially assisted operated motor vehicle, computer program and assistance system |
| US12503137B2 (en) * | 2021-04-01 | 2025-12-23 | Volkswagen Aktiengesellschaft | Method for determining a trajectory of an at least partially assisted operated motor vehicle, computer program and assistance system |
| CN113561892A (zh) * | 2021-05-20 | 2021-10-29 | 东风汽车集团股份有限公司 | 一种汽车开门智能防撞系统及方法 |
| CN113561892B (zh) * | 2021-05-20 | 2023-10-24 | 东风汽车集团股份有限公司 | 一种汽车开门智能防撞系统及方法 |
| CN115257738A (zh) * | 2022-08-15 | 2022-11-01 | 合肥工业大学 | 一种考虑相邻车辆切入风险的智能车辆跟驰模型 |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4043309A4 (en) | 2023-05-10 |
| CN114834443B (zh) | 2025-11-11 |
| US20220203971A1 (en) | 2022-06-30 |
| EP4043309A1 (en) | 2022-08-17 |
| CN114834443A (zh) | 2022-08-02 |
| US12233856B2 (en) | 2025-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112590778B (zh) | 车辆控制的方法、装置、控制器和智能汽车 | |
| WO2021051959A1 (zh) | 车辆控制的方法、装置、控制器和智能汽车 | |
| JP7289760B2 (ja) | 電子制御装置 | |
| CN111497864B (zh) | 利用v2x应用程序向人传递当前驾驶意图信号的方法及装置 | |
| CN114906164B (zh) | 用于自主驾驶的轨迹验证 | |
| JP7145815B2 (ja) | 電子制御装置 | |
| CN109969172B (zh) | 车辆控制方法、设备及计算机存储介质 | |
| KR102426734B1 (ko) | 부과된 책임 제약이 있는 항법 시스템 | |
| TW202246093A (zh) | 偵測車輛的駕駛行為 | |
| EP4089369A1 (en) | Path selection method and path selection device | |
| US9280899B2 (en) | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks | |
| EP4406794A1 (en) | Trajectory planning method and apparatus for vehicle, and vehicle | |
| CN114061581A (zh) | 通过相互重要性对自动驾驶车辆附近的智能体排名 | |
| Wang et al. | Vehicle collision prediction at intersections based on comparison of minimal distance between vehicles and dynamic thresholds | |
| JP2021020580A (ja) | 車両制御装置、車両制御方法、およびプログラム | |
| WO2022246853A1 (zh) | 一种车辆系统的安全测试方法和测试用车辆 | |
| US12017679B2 (en) | Adaptive trust calibration | |
| US20240025395A1 (en) | Path generation based on predicted actions | |
| US12552410B2 (en) | Path generation based on predicted actions | |
| US12420830B2 (en) | Path generation based on predicted actions | |
| CN117022262A (zh) | 无人车速度规划控制方法、装置、电子设备及存储介质 | |
| WO2022158272A1 (ja) | 処理方法、処理システム、処理プログラム、処理装置 | |
| JP7125969B2 (ja) | 車両制御装置、車両制御方法、およびプログラム | |
| CN116601064A (zh) | 用于在检测到车辆周围有障碍物时控制车辆的方法;用于具有自主行驶功能模块的车辆的控制装置;计算机可读介质和机动车辆 | |
| WO2023213200A1 (zh) | 一种会车方法及相关装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20866454 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2020866454 Country of ref document: EP Effective date: 20220330 |
