WO2022133684A1 - 控制方法、相关设备及计算机可读存储介质 - Google Patents

控制方法、相关设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2022133684A1
WO2022133684A1 PCT/CN2020/138110 CN2020138110W WO2022133684A1 WO 2022133684 A1 WO2022133684 A1 WO 2022133684A1 CN 2020138110 W CN2020138110 W CN 2020138110W WO 2022133684 A1 WO2022133684 A1 WO 2022133684A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
obstacle
information
risk level
area
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
Application number
PCT/CN2020/138110
Other languages
English (en)
French (fr)
Inventor
王存连
陈瑞
龚胜波
吴曦
任绘锦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN202080004118.5A priority Critical patent/CN112703144A/zh
Priority to EP20966265.9A priority patent/EP4261092B1/en
Priority to PCT/CN2020/138110 priority patent/WO2022133684A1/zh
Publication of WO2022133684A1 publication Critical patent/WO2022133684A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • 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
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/18—Conjoint control of vehicle sub-units of different type or different function including control of braking systems
    • B60W10/184—Conjoint control of vehicle sub-units of different type or different function including control of braking systems with wheel brakes
    • 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
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/20—Conjoint control of vehicle sub-units of different type or different function including control of steering systems
    • 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
    • B60W30/0956—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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • 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
    • B60W2554/402—Type
    • 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
    • B60W2554/4041—Position
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data

Definitions

  • the present application relates to the technical field of intelligent driving, and in particular, to a control method, a related device, and a computer-readable storage medium.
  • the vehicle During the driving process of the vehicle, the vehicle itself plans the driving trajectory and drives according to the planned driving trajectory. In the face of obstacles in front of the vehicle or around the vehicle, it is particularly important how the vehicle executes the decision.
  • the vehicle determines whether the vehicle collides with the obstacle by detecting whether the distance between itself and the obstacle meets the safety threshold. If the distance between itself and the obstacle is less than the safety threshold. , to determine that the vehicle may collide with the obstacle. In this case, the vehicle needs to stop (or follow at a low speed) or perform an obstacle avoidance maneuver to avoid the collision to avoid the vehicle colliding with the obstacle.
  • parking or following a car at low speed
  • the current traffic rules do not allow changing lanes. Therefore, in the face of an obstacle ahead, how to avoid the obstacle to ensure the safety and smoothness of the vehicle is a technical problem that needs to be solved urgently.
  • the present application provides a control method, related equipment, and a computer-readable storage medium, which can effectively avoid obstacles when facing an obstacle ahead, and ensure the safety and smoothness of vehicle driving.
  • an embodiment of the present application provides a control method, which may include the following steps: first, acquiring vehicle information, obstacle information, and a drivable area of the vehicle; wherein, the drivable area of the vehicle is used to indicate that the vehicle can travel Safe driving area; for example, vehicle information may include but not limited to the location, size, etc. of the vehicle, and obstacle information may include but not limited to the location, size, etc.
  • the vehicle information, obstacle information and the drivable area of the vehicle indicate M planned paths, where M is an integer greater than 0; the M planned paths correspond to their respective traffic costs, and the traffic costs It is related to at least one of the following information: the risk level of the obstacle, the risk level of the vehicle; the risk level of the obstacle is used to indicate that the obstacle may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle; the vehicle The risk level is used to characterize the degree of damage that the vehicle may cause to obstacles.
  • the pass costs are related to at least one of the following information: the risk level of the obstacle and the risk level of the vehicle, wherein the risk level of the obstacle is used for Indicates that obstacles may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle.
  • the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • Path planning when the control device faces an obstacle intrusion, it can effectively avoid the obstacle and ensure the safety and smoothness of the vehicle.
  • the vehicle information includes the coordinates and dimensions of the vehicle
  • the obstacle information includes the coordinates and dimensions of the obstacle
  • the coordinates of the vehicle and the coordinates of the obstacle are coordinates in the geodetic coordinate system ENU
  • the method also It can include the following steps: perform grid processing on the drivable area of the vehicle to obtain a grid map; convert the coordinates of the obstacles from the ENU to the vehicle coordinate system according to the coordinates of the vehicle, and obtain the obstacles based on the size of the obstacles
  • the occupied area on the grid map based on the occupied area, obtain M planned paths from the starting point to the target point.
  • the drivable area of the vehicle is rasterized, and the occupied area of the obstacle on the grid map is obtained through the obstacle information, so that the path planning can be performed based on the occupied area, which is compared with the prior art. , reducing the dependence on sensor accuracy.
  • the implementation process of performing the first process may include: determining a target planned path, where the target planned path is a path with the smallest travel cost among the M planned paths.
  • the pass costs are related to at least one of the following information: the risk level of the obstacle and the risk level of the vehicle, wherein the risk level of the obstacle is used for Indicates that obstacles may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle.
  • the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle. route plan.
  • the control device faces the intrusion of obstacles, among the M planned paths, the planned path with the smallest traffic cost is determined as the target planned path, so that the control device can drive according to the above-mentioned target planned path, and can effectively avoid obstacles and ensure the safety and smoothness of the vehicle.
  • the travel cost corresponding to the target planned path is less than the target threshold.
  • the control device faces an obstacle intrusion, among the M planned paths, the planned path with the smallest traffic cost is determined as the target planned path, and in addition, it is further judged whether the above-mentioned target planned path is smaller than the target threshold value.
  • the target threshold is used to indicate the acceptable maximum traffic cost, and when it is determined that the target planned path is less than the target threshold, the control device can drive according to the above-mentioned target planned path; when it is determined that the target planned path is greater than (or equal to ) target threshold, the control device may control the vehicle to remain stationary.
  • the above method may further include the following steps: obtaining predicted collision information; wherein the predicted collision information is information obtained when predicting a possible collision between the vehicle and the obstacle; determining the risk of the obstacle according to the predicted collision information class and/or risk class of the vehicle.
  • the control device can determine the risk level of the obstacle and/or the risk level of the vehicle based on the predicted collision information, which reduces the dependence on the accuracy of the sensor compared to the prior art.
  • this implementation provides a basis for subsequent path planning, and can achieve more optimized path planning. When the control device faces an obstacle intrusion, it can effectively avoid the obstacle and ensure the safety and peace of the vehicle. Consistency.
  • the predicted collision information includes: the speed ⁇ v of the vehicle relative to the obstacle, the intersecting volume when the vehicle and the obstacle may collide, the collision angle when the vehicle and the obstacle may collide, the vehicle and the obstacle At least one of the center distance between obstacles and the class to which the obstacles belong.
  • an embodiment of the present application provides a risk estimation method, and the method may include the following steps: first, obtain predicted collision information according to the position information and motion state information of the vehicle and the obstacle; the predicted collision information is the predicted vehicle and The information obtained when the obstacle may collide; then, the risk level of the obstacle and/or the risk level of the vehicle is obtained according to the predicted collision information; the risk level of the obstacle is used to indicate that the obstacle may encroach on the drivable area of the vehicle and the obstacle The degree of damage that may be caused to the vehicle; the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to obstacles.
  • control device can determine the risk level of the obstacle and/or the risk level of the vehicle based on the predicted collision information, which reduces the dependence on the accuracy of the sensor compared to the prior art.
  • the predicted collision information includes: the speed ⁇ v of the vehicle relative to the obstacle, the intersecting volume when the vehicle and the obstacle may collide, the collision angle when the vehicle and the obstacle may collide, the vehicle and the obstacle At least one of the center distance between obstacles and the class to which the obstacles belong.
  • an embodiment of the present application provides a path planning device, the device may include: an acquisition unit, configured to acquire vehicle information, obstacle information, and a drivable area of the vehicle; wherein, the drivable area of the vehicle The area is used to indicate the area where the vehicle can drive safely; the processing unit is used to execute the first process according to the vehicle information and obstacle information and in combination with the drivable area of the vehicle; wherein the vehicle information, The obstacle information and the drivable area of the vehicle indicate M planned paths, where M is an integer greater than 0; the M planned paths correspond to respective pass costs, and the pass costs are equal to at least one of the following information: related to: the risk level of the obstacle, the risk level of the vehicle; the risk level of the obstacle is used to characterize that the obstacle may encroach on the drivable area of the vehicle and the obstacle is harmful to the vehicle The degree of damage that may be caused; the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • the pass costs are related to at least one of the following information: the risk level of the obstacle and the risk level of the vehicle, wherein the risk level of the obstacle is used for Indicates that obstacles may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle.
  • the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • Path planning when the control device faces an obstacle intrusion, it can effectively avoid the obstacle and ensure the safety and smoothness of the vehicle.
  • the vehicle information includes the coordinates and size of the vehicle
  • the obstacle information includes the coordinates and size of the obstacle
  • the coordinates of the vehicle and the coordinates of the obstacle are in the earth coordinates under the coordinate system ENU
  • the processing unit is further configured to: perform grid processing on the drivable area of the vehicle to obtain a grid map; convert the coordinates of the obstacles from the coordinates of the vehicle from the coordinates of the vehicle
  • the ENU is down-converted to the vehicle coordinate system, and the occupied area of the obstacle on the grid map is obtained in combination with the size of the obstacle; based on the occupied area, M plans from the starting point to the target point are obtained. path.
  • the processing unit is specifically configured to: determine a target planned path, where the target planned path is the path with the smallest travel cost among the M planned paths.
  • the travel cost corresponding to the target planned path is smaller than the target threshold.
  • the obtaining unit is further configured to obtain predicted collision information; wherein the predicted collision information is information obtained when predicting that the vehicle and the obstacle may collide; the processing unit, It is also used for determining the risk level of the obstacle and/or the risk level of the vehicle according to the predicted collision information.
  • the predicted collision information includes: a speed ⁇ v of the vehicle relative to the obstacle, a volume intersected when the vehicle and the obstacle may collide, the vehicle and the obstacle. at least one of a collision angle when the obstacle may collide, a center distance between the vehicle and the obstacle, and a category to which the obstacle belongs.
  • an embodiment of the present application provides a risk assessment apparatus, which may include: an information acquisition unit configured to acquire predicted collision information according to position information and motion state information of vehicles and obstacles; the predicted collision information Information obtained when predicting a possible collision between the vehicle and the obstacle; a processing unit, configured to obtain the risk level of the obstacle and/or the risk level of the vehicle according to the predicted collision information; the obstacle The risk level of the obstacle is used to characterize the degree of damage that the obstacle may cause to the vehicle and the obstacle may encroach on the drivable area of the vehicle; the risk level of the vehicle is used to characterize the possible damage to the vehicle by the vehicle Describe the extent of damage caused by obstacles.
  • the predicted collision information includes: a speed ⁇ v of the vehicle relative to the obstacle, a volume intersected when the vehicle and the obstacle may collide, the vehicle and the obstacle. at least one of a collision angle when the obstacle may collide, a center distance between the vehicle and the obstacle, and a category to which the obstacle belongs.
  • an embodiment of the present application further provides a terminal, which can implement the functions described in the methods involved in any one of the third aspect and/or the fourth aspect.
  • the above functions can be implemented by hardware, or can be
  • the hardware or software includes one or more units or modules corresponding to the above functions.
  • an embodiment of the present application provides a control device, including a processor and a memory, where the processor and the memory are connected to each other, wherein the memory is used to store a computer program, and the computer program includes program instructions, the The processor is configured to invoke the program instructions to execute the method described in any one of the first aspect or the second aspect.
  • an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program includes program instructions that, when executed by an execution processor, cause the processor to A method as in the first aspect or the second aspect is performed.
  • an embodiment of the present application further provides a computer program, the computer program includes computer software instructions, and when executed by a computer, the computer software instructions cause the computer to execute the method of the first aspect or the second aspect .
  • FIG. 1 is a functional block diagram of a vehicle 100 according to an embodiment of the present application.
  • FIG. 2a is a schematic diagram of a first application scenario provided by an embodiment of the present application.
  • FIG. 2b is a schematic diagram of a second application scenario provided by an embodiment of the present application.
  • FIG. 2c is a schematic diagram of a third application scenario provided by an embodiment of the present application.
  • FIG. 2d is a schematic diagram of a fourth application scenario provided by an embodiment of the present application.
  • 3a is a schematic flowchart of a control method provided by an embodiment of the present application.
  • FIG. 3b is a schematic diagram of a planning path provided by an embodiment of the present application.
  • FIG. 3c is a schematic diagram of a drivable area of a vehicle according to an embodiment of the present application.
  • FIG. 3d is a schematic diagram of a drivable area of another vehicle according to an embodiment of the application.
  • 3e is a schematic diagram of a grid map provided by an embodiment of the present application.
  • 3f is a schematic diagram of expanding the occupied area of an obstacle according to an embodiment of the present application.
  • 3g is another schematic diagram of expanding the occupied area of an obstacle according to an embodiment of the present application.
  • 3h is a schematic diagram of a vehicle geometry provided by an embodiment of the application.
  • 3i is a schematic diagram of a vehicle colliding with an obstacle according to an embodiment of the present application.
  • 3j is a schematic flowchart of another control method provided by an embodiment of the present application.
  • FIG. 3k is a schematic diagram of displaying the geometric intersection of a vehicle and an obstacle through a central control screen of the vehicle according to an embodiment of the application;
  • FIG. 4 is a schematic flowchart of a risk assessment method provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a control device provided by an embodiment of the present application.
  • FIG. 6 provides a schematic structural diagram of a risk assessment device according to an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a control device according to an embodiment of the present application.
  • any embodiment or design approach described in the embodiments of the present application as “exemplarily” or “such as” should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as “exemplarily” or “such as” is intended to present the related concepts in a specific manner.
  • “A and/or B” means A and B, and A or B has two meanings.
  • “A, and/or B, and/or C” means any one of A, B, and C, alternatively, means any two of A, B, and C, alternatively, means A and B and C.
  • a road refers to a passage for vehicles to travel and for connecting two places.
  • a lane is a passageway for a single column of vehicles traveling in the same direction.
  • Common lanes include different types of lanes such as straight lanes, left-turn lanes, and right-turn lanes.
  • a road consists of one or more lanes. For example, a road consists of four lanes: 1 left turn lane, 2 straight lanes and 1 right turn lane.
  • the planned path refers to a path used to make the vehicle drive on a designated road, and may also refer to a path that is accurate to the sub-meter level and used to make the vehicle drive on a designated lane.
  • control method provided in this application can be applied to the scene where obstacles intrude (or: small intrusions into) the current lane where the vehicle is driving, and can also be applied to the entire automatic driving process of the vehicle to ensure that the vehicle is driving Safety and smoothness during the process.
  • FIG. 1 is a functional block diagram of a vehicle 100 provided by an embodiment of the present application.
  • the vehicle 100 may be configured in a fully autonomous driving mode or a partially autonomous driving mode, or a manual driving mode.
  • the vehicle 100 may include at least the following subsystems: a sensing subsystem 101 , a decision-making subsystem 102 and an execution subsystem 103 . in,
  • the sensing subsystem 101 may include at least sensors.
  • the sensors may include internal sensors and external sensors; wherein, the internal sensors are used to monitor the state of the vehicle, and may include at least one of a vehicle speed sensor, an acceleration sensor, an angular velocity sensor, and the like.
  • the external sensors are mainly used to monitor the external environment around the vehicle, which can include video sensors and radar sensors for example; the video sensor is used to acquire and monitor the image data of the surrounding environment of the vehicle; the radar sensor is used to acquire and monitor the electromagnetic waves of the surrounding environment of the vehicle Data, mainly by emitting electromagnetic waves, and then by receiving electromagnetic waves reflected by surrounding objects to detect the distance between surrounding objects and the vehicle, the shape of surrounding objects and other data.
  • multiple radar sensors are distributed throughout the exterior of the vehicle 100 .
  • a subset of the plurality of radar sensors are coupled to the front of the vehicle 100 to locate objects in front of the vehicle 100 .
  • One or more other radar sensors may be located at the rear of the vehicle 100 to locate objects behind the vehicle 100 when the vehicle 100 is moving backwards.
  • Other radar sensors may be located on the sides of the vehicle 100 to locate objects such as other vehicles 100 that approach the vehicle 100 from the side.
  • a light detection and ranging (LIDAR) sensor may be mounted on the vehicle 100 , eg, by mounting the LIDAR sensor in a rotating structure mounted on top of the vehicle 100 .
  • the rotating LIDAR sensor 120 can then transmit light signals around the vehicle 100 in a 360° pattern, continuously mapping all objects around the vehicle 100 as the vehicle 100 moves.
  • LIDAR light detection and ranging
  • imaging sensors such as cameras, video cameras, or other similar image capture sensors may be mounted on the vehicle 100 to capture images as the vehicle 100 moves.
  • Multiple imaging sensors may be placed on all sides of the vehicle 100 to capture images around the vehicle 100 in a 360° pattern. Imaging sensors can capture not only visible spectrum images, but also infrared spectrum images.
  • a Global Positioning System (GPS) sensor may be located on the vehicle 100 to provide the controller with geographic coordinates related to the location of the vehicle 100 and the time of generation of the coordinates.
  • GPS includes an antenna for receiving GPS satellite signals and a GPS receiver coupled to the antenna. For example, when an object is observed in an image or another sensor, GPS can provide the geographic coordinates and time of the discovery.
  • the decision-making subsystem 102 may at least include an electronic control unit (Electronic Control Unit, ECU), a map database, and an object database.
  • ECU Electronic Control Unit
  • ECU also known as "trip computer”, “vehicle computer”, etc.
  • MCU microcontroller Unit
  • memory for example, read-only memory ROM, random access memory RAM
  • input/output interface for example, read-only memory ROM, random access memory RAM
  • input/output interface for example, read-only memory ROM, random access memory RAM
  • analog-to-digital converter analog-to-digital converter
  • large-scale integrated circuits such as shaping and driving.
  • the decision-making subsystem 102 may also include a communication unit.
  • the ECU is a computing device used to control the vehicle 100, and performs a decision-making control function.
  • an ECU is connected to a bus and communicates with other devices via the bus.
  • the ECU can acquire information from internal and external sensors, map database and HMI, and output the corresponding information to the HMI and actuators.
  • the ECU loads the program stored in the ROM into the RAM, and the CPU runs the program in the RAM to realize the automatic driving function.
  • an ECU may consist of multiple ECUs.
  • the ECU can identify static and/or dynamic objects around the vehicle, for example, based on the acquisition of object monitoring results from external sensors.
  • the ECU can monitor the speed, direction and other attributes of surrounding targets.
  • the ECU can obtain the state information of the vehicle itself, based on the output information of the internal sensors. Based on this information, the ECU plans the driving path, and outputs corresponding control signals to the actuator, which executes the corresponding lateral and longitudinal movements.
  • control device may include, but is not limited to, the above-mentioned ECU.
  • control transposition may include an acquisition unit and a processing unit; wherein,
  • the obtaining unit is used to obtain vehicle information, obstacle information and the drivable area of the vehicle; wherein, the drivable area of the vehicle is used to indicate the area where the vehicle can drive safely; the processing unit is used to obtain the vehicle information, obstacle information, and The first process is performed in combination with the drivable area of the vehicle; wherein, the vehicle information, the obstacle information, and the drivable area of the vehicle indicate M planned paths, where M is an integer greater than 0; the M planned paths correspond to their respective traffic costs,
  • the passing cost is related to at least one of the following information: the risk level of the obstacle, the risk level of the vehicle; the risk level of the obstacle is used to indicate that the obstacle may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle ;
  • the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to obstacles.
  • the above method can still plan a hazard avoidance path with the least collision damage for the driver to deal with urgently. It can effectively avoid obstacles and ensure the safety of the vehicle to the greatest extent.
  • a virtual wall is generated in front of the obstacle, so that the vehicle stops or slows down before the obstacle, so as to ensure that the vehicle is in the driving process. security in.
  • the above-mentioned obtaining unit can also be used to: obtain predicted collision information; wherein, the predicted collision information is the information obtained when predicting that a vehicle and an obstacle may collide; the above-mentioned processing unit can also be used to: according to The predicted collision information determines the risk level of the obstacle and/or the risk level of the vehicle.
  • control device may perform path planning based on the risk level of the obstacle and the risk level of the vehicle determined by the above method, and may also perform early warning and reminding, etc., which are not specifically limited here.
  • the communication unit is used for V2X (vehicle to everything, that is, Vehicle to X) communication.
  • V2X vehicle to everything
  • data interaction can be performed with surrounding vehicles, roadside communication devices, and cloud servers.
  • a radio coupled to an antenna may be located in the vehicle 10 to provide wireless communication for the system.
  • the radio is used to operate any wireless communication technology or wireless standard, including but not limited to WiFi (IEEE 802.11), cellular (eg, Global System for Mobile Communications (GSM), Code Division Multiple Access, One or more of CDMA), Time Division Multiple Access (TDMA), Long Term Evolution (LTE), New Radio (New Radio).
  • GSM Global System for Mobile Communications
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • LTE Long Term Evolution
  • New Radio New Radio
  • a radio may include multiple radios so that the controller can Communicate over wireless channels using a variety of radio technologies.
  • content information or feature information of a corresponding object may be stored in the object database. For example, identifying the content of the reticle.
  • the object database that needs to be explained may be included in the map database, and does not necessarily exist separately.
  • the map database is used to store map information; in some feasible embodiments, a hard disk drive (Hard Disk Drive, HDD) may be used as a data storage device of the map database.
  • HDD Hard Disk Drive
  • the map database can contain rich location information; for example, the connection relationship between roads, the location of lane lines, the number of lane lines, and other objects around the road, etc.; for example, the information of traffic signs (such as , the location and height of the traffic lights, the content of the sign, such as speed limit signs, continuous detours, slow driving, etc.), trees around the road, building information, etc.
  • the aforementioned information is all associated with geographic location.
  • map information can also be used for positioning, combined with sensor data.
  • the stored map information may be two-dimensional information or three-dimensional information.
  • Actuating subsystem 103 may include at least actuators for controlling lateral and/or longitudinal movement of vehicle 100 .
  • the brake actuator controls the braking system and the braking force according to the control signal received from the ECU;
  • the steering actuator controls the steering system through the control signal from the ECU; in some feasible embodiments, the steering system may be an electronic steering system, Or a mechanical steering system.
  • FIG. 1 the elements of the system in FIG. 1 are for illustrative purposes only, and other systems including more or fewer components may be used to perform any of the methods disclosed herein.
  • FIG. 2a it is a schematic diagram of a first application scenario provided by an embodiment of the present application.
  • the vehicle is driving on a certain road section, and there is a social vehicle A in the left lane of the vehicle (the social vehicle A is an obstacle to the vehicle).
  • the vehicle learns that the social car A has a tendency to turn right (for example, the right turn signal of the social car is flashing collected by the vehicle through the camera), and the vehicle obtains vehicle information, obstacle information and the drivable area of the vehicle, such as , the drivable area may be at least one of a compliant drivable area and an emergency evasive drivable area, wherein the compliant driving area is used to indicate all areas in which the vehicle can safely drive when it satisfies the traffic rules;
  • the safe driving area is used to indicate the area where the vehicle does not collide with obstacles when driving; after that, the vehicle obtains M planned paths according to the vehicle information, obstacle information, and the driving area of the vehicle, where M is greater than 0.
  • the target planned path is obtained. For example, among the M planned paths, the planned path with the smallest travel cost is determined as the target planned path, so that the vehicle can follow the determined target planned path. Drive to avoid a collision with society A. Through this implementation, the safety of the vehicle during driving can be guaranteed.
  • the control device may adjust the driving speed and/or the driving path of the vehicle to avoid the obstacle, so as to ensure the safety of the vehicle during driving. safety.
  • a virtual wall is generated in front of the obstacle, so that the vehicle stops or slows down before the obstacle to ensure that the vehicle is driving during driving security.
  • FIG. 2b it is a schematic diagram of a second application scenario provided by an embodiment of the present application.
  • the vehicle is going straight on a certain road segment.
  • the right front of the vehicle suddenly enters the social vehicle A.
  • the vehicle obtains vehicle information, obstacle information and the drivable area of the vehicle.
  • the drivable area may be a compliant drivable area, an emergency avoidance area At least one of the dangerous drivable areas, wherein the compliant driving area is used to indicate all areas where the vehicle can travel safely when driving in compliance with traffic rules; the emergency evasive drivable area is used to indicate that the vehicle does not encounter obstacles when driving Collision area; after that, the vehicle obtains M planned paths according to the vehicle information, obstacle information, and combined with the drivable area of the vehicle, where M is an integer greater than 1, and the target is obtained based on the travel costs corresponding to the M planned paths.
  • the planned path for example, among the M planned paths, the planned path with the smallest traffic cost is determined as the target planned path, so that the vehicle can travel according to the determined target planned path to avoid collision with society A.
  • the safety of the vehicle during driving can be guaranteed.
  • FIG. 2c it is a schematic diagram of a third application scenario provided by an embodiment of the present application.
  • the vehicle is going straight on a certain road section.
  • the vehicle obtains vehicle information, obstacle information (wherein the obstacle information includes the information of the rider and the information of the social car A) and the available information of the vehicle.
  • the driving area for example, the drivable area may be at least one of a compliant drivable area and an emergency evasion drivable area, wherein the compliant driving area is used to indicate all the safe driving areas of the vehicle when it satisfies the traffic rules. area; the drivable area for emergency avoidance is used to indicate the area where the vehicle does not collide with obstacles when driving; after that, the vehicle obtains M planned paths according to the vehicle information, obstacle information, and combined with the drivable area of the vehicle, where M is an integer greater than 1, and the target planned path is obtained based on the corresponding travel costs of the M planned paths.
  • the planned path with the smallest travel cost is determined as the target planned path, so that the vehicle can follow the determined path.
  • the target plans a path to travel to avoid collision with society A. Through this implementation, the safety of the vehicle during driving can be guaranteed.
  • FIG. 2d it is a schematic diagram of a fourth application scenario provided by an embodiment of the present application.
  • the vehicle is driving on a certain road section, and there are obstacles in the driving path of the vehicle.
  • the obstacle is large particle debris, and there are social vehicles driving in the right lane of the vehicle, and there is traffic in the middle of the two lanes.
  • the marking line is a solid line. Vehicles cannot change lanes when traffic rules do not allow lane changing or the adjacent lanes are crowded with traffic.
  • the vehicle can obtain M planned routes according to the vehicle information, obstacle information, combined with the drivable area for emergency evasion, and obtain the target planned route based on the corresponding travel costs of the M planned routes.
  • the planned path with the smallest traffic cost is determined as the target planned path, so that the vehicle can travel according to the determined target planned path to avoid collision with society A. It can be understood that when the vehicle does not obtain the target planned path, the vehicle can remain stationary. When the social vehicle in the vehicle on the right passes safely, the emergency evasion drivable area is re-acquired to obtain the target planning path, so as to bypass the obstacle and continue to pass.
  • FIG. 3a is a schematic flowchart of a control method provided by an embodiment of the present application, and the method may include but is not limited to the following steps:
  • Step S301 acquiring vehicle information, obstacle information, and a drivable area of the vehicle; wherein, the drivable area of the vehicle is used to indicate an area in which the vehicle can travel safely.
  • the vehicle may also be referred to as a self-vehicle.
  • a sequence of points or curves connecting the starting position and the ending position is called a path
  • a strategy for forming a path is called path planning.
  • the planned path can be a path that enables the vehicle to travel on a designated road, or can be a path that is accurate to a sub-meter level so that the vehicle travels on a designated lane.
  • the planned path is a curve from the starting position A to the ending position B.
  • the drivable area of the vehicle may include at least one of a compliant driving area and an emergency evasion drivable area; wherein, the compliant driving area is used to indicate that the vehicle can drive safely when it complies with traffic rules.
  • the entire area of the emergency avoidance drivable area is used to indicate the area where the vehicle does not collide with obstacles when driving.
  • the vehicle is driving on a certain road section, and there is a social vehicle A in the left lane of the vehicle (the social vehicle A is an obstacle to the vehicle).
  • the vehicle learns that the social car A has a tendency to turn right (for example, the vehicle captures through the camera that the right turn signal of the social car is flashing), as shown in Figure 3c, the compliant driving area is used to indicate that the vehicle is within the All areas that can be safely driven when driving according to traffic rules may include but are not limited to areas within the lane (excluding lanes with mismatched directions) or the coverage area of the best virtual lane line in the intersection, parking zone area, etc.
  • the drivable area for emergency avoidance is used to indicate the area where the vehicle does not collide with obstacles when driving. Motor vehicle lanes, etc. It is understandable that a vehicle may violate the regulations when driving in an emergency avoidance area.
  • compliant driving area and emergency evasion drivable area are just examples, and the embodiments of the present application do not limit the name of the drivable area, and the compliant driving area may also be called the best drivable area.
  • the driving area, the drivable area for emergency avoidance, may also be called the worst drivable area.
  • the compliant driving area and the emergency evasion drivable area described above may also be referred to as a first area, a second area, and the like, respectively.
  • the drivable area may include one or more of the above-described compliant driving areas and emergency evasion drivable areas, which are not specifically limited in this application.
  • an obstacle refers to something that hinders or hinders the running of a vehicle, and may include moving or stationary persons or objects (such as cars, trees, and cyclists) in the drivable area of the vehicle.
  • the vehicle information may include, but is not limited to, the position of the vehicle (also referred to as coordinates), size, motion state information, etc.;
  • the obstacle information may include but not limited to the position of the obstacle (also referred to as coordinates) ), size, motion status information, etc.
  • the motion state information of the vehicle may include one or more of the following: the current vehicle speed, heading angle, steering wheel angle, and acceleration.
  • Step S302 Execute the first process according to the vehicle information, the obstacle information, and in combination with the drivable area of the vehicle.
  • the vehicle information, the obstacle information, and the drivable area of the vehicle indicate M planned paths, where M is an integer greater than 0, wherein the M planned paths correspond to their respective travel costs, and the travel costs are the same as At least one of the following information is related to: the risk level of the obstacle, the risk level of the vehicle; the risk level of the obstacle is used to indicate that the obstacle may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle; The risk level is used to characterize the degree of damage the vehicle may cause to obstacles.
  • the risk level of the obstacle and the risk level of the vehicle may or may not be the same.
  • the larger the traffic cost corresponding to the planned path the larger the cost when the vehicle travels along the planned path, and the smaller the probability of being selected during path planning.
  • the traffic cost can be a numerical value, and the M planned paths can obtain corresponding unitless numerical values based on the same standard.
  • the control device may acquire M planned paths according to vehicle information, obstacle information, and in combination with the drivable area of the vehicle.
  • the implementation process may include: first, acquiring vehicle information, obstacle information, and The drivable area of the vehicle, generally speaking, the drivable area of the vehicle may be a rectangular area with the self-vehicle as the center and the size of L*I.
  • the drivable area of the vehicle is rasterized to obtain a raster map; then, the coordinates of the obstacles are converted from the geodetic coordinate system ENU to the vehicle coordinate system according to the coordinates of the vehicle, and obtained in combination with the size of the obstacles
  • the occupied area of the obstacle on the grid map thus, M planned paths from the starting point to the target point can be obtained based on the above occupied area.
  • a square or other size rectangular area with a size of 50m*50m is used as the drivable area, and the drivable area is rasterized to obtain a grid map (gray in Figure 3e).
  • the grid resolution is 0.25m*0.25m, that is, the size of each grid in the grid map is 0.25m*0.25m.
  • the coordinates of obstacles are transformed from the ENU coordinate system to the vehicle coordinate system to obtain the relative position coordinates of the obstacles relative to the vehicle.
  • M planned paths can be obtained based on the above occupied area. Compared with the prior art, this method reduces the dependence on the accuracy of the sensor.
  • the control device may expand the occupied area of the obstacle according to the relative movement trend between the vehicle and the obstacle.
  • the so-called expansion is to expand the area of the occupied area of the obstacle.
  • the occupied area is adjusted with a first spatial expansion rate.
  • the occupied area is adjusted by the second space expansion rate.
  • the first spatial expansion rate is greater than the second spatial expansion rate.
  • expansion at a first length and expansion at a second length can be used to characterize a first rate of spatial expansion and a second rate of spatial expansion, respectively. The following situations are described in detail:
  • the obstacle is on the right side of the vehicle.
  • the first left boundary of the occupied area of the obstacle is set to the first left boundary of the obstacle.
  • a length is expanded. It can be known from FIG. 3f that the area of the occupied area after expansion is larger than that of the occupied area without expansion.
  • the obstacle is on the right side of the vehicle.
  • the first left boundary of the occupied area of the obstacle is set to the The expansion is performed by a length, and at the same time, the first right boundary of the occupied area of the obstacle is expanded by a second length. It can be known from FIG. 3g that the area of the expanded occupied area is larger than that of the unexpanded occupied area.
  • the first length and the second length may be different lengths.
  • the first length and the second length may be between e0 and e max , where e0 refers to the minimum moving length and e max refers to the maximum moving length.
  • the above-mentioned first length and second length may be determined according to the approach distance between the vehicle and the obstacle.
  • the expansion rate is close to a monotonic function of distance, but the expansion rate cannot be greater than the maximum degree of expansion e max .
  • the first length and the second length can be calculated according to a first formula, which can be described as:
  • e0 represents the minimum expansion length on both sides of the first driving area
  • e max represents the maximum expansion length on both sides of the first driving area
  • s represents the lateral shortest distance
  • the lateral closest distance refers to the component of the distance between the vehicle and the obstacle in the direction perpendicular to the lane.
  • the expansion rate may be a near monotonic function of velocity, but the expansion rate cannot be greater than the maximum degree of expansion e max .
  • the greater the approach speed between the vehicle and the obstacle the greater the first space expansion rate.
  • the smaller the approach speed between the vehicle and the obstacle the smaller the expansion rate of the second space.
  • the control device may obtain M planned paths based on the expanded occupied area.
  • a cost function can be used to calculate the travel cost corresponding to each planned path, wherein the cost function is constructed according to at least one of the safety item S, the comfort item C, the obstacle risk level R1, and the vehicle risk level R2
  • the cost function of is constructed according to at least one of the safety item S, the comfort item C, the obstacle risk level R1, and the vehicle risk level R2
  • the cost function of is constructed according to at least one of the safety item S, the comfort item C, the obstacle risk level R1, and the vehicle risk level R2
  • the cost function of is constructed according to at least one of the safety item S, the comfort item C, the obstacle risk level R1, and the vehicle risk level R2
  • the cost function of among them, the safety term S is used to represent the lateral target offset and the longitudinal speed offset maintained between the vehicle and the obstacle; the comfort term C is used to represent the degree of change in the acceleration of the vehicle, for example, the change in the acceleration of the vehicle
  • the degree can include lateral Jerk jerk and longitudinal Jerk jerk;
  • the degree of damage caused by obstacles to the vehicle can be divided into: slight scratches, slight deformation, vehicle body dents, etc.
  • the degree of damage caused by the vehicle to the obstacle is related to the category of the obstacle. For example, when the obstacle is a pedestrian, the degree of damage caused by the vehicle to the obstacle can include pedestrian injury; when the obstacle is other vehicles, the vehicle to the obstacle The degree of damage can include minor scratches, slight deformation, body dents, etc. It should be understood that the above examples are only examples and should not be construed as limitations.
  • the above-mentioned cost function may be:
  • w1, w2, w3 and w4 are weight coefficients; S represents the safety item; C represents the comfort item; R1 represents the risk level of the obstacle; R2 represents the risk level of the vehicle.
  • the control device can adjust the sizes of the above-mentioned w1, w2, w3, and w4.
  • the control device can increase the weight coefficient of the safety item S; or, when the control device detects an obstacle When the drivable area of the vehicle is invaded, and the operation information of the driver of the vehicle is acceleration and no steering, increase the weight coefficient of the safety term S; or, when the control device detects that an obstacle is occupying the drivable area of the vehicle, and When the operation information of the driver of the vehicle is to accelerate, steer and avoid obstacles, reduce the weight coefficient of the safety item S; When the information is deceleration without steering or deceleration steering, reduce the weight coefficient of the safety term S.
  • the control device when the control device determines that the collision time between the vehicle and the obstacle is less than the set value, the control device can increase the weight coefficient of the risk level R1 of the whole obstacle.
  • the above-mentioned safety item S, comfort item C, the risk level R1 of the obstacle and the risk level R2 of the vehicle can be respectively expressed as:
  • w11, w12, w21, w22 are weight coefficients.
  • the predicted collision information can be obtained according to the position information and motion state information of the vehicle and the obstacle; wherein, the predicted collision information is the information obtained when predicting that the vehicle and the obstacle may collide; then, Obtain the risk level of the obstacle and/or the risk level of the vehicle according to the predicted collision information.
  • the embodiment of the present application also provides a method of how to predict a collision between a vehicle and an obstacle.
  • the control device can predict the first collision of the vehicle within a preset time period according to the position information and motion state information of the vehicle and the obstacle.
  • the motion trajectory and the second motion trajectory of the obstacle and then determine whether the first motion trajectory and the second motion trajectory collide.
  • the size of the vehicle (L, W, H) and the size of the obstacle (l, w ,h) calculate the safety distance between the two, where the safety distance can be expressed as:
  • ⁇ represents the reserved amount, which is related to the perception accuracy of the vehicle.
  • the vehicle geometry refers to the geometric envelope of the vehicle, which represents the overall shape obtained by gradually extending the shape of a vehicle
  • the obstacle geometry refers to the geometric envelope of the obstacle.
  • FIG. 3h it is a schematic diagram of a vehicle geometry provided in an embodiment of the present application.
  • the heading angle of the obstacle at time t is obtained according to the second motion trajectory, so that the geometric model of the obstacle at time t can be obtained.
  • the geometric model of the obstacle at time t can be expressed as:
  • the rotation feature matrix A( ⁇ (t)) can be expressed as:
  • collisionStatu(t) collisionCheck(P ego ,P obj (t)
  • a schematic diagram of the collision between the first motion trajectory and the second motion trajectory may be as shown in FIG. 3i.
  • the above-mentioned method of judging whether there is an intersection between the geometric model of the vehicle and the geometric model of the obstacle at time t does not solely refer to the first motion trajectory corresponding to the vehicle and the first motion trajectory corresponding to the obstacle.
  • the intersection of two motion trajectories refers to the intersection of the motion trajectories of two geometric bodies.
  • the control device obtains the following predicted collision information, wherein the predicted collision information includes: the speed of the vehicle relative to the obstacle ⁇ v, At least one of the intersecting volume when the vehicle and the obstacle may collide, the collision angle when the vehicle and the obstacle may collide, the center distance between the vehicle and the obstacle, and the category to which the obstacle belongs.
  • control device can also acquire the collision time t0.
  • the risk level of the obstacle and the risk level of the vehicle may be obtained according to the predicted collision information.
  • the risk level of the obstacle and the risk level of the vehicle can be obtained through the risk assessment function.
  • the risk assessment function may be a function constructed according to predicted collision information.
  • the risk assessment function can be expressed as:
  • represents the collision angle when the vehicle and the obstacle may collide, o(x) Represents the center distance between the vehicle and the obstacle, and class represents the class of the obstacle.
  • the category to which the obstacle belongs may include, but is not limited to, pedestrians, other vehicles, and non-motor vehicles (eg, bicycles, electric motorcycles, etc.).
  • non-motor vehicles eg, bicycles, electric motorcycles, etc.
  • , w c can satisfy:
  • , and w c It can be determined by judging whether it is a key factor. For example, taking
  • the control device obtains M planned paths according to the vehicle information, obstacle information, and combined with the drivable area of the vehicle, and after determining the traffic cost corresponding to each planned path by the method described above, the control device can be based on each planned path.
  • the first processing is performed on the corresponding toll cost, and the first processing may include but is not limited to the following steps:
  • Step S302-1 Determine a target planned path, wherein the target planned path is the path with the smallest travel cost among the M planned paths.
  • control device may sort the M planned paths based on the respective travel costs of the M planned paths, and obtain a sorting result; then, in the obtained sorting result, determine the planned path with the smallest travel cost as the target planning path. Then, when the control device drives according to the above-determined target planning path, it can effectively avoid obstacles and ensure the safety and smoothness of the vehicle.
  • Step S302-2 judging whether the travel cost corresponding to the target planned path is less than the target threshold; if so, execute step S302-3; if not, execute step S302-4.
  • the target threshold is used to indicate an acceptable maximum toll cost.
  • the control device may determine the target threshold by analyzing the user's historical traffic data (eg, the historical traffic data may include historical traffic accident data).
  • the target threshold may be set by the user according to their own needs.
  • Step S302-3 when it is determined that the target planned route is smaller than the target threshold, drive according to the target planned route.
  • Step S302-4 in the case that it is determined that the target planned path is not less than (for example, may be greater than or equal to) the target threshold, control the vehicle to remain stationary.
  • the pass costs are related to at least one of the following information: the risk level of the obstacle and the risk level of the vehicle, wherein the risk level of the obstacle is used for Indicates that obstacles may encroach on the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle.
  • the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • Path planning when the control device faces an obstacle intrusion, it can effectively avoid the obstacle and ensure the safety and smoothness of the vehicle.
  • a schematic diagram of the intersection between the geometric model of the vehicle and the geometric model of the obstacle at time t may be displayed on the central control screen 501 of the vehicle, and based on the intersection of The situation sends out a warning message, for example, the warning message can be: Please note, please note that after 5 seconds, the vehicle will collide with an obstacle.
  • the warning prompt information may also be: please drive carefully, the vehicle will collide with an obstacle.
  • the driver's driving attention can be improved, in this case, the driver can switch the automatic driving mode to the manual driving mode, or reduce the driving level of the autonomous vehicle, for example, the automatic driving level L5 switches to autopilot level L3, and so on.
  • FIG. 4 is a schematic flowchart of a risk assessment method provided by an embodiment of the present application, and the method may include but is not limited to the following steps:
  • Step S401 obtaining predicted collision information according to the position information and motion state information of the vehicle and the obstacle; the predicted collision information is the information obtained when predicting that the vehicle and the obstacle may collide.
  • the predicted collision information includes: the speed ⁇ v of the vehicle relative to the obstacle, the intersecting volume when the vehicle and the obstacle may collide, the collision angle when the vehicle and the obstacle may collide, the vehicle and the obstacle At least one of the center distance between and the category of the obstacle.
  • Step S402 Obtain the risk level of the obstacle and/or the risk level of the vehicle according to the predicted collision information; the risk level of the obstacle is used to represent the obstacle that may occupy the drivable area of the vehicle and the degree of damage that the obstacle may cause to the vehicle; The risk level is used to characterize the degree of damage that the vehicle may cause to obstacles.
  • control device may obtain the risk level of the obstacle and the risk level of the vehicle through the risk assessment function.
  • the risk assessment function may be a function constructed according to predicted collision information.
  • the risk assessment function can be expressed as:
  • represents the intersecting volume when the vehicle and the obstacle may collide,
  • represents the collision angle when the vehicle and the obstacle may collide, o(x) represents The center distance between the vehicle and the obstacle, class indicates the class of the obstacle.
  • the category to which the obstacle belongs may include, but is not limited to, pedestrians, other vehicles, and non-motor vehicles (eg, bicycles, electric motorcycles, etc.).
  • non-motor vehicles eg, bicycles, electric motorcycles, etc.
  • , w c can satisfy:
  • , and w c It can be determined by judging whether it is a key factor. For example, taking
  • the vehicle can perform path planning based on the risk level of the obstacle and the risk level of the vehicle determined by the above method, and can also perform early warning reminders, etc., which are not specifically limited here.
  • control device can determine the risk level of the obstacle and/or the risk level of the vehicle based on the predicted collision information, which reduces the dependence on the accuracy of the sensor compared to the prior art.
  • an embodiment of the present application provides a control device, and the device 50 may include:
  • an obtaining unit 500 configured to obtain vehicle information, obstacle information, and a drivable area of the vehicle; wherein, the drivable area of the vehicle is used to indicate an area where the vehicle can travel safely;
  • the processing unit 510 is configured to perform a first process according to the vehicle information, the obstacle information, and in combination with the drivable area of the vehicle; wherein the vehicle information, the obstacle information, and the drivable area of the vehicle
  • the area indicates M planned paths, where M is an integer greater than 0; the M planned paths correspond to respective pass costs, and the pass costs are related to at least one of the following information: the risk level of the obstacle, the the risk level of the vehicle; the risk level of the obstacle is used to characterize the degree of damage that the obstacle may cause to the vehicle and the obstacle may encroach on the drivable area of the vehicle; the risk level of the vehicle Used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • the vehicle information includes the coordinates and size of the vehicle
  • the obstacle information includes the coordinates and size of the obstacle
  • the coordinates of the vehicle and the coordinates of the obstacle are in the earth
  • the coordinates under the coordinate system ENU; the above-mentioned processing unit 510 is also used for:
  • M planned paths from the starting point to the target point are acquired.
  • processing unit 510 is specifically configured to:
  • a target planned path is determined, where the target planned path is the path with the smallest travel cost among the M planned paths.
  • the travel cost corresponding to the target planned path is smaller than the target threshold.
  • the obtaining unit is further configured to obtain predicted collision information; wherein the predicted collision information is information obtained when predicting that the vehicle and the obstacle may collide; the processing unit is further for determining the risk level of the obstacle and/or the risk level of the vehicle based on the predicted collision information.
  • the speed ⁇ v of the vehicle relative to the obstacle, the intersecting volume when the vehicle and the obstacle may collide, and when the vehicle and the obstacle may collide At least one of the collision angle of , the center distance between the vehicle and the obstacle, and the category to which the obstacle belongs.
  • an embodiment of the present application provides a risk assessment device, and the device 60 may include:
  • Obtaining unit 600 is used to obtain predicted collision information according to the position information and motion state information of the vehicle and the obstacle; the predicted collision information is the information obtained when predicting that the vehicle and the obstacle may collide;
  • the processing unit 610 is configured to obtain the risk level of the obstacle and/or the risk level of the vehicle according to the predicted collision information; the risk level of the obstacle is used to indicate that the obstacle may encroach on the vehicle. The drivable area and the degree of damage that the obstacle may cause to the vehicle; the risk level of the vehicle is used to characterize the degree of damage that the vehicle may cause to the obstacle.
  • the predicted collision information includes: a speed ⁇ v of the vehicle relative to the obstacle, a volume intersected when the vehicle and the obstacle may collide, the vehicle and the obstacle. at least one of a collision angle when the obstacle may collide, a center distance between the vehicle and the obstacle, and a category to which the obstacle belongs.
  • FIG. 7 is a schematic structural diagram of a control device provided by an embodiment of the present application.
  • the control device 70 includes at least one processor 701 and at least one communication interface 703 .
  • at least one memory 702 may also be included.
  • the control device may also include general components such as an antenna, which will not be described in detail here.
  • the processor 701 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the above programs.
  • CPU central processing unit
  • ASIC application-specific integrated circuit
  • the communication interface 703 is used to communicate with other devices or a communication network.
  • Memory 702 which can be read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (random access memory, RAM) or other types of static storage devices that can store information and instructions
  • ROM read-only memory
  • RAM random access memory
  • static storage devices that can store information and instructions
  • Type of dynamic storage device it can also be Electrically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, CD-ROM storage (including compact discs, laser discs, compact discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by Any other medium accessed by the computer, but not limited to this.
  • the memory can exist independently and be connected to the processor through a bus.
  • the memory can also be integrated with the processor.
  • the memory 702 is used for storing the application code for executing the above solution, and the execution is controlled by the processor 701 .
  • the processor 701 is configured to execute the application code stored in the memory 702 .
  • the code stored in the memory 702 may execute the control method provided in FIG. 3a and FIG. 3j above, and the risk assessment method provided in FIG. 4 .
  • the processor 701 is used to call data and program codes in the memory, and execute:
  • the drivable area of the vehicle is used to indicate an area where the vehicle can safely drive;
  • the vehicle information, the obstacle information and the drivable area of the vehicle indicate M planned paths, where M is an integer greater than 0; the M planned paths correspond to their respective traffic costs, and the traffic costs It is related to at least one of the following information: the risk level of the obstacle, the risk level of the vehicle; the risk level of the obstacle is used to characterize that the obstacle may encroach on the drivable area of the vehicle and all The degree of damage that the obstacle may cause to the vehicle; the risk level of the vehicle is used to represent the degree of damage that the vehicle may cause to the obstacle.
  • the vehicle information includes the coordinates and size of the vehicle
  • the obstacle information includes the coordinates and size of the obstacle
  • the coordinates of the vehicle and the coordinates of the obstacle are coordinates in the geodetic coordinate system ENU
  • the processor 701 can also be used to:
  • M planned paths from the starting point to the target point are acquired.
  • the processor 701 performing the first process may include: determining a target planned path, where the target planned path is the path with the smallest travel cost among the M planned paths. Wherein, the travel cost corresponding to the target planned path is less than the target threshold.
  • the processor 701 may also be used to: obtain predicted collision information; wherein, the predicted collision information is information obtained when predicting that the vehicle and the obstacle may collide; determine the collision according to the collision information The risk level of the obstacle and/or the risk level of the vehicle.
  • the predicted collision information includes: the speed ⁇ v of the vehicle relative to the obstacle, the intersecting volume when the vehicle and the obstacle may collide, and when the vehicle and the obstacle may collide At least one of the collision angle of , the center distance between the vehicle and the obstacle, and the category to which the obstacle belongs.
  • control device 70 for the functions of the control device 70 described in the embodiments of the present application, reference may be made to the relevant descriptions in the method embodiments described above in FIG. 3 a , FIG. 3 j , and FIG.
  • Embodiments of the present application further provide a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program enables the control apparatus to execute any control method described in the foregoing method embodiments. some or all of the steps.
  • Embodiments of the present application further provide a computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause an electronic device to execute the method described in the foregoing method embodiments Some or all of the steps of any convolution method.
  • Computer-readable media may include computer-readable storage media, which corresponds to tangible media, such as data storage media, or communication media including any medium that facilitates transfer of a computer program from one place to another (eg, according to a communication protocol) .
  • a computer-readable medium may generally correspond to (1) a non-transitory tangible computer-readable storage medium, or (2) a communication medium, such as a signal or carrier wave.
  • Data storage media can be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, code and/or data structures for implementing the techniques described in this application.
  • the computer program product may comprise a computer-readable medium.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种控制方法、相关设备及计算机可读存储介质，该方法中，首先获取车辆信息、障碍物信息以及车辆的可行驶区域（S301）。根据车辆信息、障碍物信息，并结合车辆的可行驶区域，执行第一处理（S302）；其中，车辆信息、障碍物信息以及车辆的可行驶区域指示了M条规划路径，M为大于0的整数；M条规划路径对应各自的通行代价，通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。上述方法可有效避让障碍物，保证车辆行驶的安全性和平顺性。

Description

控制方法、相关设备及计算机可读存储介质 技术领域
本申请涉及智能驾驶技术领域，尤其涉及一种控制方法、相关设备及计算机可读存储介质。
背景技术
在车辆的行驶过程中，由车辆自身规划行驶轨迹，并按照规划的行驶轨迹行驶，面对车辆前方或车辆周围有障碍物的情况下，车辆如何执行决策显得尤为重要。
现有技术中，车辆前方有障碍物入侵当前车道时，车辆通过检测自身与障碍物间的距离是否满足安全阈值来判断车辆是否与障碍物发生碰撞，若自身与障碍物间的距离小于安全阈值，确定车辆与障碍物可能会发生碰撞。在这种情况下，车辆需要停车(或低速跟车)或执行避障动作避免碰撞，以避免车辆与障碍物发生碰撞。然而，在这一实现方式中，停车(或低速跟车)会影响本车道交通效率，进行换道避障车辆会与相邻车道车辆互动，增加不可控因素(社会车辆)对车辆的影响。尤其在某些特定场景下，当前交通规则并不允许换道。因此，面对前方障碍物，如何避让障碍物，以保证车辆行驶的安全性及平顺性是亟需解决的技术问题。
发明内容
本申请提供了一种控制方法、相关设备及计算机可读存储介质，面对前方障碍物时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
第一方面，本申请实施例提供了一种控制方法，该方法可以包括如下步骤：首先，获取车辆信息、障碍物信息以及车辆的可行驶区域；其中，车辆的可行驶区域用于指示车辆可以安全行驶的区域；例如，车辆信息可以包括但不限于车辆的位置、尺寸等，障碍物信息可以包括但不限于障碍物的位置、尺寸等；之后，根据车辆信息、障碍物信息，并结合车辆的可行驶区域，执行第一处理；其中，车辆信息、障碍物信息以及车辆的可行驶区域指示了M条规划路径，M为大于0的整数；M条规划路径对应各自的通行代价，通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。
实施本申请实施例，由于M条规划路径对应各自的通行代价，该通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级，其中，障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度，车辆的风险等级用于表征车辆可能对障碍物造成的损失程度，通过这一实现方式，可以实现更为优化的路径规划，当控制装置面对有障碍物入侵时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
在一种可能的实现方式中，车辆信息包括车辆的坐标和尺寸，障碍物信息包括障碍物 的坐标和尺寸，车辆的坐标和障碍物的坐标为在大地坐标系ENU下的坐标；该方法还可以包括如下步骤：对车辆的可行驶区域进行栅格化处理，得到栅格地图；根据车辆的坐标将障碍物的坐标从ENU下转换到车辆坐标系下，并结合障碍物的尺寸获取障碍物在栅格地图上的占据区域；基于占据区域，获取M条从起始点到目标点的规划路径。实施本申请实施例，对车辆的可行驶区域进行栅格化处理，并通过障碍物信息获取障碍物在栅格地图上的占据区域，从而可以基于占据区域进行路径规划，相比于现有技术，降低了对传感器精度的依赖性。
在一种可能的实现方式中，执行第一处理的实现过程可以包括：确定目标规划路径，该目标规划路径为M条规划路径中通行代价最小的路径。实施本申请实施例，由于M条规划路径对应各自的通行代价，该通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级，其中，障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度，车辆的风险等级用于表征车辆可能对障碍物造成的损失程度，通过这一实现方式，可以实现更为优化的路径规划。当控制装置面对有障碍物入侵时，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，从而控制装置可以按照上述目标规划路径进行驾驶，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
在一种可能的实现方式中，目标规划路径对应的通行代价小于目标阈值。实施本申请实施例，当控制装置面对有障碍物入侵时，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，此外，还进一步判断上述目标规划路径是否小于目标阈值，其中，该目标阈值用于指示可以接受的最大通行代价，在判断出目标规划路径小于目标阈值的情况下，控制装置可以按照上述目标规划路径进行驾驶；在判断出目标规划路径大于(或等于)目标阈值的情况下，控制装置可以控制车辆保持静止。现有技术中，控制装置进行路径规划时，只考虑碰撞或不碰撞，在预测出所有规划路径均会与障碍物发生碰撞的情况下，路径规划失败。本申请相较于现有技术来说，当车辆与障碍物会出现碰撞的情况下，仍然可以规划出碰撞伤害最小的避险路径，供驾驶员紧急处理，一方面，可以有效避免路径规划失败的情形；另一方面，还可以有效避让障碍物，可以在最大程度上保证车辆行驶的安全性。
在一种可能的实现方式中，上述方法还可以包括如下步骤：获取预测碰撞信息；其中，预测碰撞信息为预测车辆和障碍物可能发生碰撞时获取的信息；根据预测碰撞信息确定障碍物的风险等级和/或车辆的风险等级。实施本申请实施例，控制装置可以基于预测碰撞信息来确定障碍物的风险等级和/或车辆的风险等级，相比于现有技术，降低了对传感器精度的依赖性。此外，通过这一实现方式，为后续路径规划提供了基础，可以实现更为优化的路径规划，当控制装置面对有障碍物入侵时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
在一种可能的实现方式中，预测碰撞信息包括：车辆相对于障碍物的速度Δv、车辆与障碍物可能发生碰撞时相交的体积、车辆与障碍物可能发生碰撞时的碰撞夹角、车辆与障碍物之间的中心距离、障碍物的所属类别中的至少一个。
第二方面，本申请实施例提供了一种风险估计方法，该方法可以包括如下步骤：首先， 根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；预测碰撞信息为预测车辆和障碍物可能发生碰撞时获取的信息；然后，根据预测碰撞信息获取障碍物的风险等级和/或车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。
实施本申请实施例，控制装置可以基于预测碰撞信息来确定障碍物的风险等级和/或车辆的风险等级，相比于现有技术，降低了对传感器精度的依赖性。
在一种可能的实现方式中，预测碰撞信息包括：车辆相对于障碍物的速度Δv、车辆与障碍物可能发生碰撞时相交的体积、车辆与障碍物可能发生碰撞时的碰撞夹角、车辆与障碍物之间的中心距离、障碍物的所属类别中的至少一个。
第三方面，本申请实施例提供了一种路径规划装置，该装置可以包括：获取单元，用于获取车辆信息、障碍物信息以及所述车辆的可行驶区域；其中，所述车辆的可行驶区域用于指示所述车辆可以安全行驶的区域；处理单元，用于根据所述车辆信息、障碍物信息，并结合所述车辆的可行驶区域，执行第一处理；其中，所述车辆信息、所述障碍物信息以及所述车辆的可行驶区域指示了M条规划路径，M为大于0的整数；所述M条规划路径对应各自的通行代价，所述通行代价与以下信息中的至少一种有关：所述障碍物的风险等级、所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
实施本申请实施例，由于M条规划路径对应各自的通行代价，该通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级，其中，障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度，车辆的风险等级用于表征车辆可能对障碍物造成的损失程度，通过这一实现方式，可以实现更为优化的路径规划，当控制装置面对有障碍物入侵时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
在一种可能的实现方式中，所述车辆信息包括所述车辆的坐标和尺寸，所述障碍物信息包括障碍物的坐标和尺寸，所述车辆的坐标和所述障碍物的坐标为在大地坐标系ENU下的坐标；所述处理单元还用于：对所述车辆的可行驶区域进行栅格化处理，得到栅格地图；根据所述车辆的坐标将所述障碍物的坐标从所述ENU下转换到车辆坐标系下，并结合所述障碍物的尺寸获取所述障碍物在所述栅格地图上的占据区域；基于所述占据区域，获取M条从起始点到目标点的规划路径。
在一种可能的实现方式中，所述处理单元，具体用于：确定目标规划路径，所述目标规划路径为所述M条规划路径中通行代价最小的路径。
在一种可能的实现方式中，所述目标规划路径对应的通行代价小于目标阈值。
在一种可能的实现方式中，所述获取单元，还用于获取预测碰撞信息；其中，所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；处理单元，还用于根据所述预测碰撞信息确定所述障碍物的风险等级和/或所述车辆的风险等级。
在一种可能的实现方式中，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速 度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
第四方面，本申请实施例提供了一种风险评估装置，该装置可以包括：获取信息单元，用于根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；处理单元，用于根据所述预测碰撞信息获取所述障碍物的风险等级和/或所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
在一种可能的实现方式中，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
第五方面，本申请实施例还提供一种终端，该终端可以实现上述第三方面和/或第四方面任一项所涉及的方法中所述的功能，上述功能可以通过硬件实现，也可以通过硬件执行相应的软件实现，所述硬件或软件包括一个或多个与上述功能相应的单元或模块。
第六方面，本申请实施例提供了一种控制装置，包括处理器和存储器，所述处理器和存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行上述第一方面或第二方面任一项所述的方法。
第七方面，本申请实施例提供一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，该计算机程序包括程序指令，该程序指令当被执行处理器执行时使所述处理器执行如第一方面或第二方面的方法。
第八方面，本申请实施例还提供了一种计算机程序，所述计算机程序包括计算机软件指令，所述计算机软件指令当被计算机执行时使所述计算机执行上述第一方面或第二方面的方法。
附图说明
图1为本申请实施例提供的一种车辆100的功能框图；
图2a为本申请实施例提供的一种第一应用场景的示意图；
图2b为本申请实施例提供的一种第二应用场景的示意图；
图2c为本申请实施例提供的一种第三应用场景的示意图；
图2d为本申请实施例提供的一种第四应用场景的示意图；
图3a为本申请实施例提供的一种控制方法的流程示意图；
图3b为本申请实施例提供的一种规划路径的示意图；
图3c为本申请实施例提供的一种车辆的可行驶区域的示意图；
图3d为本申请实施例提供的另一种车辆的可行驶区域的示意图；
图3e为本申请实施例提供的一种栅格地图的示意图；
图3f为本申请实施例提供的一种对障碍物的占据区域进行膨胀的示意图；
图3g为本申请实施例提供的另一种对障碍物的占据区域进行膨胀的示意图；
图3h为本申请实施例提供的一种车辆几何体的示意图；
图3i为本申请实施例提供的一种车辆与障碍物发生碰撞时的示意图；
图3j为本申请实施例提供的另一种控制方法的流程示意图；
图3k为本申请实施例提供的一种通过车辆的中控屏显示车辆与障碍物出现几何相交的示意图；
图4为本申请实施例提供的一种风险评估方法的流程示意图；
图5为本申请实施例提供的一种控制装置的结构示意图；
图6为本申请实施例提供一种风险评估装置的结构示意图；
图7为本申请实施例提供的一种控制装置的结构示意图。
具体实施方式
下面结合附图对本申请实施例中的技术方案进行清楚、完整的描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。
本申请的说明书以及附图中的术语“第一”和“第二”等是用于区分不同的对象，或者用于区别对同一对象的不同处理，而不是用于描述对象的特定顺序。此外，本申请的描述中所提到的术语“包括”和“具有”以及它们的任何变形，意图在于覆盖不排他的包含。例如包含了一些列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括其他没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。需要说明的是，本申请实施例中，“示例性地”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性地”或者“例如”的任何实施例或设计方法不应被解释为比其他实施例或设计方案更优地或更具优势。确切而言，使用“示例性地”或者“例如”等词旨在以具体方式呈现相关概念。在本申请实施例中，“A和/或B”表示A和B，A或B两个含义。“A，和/或B，和/或C”表示A、B、C中的任一个，或者，表示A、B、C中的任两个，或者，表示A和B和C。
为了更好的理解本申请所描述的技术方案，下面先解释本申请实施例涉及的相关技术术语：
在本申请实施例中，道路是指供车辆行驶，用于连通两地的通道。车道是指供沿同一方向行驶的单一纵列车辆行驶的通道，常见的车道包括直行车道、左转弯车道以及右转弯车道等不同种类。一条道路中包括一条或者多条车道。例如，一条道路包括：1条左转弯车道、2条直行车道和1条右转弯车道共四条车道。
在本申请实施例中，规划路径是指，用于使得车辆即将行驶在指定道路上的路径，也可以是指，精确到亚米级，且用于使得车辆行驶在指定车道上的路径。
需要说明的是，本申请提供的控制方法可以应用于障碍物入侵(亦或是：小幅入侵)车辆行驶的当前车道的场景，还可以应用于车辆的整个自动驾驶过程中，以保障车辆在驾驶过程中的安全性和平顺性。
图1是本申请实施例提供的一种车辆100的功能框图。在一些实施方式中，可以将车辆100配置为完全自动驾驶模式或部分地自动驾驶模式，亦或是人工驾驶模式。
在本申请实施例中，车辆100可以至少包括如下子系统：传感子系统101，决策子系统102和执行子系统103。其中，
传感子系统101至少可以包括传感器。具体地，传感器可以包括内部传感器和外部传感器；其中，内部传感器用来监测车辆的状态，可以包括车辆速度传感器、加速度传感器、角速度传感器等中的至少一种。外部传感器主要用来监测车辆周围的外部环境，示例性的，可以包括视频传感器和雷达传感器；视频传感器用于获取并监测车辆周围环境的图像数据；雷达传感器用于获取并监测车辆周围环境的电磁波数据，主要通过发射电磁波，然后通过接收周围物体反射的电磁波来检测周围物体与车辆的距离、周围物体的外形等各项数据。
例如，多个雷达传感器分布在整个车辆100的外部。多个雷达传感器的子集耦合到车辆100的前部，从而定位车辆100前方的对象。一个或多个其他雷达传感器可位于车辆100的后部，从而在车辆100后退时定位车辆100后方的对象。其他雷达传感器可位于车辆100的侧面，从而定位从侧面靠近车辆100的例如其他车辆100等对象。例如，激光雷达(light detection and ranging，LIDAR)传感器可安装在车辆100上，例如，将LIDAR传感器安装在车辆100顶部安装的旋转结构中。然后旋转LIDAR传感器120能以360°模式传输车辆100周围的光信号，从而随着车辆100移动不断映射车辆100周围所有对象。
例如，相机、摄像机或其他类似图像采集传感器等成像传感器可安装在车辆100上，从而随着车辆100移动捕捉图像。可以在车辆100的所有侧面放置多个成像传感器，从而以360°模式捕捉车辆100周围的图像。成像传感器不仅可以捕捉可见光谱图像，还可以捕捉红外光谱图像。
例如，全球定位系统(Global Positioning System，GPS)传感器可位于车辆100上，从而向控制器提供与车辆100的位置相关的地理坐标和坐标生成时间。GPS包括用于接收GPS卫星信号的天线以及耦合到天线的GPS接收器。例如，当在图像中或另一传感器观察到对象时，GPS可提供发现物的地理坐标和时间。
决策子系统102至少可以包括电子控制单元(Electronic Control Unit，ECU)、地图数据库、对象数据库。具体来说，ECU，又称“行车电脑”、“车载电脑”等，是汽车专用的微机控制器。ECU由微处理器(Microcontroller Unit，MCU)、存储器(例如，只读存储器ROM、随机存取存储器RAM)、输入/输出接口、模数转换器以及整形、驱动等大规模集成电路组成。在一些可行的实施例中，决策子系统102还可以包括通信单元。其中，ECU是用来控制车辆100的计算设备，执行决策控制功能。例如，ECU与总线相连，并通过总线与其他设备进行通信。例如，ECU可以获取内部、外部传感器，地图数据库和HMI传递的信息，并输出相应的信息到HMI和执行器。例如，ECU加载存储在ROM中的程序到RAM，CPU运行RAM中的程序，来实现自动驾驶功能。在实际应用中，ECU可能由多个ECU组成。ECU可以识别车辆周围静态的和/或动态的目标，例如，基于外部传感器获取目标监测结果。ECU可以监测周围目标的速度、方向等属性。ECU可以获取到车辆自身状态信息，基于内部传感器的输出信息。ECU根据这些信息，对驾驶路径进行规划，并输出相应的控制信号到执行器，由执行器执行相应的横向和纵向运动。
在本申请实施例中，控制装置可以包括但不限于上述ECU。
在一种可行的实施例中，上述控制转置可以包括获取单元和处理单元；其中，
获取单元，用于获取车辆信息、障碍物信息以及车辆的可行驶区域；其中，车辆的可行驶区域用于指示车辆可以安全行驶的区域；处理单元，用于根据车辆信息、障碍物信息，并结合车辆的可行驶区域，执行第一处理；其中，车辆信息、障碍物信息以及车辆的可行驶区域指示了M条规划路径，M为大于0的整数；M条规划路径对应各自的通行代价，通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。
上述方法在确定车辆与障碍物的碰撞无法避免的情况下，仍然可以规划出碰撞伤害最小的避险路径，供驾驶员紧急处理，通过这一实现方式，可以有效避免路径规划失败的情形，还可以有效避让障碍物，可以在最大程度上保证车辆行驶的安全性。在实际应用中，在控制装置确定车辆与障碍物之间的碰撞无法避免的情况下，在障碍物之前生成一道虚拟墙，使得车辆在障碍物前停止或降速前进，以保障车辆在驾驶过程中的安全性。
在本申请实施例中，上述获取单元，还可以用于：获取预测碰撞信息；其中，预测碰撞信息为预测车辆和障碍物可能发生碰撞时获取的信息；上述处理单元，还可以用于：根据预测碰撞信息确定障碍物的风险等级和/或车辆的风险等级。
在一些可行的实施例中，控制装置可以基于上述方法确定好的障碍物的风险等级以及车辆的风险等级进行路径规划，还可以进行预警提醒等等，此处不作具体限定。
在本申请实施例中，通信单元用于进行V2X(vehicle to everything，即Vehicle to X)通信。例如，可以与周围车辆、路边通信设备、云端服务器进行数据交互。例如，耦合到天线的无线电可位于车辆10中，从而为系统提供无线通信。无线电用于操作任何无线通信技术或无线标准，包括但不限于WiFi(IEEE 802.11)、蜂窝(例如，全球移动通信系统(Global System for Mobile Communications，GSM)、码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、长期演进(Long Term Evolution，LTE)、新空口(New Radio)中的一种或多种。无线电可包括多个无线电，使得控制器可以使用多种无线电技术通过无线信道进行通信。
在本申请实施例中，对象数据库中可以存储相应对象的内容信息，或者特征信息。例如，标识标线的内容。需要说明的对象数据库可能包含在地图数据库中，不一定单独存在。
在本申请实施例中，地图数据库用于存放地图信息；在一些可行的实施例中，可以使用硬盘驱动器(Hard Disk Drive，HDD)作为地图数据库的数据存储设备。可以理解的是，地图数据库中可以包含丰富的位置信息；例如，道路之间的连接关系、车道线的位置、车道线的数量以及道路周围的其他对象等；再例如，交通标识的信息(例如，红绿灯的位置，高度，标识的内容，如限速标识、连续弯路、慢行等)、道路周围的树木、建筑物信息等。前述信息都与地理位置相关联。此外，地图信息也可以被用来进行定位，与传感数据结合。在一些可行的实施例中，存储的地图信息可以是二维信息，也可以是三维信息。
执行子系统103至少可以包括执行器，执行器用于控制车辆100进行横向和/或纵向运动。例如，刹车执行器根据从ECU接收的控制信号，控制刹车系统和刹车的力度；转向执 行器通过来自ECU的控制信号控制转向系统；在一些可行的实施例中，转向系统可以是电子转向系统，或者是机械转向系统。
需要说明的是，图1中的系统的元件仅出于说明目的，包括更多或更少组件的其他系统可用于执行本申请公开的任何方法。
为了便于更好的理解本申请，下面介绍几个本申请所描述的方法可以应用的应用场景：
第一应用场景：
参见图2a，是本申请实施例提供的一种第一应用场景的示意图。如图2a所示，车辆行驶在某一路段，车辆的左侧车道行驶有社会车A(社会车A对车辆来说，即为障碍物)。在某一时刻，车辆获知社会车A有向右转的趋势(例如，车辆通过摄像头采集到社会车的右转向灯在闪烁)，车辆获取车辆信息、障碍物信息以及车辆的可行驶区域，例如，该可行驶区域可以为合规可行驶区域、紧急避险可行驶区域中的至少一种，其中，合规行驶区域用于指示车辆在满足交通规则行驶时可以安全行驶的全部区域；紧急避险可行驶区域用于指示车辆行驶时不与障碍物发生碰撞的区域；之后，车辆根据车辆信息、障碍物信息，并结合车辆的可行驶区域获取M条规划路径，其中，M为大于0的整数，基于M条规划路径各自对应的通行代价，获取目标规划路径，例如，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，从而车辆可以按照确定的目标规划路径进行行驶，以避免与社会A出现碰撞。通过这一实现方式，可以保障车辆在驾驶过程中的安全性。在一些实施例中，在确定车辆与障碍物将会发生碰撞的情况下，控制装置可以对车辆的行驶速度和/或行驶路径进行调整，以避让障碍物，从而可以保证车辆在驾驶过程中的安全性。在一些实施例中，在确定车辆与障碍物之间的碰撞无法避免的情况下，在障碍物之前生成一道虚拟墙，使得车辆在障碍物前停止或降速前进，以保障车辆在驾驶过程中的安全性。
第二应用场景：
参见图2b，是本申请实施例提供的一种第二应用场景的示意图。如图2b所示，车辆在某一路段上直行。在某一时刻，车辆的右前方突然驶入社会车A，此时，车辆获取车辆信息、障碍物信息以及车辆的可行驶区域，例如，该可行驶区域可以为合规可行驶区域、紧急避险可行驶区域中的至少一种，其中，合规行驶区域用于指示车辆在满足交通规则行驶时可以安全行驶的全部区域；紧急避险可行驶区域用于指示车辆行驶时不与障碍物发生碰撞的区域；之后，车辆根据车辆信息、障碍物信息，并结合车辆的可行驶区域获取M条规划路径，其中，M为大于1的整数，基于M条规划路径各自对应的通行代价，获取目标规划路径，例如，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，从而车辆可以按照确定的目标规划路径进行行驶，以避免与社会A出现碰撞。通过这一实现方式，可以保障车辆在驾驶过程中的安全性。
第三应用场景：
参见图2c，是本申请实施例提供的一种第三应用场景的示意图。如图2c所示，车辆在某一路段上直行，在某一时刻，车辆的右侧非机动车道上有骑行者骑行，且骑行速度超过35km/h。此外，车辆的右前方有社会车将驶入当前行驶的车道，此时，车辆获取车辆信息、障碍物信息(其中，障碍物信息包括骑行者的信息和社会车A的信息)以及车辆的可行驶区域，例如，该可行驶区域可以为合规可行驶区域、紧急避险可行驶区域中的至少一种， 其中，合规行驶区域用于指示车辆在满足交通规则行驶时可以安全行驶的全部区域；紧急避险可行驶区域用于指示车辆行驶时不与障碍物发生碰撞的区域；之后，车辆根据车辆信息、障碍物信息，并结合车辆的可行驶区域获取M条规划路径，其中，M为大于1的整数，基于M条规划路径各自对应的通行代价，获取目标规划路径，例如，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，从而车辆可以按照确定的目标规划路径进行行驶，以避免与社会A出现碰撞。通过这一实现方式，可以保障车辆在驾驶过程中的安全性。
第四应用场景：
参见图2d，是本申请实施例提供的一种第四应用场景的示意图。如图2d所示，车辆行驶在某一路段，在车辆的行驶路径中包含障碍物，例如，该障碍物为大颗粒遗洒物，且车辆的右侧车道行驶有社会车辆，两车道中间交通标志线为实线，在交通规则不允许换道或相邻车道车流密集的情况下，车辆无法换道。在这种情况下，车辆可以根据车辆信息、障碍物信息，并结合紧急避险可行驶区域获取M条规划路径，并基于M条规划路径各自对应的通行代价，获取目标规划路径，例如，在M条规划路径中，将通行代价最小的规划路径确定为目标规划路径，从而车辆可以按照确定的目标规划路径进行行驶，以避免与社会A出现碰撞。可以理解的是，当车辆并未获取到目标规划路径时，车辆可以保持静止。在右侧车辆中的社会车辆安全通过时，重新获取紧急避险可行驶区域，以得到目标规划路径，以绕开障碍物，继续通行。
参见图3a，图3a为本申请实施例提供的一种控制方法的流程示意图，该方法可以包括但不限于如下步骤：
步骤S301、获取车辆信息、障碍物信息以及车辆的可行驶区域；其中，车辆的可行驶区域用于指示车辆可以安全行驶的区域。在本申请实施例中，车辆，也可以称为自车。
在本申请实施例中，连接起点位置和终点位置的序列点或曲线称之为路径，构成路径的策略称之为路径规划。可以理解的是，规划路径可以为使得车辆行驶在指定道路上的路径，也可以为精确到亚米级，使得车辆行驶在制定车道上的路径。例如，如图3b所示，规划路径为从起点位置A到终点位置B之间的一条曲线。
在本申请实施例中，车辆的可行驶区域可以包括合规行驶区域、紧急避险可行驶区域中的至少一种；其中，合规行驶区域用于指示车辆在满足交通规则行驶时可以安全行驶的全部区域；紧急避险可行驶区域用于指示车辆行驶时不与障碍物发生碰撞的区域。
下面结合图3c-图3d详细描述本申请实施例所涉及的车辆的可行驶区域。
以上述所示的第一应用场景为例，车辆行驶在某一路段，车辆的左侧车道行驶有社会车A(社会车A对车辆来说，即为障碍物)。在某一时刻，车辆获知社会车A有向右转的趋势(例如，车辆通过摄像头采集到社会车的右转向灯在闪烁)，如图3c所示，合规行驶区域用于指示车辆在满足交通规则行驶时可以安全行驶的全部区域，可以包括但不限于车道范围内的区域(不含方向不匹配的车道)或路口中最佳虚拟车道线的覆盖区域、停车带区域等。如图3d所示，紧急避险可行驶区域用于指示车辆行驶时不与障碍物发生碰撞的区域，相较于合规行驶区域来说，增加了方向不匹配的车道、部分逆行车道、非机动车车道等。可以理解的事，车辆行驶在紧急避险可行驶区域时可能违章。
应理解，上述所描述的合规行驶区域以及紧急避险可行驶区域只是一种示例，本申请实施例并不对可行驶区域的名称进行限定，其中，合规行驶区域也可以称为最佳可行驶区域，紧急避险可行驶区域也可以称为最差可行驶区域。在一些实施例中，上述所描述的合规行驶区域以及紧急避险可行驶区域也可以分别称为第一区域、第二区域等。
应理解，在实际应用中，可行驶区域可以包括上述描述的合规行驶区域、紧急避险可行驶区域中的一种或多种，本申请对此不做具体限定。
在本申请实施例中，障碍物是指妨碍或阻碍车辆行驶的事物，可以包括在车辆的可行驶区域内移动或静止的人或物体(比如汽车、树木和骑自行车的人等)。
在本申请实施例中，车辆信息可以包括但不限于车辆的位置(也可以称为坐标)、尺寸、运动状态信息等；障碍物信息可以包括但不限于障碍物的位置(也可以称为坐标)、尺寸、运动状态信息等。以车辆的运动状态信息为例，车辆的运动状态信息可以包括以下一个或多个：当前车辆的行驶速度、航向角、方向盘转角、加速度。
步骤S302、根据车辆信息、障碍物信息，并结合车辆的可行驶区域，执行第一处理。
在本申请实施例中，上述车辆信息、障碍物信息以及车辆的可行驶区域指示了M条规划路径，M为大于0的整数，其中，M条规划路径对应各自的通行代价，该通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。
具体来说，障碍物的风险等级与车辆的风险等级可以相同，也可以不相同。
一般来说，规划路径对应的通行代价越大意味着车辆按照该规划路径进行行驶时付出的代价越大，在路径规划时，被选中的几率越小。在实际应用中，通行代价可以是一个数值，M条规划路径可以基于相同的标准得到对应的无单位的数值。
在本申请实施例中，控制装置可以根据车辆信息、障碍物信息，并结合车辆的可行驶区域获取M条规划路径，该实现过程可以包括：首先，在t时刻获取车辆信息、障碍物信息以及车辆的可行驶区域，一般来说，车辆的可行驶区域可以为自车为中心，尺寸大小为L*I的矩形区域。之后，对车辆的可行驶区域进行栅格化处理，得到栅格地图；然后，根据车辆的坐标将障碍物的坐标从大地坐标系ENU下转换到车辆坐标系下，并结合障碍物的尺寸获取障碍物在栅格地图上的占据区域；从而，可以基于上述占据区域，获取M条从起始点到目标点的规划路径。如图3e所示，以车辆为中心，将尺寸为50m*50m的方形或其他尺寸的矩形区域作为可行驶区域，对可行驶区域进行栅格化处理，得到栅格地图(如图3e中灰色格子所示)；栅格分辨率为0.25m*0.25m，即该栅格地图中每个栅格的尺寸为0.25m*0.25m。将障碍物(包括图3e中所示的社会车和障碍物)的坐标从ENU坐标系下转换到车辆坐标系下，以得到障碍物相对车辆的相对位置坐标。之后，再根据车辆坐标及尺寸和障碍物的相对位置坐标及尺寸将自车辆和障碍物映射到栅格地图上，得到车辆和障碍物在栅格地图上的占据区域。换句话说，在获取障碍物在栅格地图的占据区域后，可以基于上述占据区域，获取M条规划路径。这一方式相比于现有技术，降低了对传感器精度的依赖性。
在一种可行的实施例中，控制装置可以根据车辆与障碍物之间的相对运动趋势对上述 障碍物的占据区域进行膨胀。所谓膨胀，即扩大障碍物的占据区域面积。例如，在车辆接近障碍物的一侧，以第一空间膨胀率对占据区域进行调整。又例如，在车辆远离障碍物的一侧，以第二空间膨胀率对占据区域进行调整。具体地，第一空间膨胀率大于第二空间膨胀率。一般来说，可以以第一长度进行膨胀和以第二长度进行膨胀分别来表征第一空间膨胀率和第二空间膨胀率。下面对上述几种情形进行具体阐述：
在一个示例中，如图3f所示，障碍物在车辆的右侧，当车辆与障碍物之间的相对运动趋势为接近趋势的情况下，将障碍物的占据区域的第一左边界以第一长度进行膨胀。从图3f可以知道的是，经过膨胀后的占据区域的区域面积大于未经过膨胀的占据区域的区域面积。
在一个示例中，如图3g所示，障碍物在车辆的右侧，当车辆与障碍物之间的相对运动趋势为接近趋势的情况下，将障碍物的占据区域的第一左边界以第一长度进行膨胀，与此同时，将障碍物的占据区域的第一右边界以第二长度进行膨胀。从图3g可以知道的是，经过膨胀后的占据区域的区域面积大于未经过膨胀的占据区域的区域面积。
在本申请实施例中，第一长度和第二长度可以为不同的长度。一般来说，第一长度和第二长度可以介于e0和e max之间，其中，e0是指最小移动长度，e max是指最大移动长度。在实际应用中，可以根据车辆与障碍物之间的接近距离确定上述第一长度和第二长度。
在一些可能的示例中，膨胀率为接近距离的单调函数，但膨胀率不能大于最大膨胀程度e max。例如，可以根据第一公式计算第一长度和第二长度，第一公式可以描述为：
E＝fmin(e0+k*s,e max)
其中，e0表示第一驾驶区域两侧的最小膨胀长度，e max表示第一驾驶区域两侧的最大膨胀长度，s表示横向最近距离。
具体来说，横向最近距离是指车辆与障碍物之间的距离在垂直于车道的方向的分量。
由第一公式可以知道的是，在车辆接近障碍物的一侧，车辆与障碍物之间的接近距离越小，第一空间膨胀率越大。在车辆远离障碍物的一侧，车辆与障碍物之间的接近距离越大，第二空间膨胀率越小。
在一些可能的示例中，膨胀率可以为接近速度的单调函数，但膨胀率不能大于最大膨胀程度e max。在车辆接近障碍物的一侧，车辆与障碍物之间的接近速度越大，第一空间膨胀率越大。在车辆远离障碍物的一侧，车辆与障碍物之间的接近速度越小，第二空间膨胀率越小。
那么，控制装置在获取障碍物在栅格地图中经过膨胀了的占据区域后，可以基于上述膨胀后的占据区域，获取M条规划路径。
在本申请实施例中，可以通过代价函数来计算每条规划路径对应的通行代价，其中，代价函数为根据安全项S、舒适项C、障碍物风险等级R1、车辆风险等级R2中至少一个构建的代价函数；其中，安全项S用于表征车辆与障碍物之间保持的横向目标偏移以及纵向速度偏移；舒适项C用于表征车辆的加速度的变化程度，例如，车辆的加速度的变化程度可以包括横向Jerk加加速度和纵向Jerk加加速度；障碍物的风险等级R1用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级R2用于表征车辆可能对障碍物造成的损失程度。
举例来说，障碍物对车辆造成的损失程度可以分为：轻微擦伤、稍许变形、车体凹陷等。车辆对障碍物造成的损失程度与障碍物的所属类别有关，例如，当障碍物为行人的时候，车辆对障碍物的损失程度可以包括行人受伤；当障碍物为其他车辆时，车辆对障碍物的损失程度可以包括轻微擦伤、稍许变形、车体凹陷等。应理解，上述举例只是一种示例，不应构成限定。
在一种可行的实施例中，上述代价函数可以为：
G＝w1×S+w2×C+w3×R1+w4×R2
其中，w1、w2、w3以及w4为权重系数；S表示安全项；C表示舒适项；R1表示障碍物的风险等级；R2表示车辆的风险等级。
在实际应用中，控制装置可以调整上述w1、w2、w3、w4的大小。以调整安全项的权重系数w1为例，当车辆终端检测到障碍物的数量大于预设阈值的情况下，控制装置可以增大安全项S的权重系数；或者，当控制装置检测到有障碍物侵占车辆的可行驶区域，且车辆的驾驶员的操作信息为加速不转向的情况下，增大安全项S的权重系数；或者，当控制装置检测到有障碍物侵占车辆的可行驶区域，且车辆的驾驶员的操作信息为加速转向避让障碍物的情况下，减小安全项S的权重系数；或者，当控制装置检测到有障碍物侵占车辆的可行驶区域，且车辆的驾驶员的操作信息为减速不转向或减速转向的情况下，减小安全项S的权重系数。
以调整障碍物的风险等级R1的权重系数为例，当控制装置确定车辆与障碍物之间发生碰撞的时间小于设定的数值，控制装置可以增大整障碍物的风险等级R1的权重系数。
需要说明的是，上述w1、w2、w3以及w4的取值范围为(0,1)。
在一种可行的实施例中，上述安全项S、舒适项C、障碍物的风险等级R1以及车辆的风险等级R2可以分别表示为：
S＝w11×d(t n) 2+w12×(ds(t n)) 2
Figure PCTCN2020138110-appb-000001
R1＝(r obj(t)) 2
R2＝(r ego(t)) 2
其中，w11、w12、w21、w22为权重系数。
在一种可行的实施例中，可以根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；其中，该预测碰撞信息为预测车辆和障碍物可能发生碰撞时获取的信息；然后，根据预测碰撞信息获取障碍物的风险等级和/或车辆的风险等级。本申请实施例还提供了一种如何预测车辆与障碍物发生碰撞的方法，具体地，控制装置可以根据车辆与障碍物的位置信息和运动状态信息，预测在预设时间段内车辆的第一运动轨迹和障碍物的第二运动轨迹，然后，判断第一运动轨迹与第二运动轨迹是否发生碰撞，例如，可以根据车辆的尺寸(L,W,H)和障碍物的尺寸(l,w,h)，计算得到二者之间的安全距离，其中，该安全距离可以表示为：
Figure PCTCN2020138110-appb-000002
其中，δ表示预留量，与车辆的感知精度有关，在t时刻，车辆与障碍物之间的距离可以表示为：
Figure PCTCN2020138110-appb-000003
如果在t时刻，车辆与障碍物之间的距离大于安全距离，则确定第一运动轨迹与第二运动轨迹不会发生碰撞。
如果在t时刻，车辆与障碍物之间的距离小于安全距离，此时，可以根据车辆几何体是否与障碍物几何体相交来确定车辆是否与障碍物发生碰撞。具体来说，车辆几何体是指，车辆的几何包络，车辆的几何包络代表了一个车辆的形状逐步延伸所得到的整体形状；障碍物几何体是指，障碍物的几何包络。如图3h所示，为本申请实施例提供的一种车辆几何体的示意图。
又例如，根据第二运动轨迹获取障碍物在t时刻的航向角，从而可以得到障碍物在t时刻的几何模型，具体地，障碍物在t时刻的几何模型可以表示为：
P obj(t)＝A(θ(t))P obj(0)+(x obj(t),y obj(t),z obj(t))-(x obj(0),y obj(0),z obj(0))
其中，旋转特征矩阵A(θ(t))可以表示为：
Figure PCTCN2020138110-appb-000004
然后，判断车辆的几何模型与障碍物在t时刻的几何模型是否存在交集，具体地，可以表示为：
collisionStatu(t)＝collisionCheck(P ego,P obj(t)
若二者之间存在交集，也即，collisionResult＝1，则确定车辆与障碍物将会发生碰撞。具体地，第一运动轨迹与第二运动轨迹将会发生碰撞的示意图可以如图3i所示。
需要说明的是，上述所提及的判断车辆的几何模型与障碍物在t时刻的几何模型是否存在交集的这一方式，并不是单一的指车辆对应的第一运动轨迹与障碍物对应的第二运动轨迹相交，而是指两个几何体的运动轨迹相交。这一实现方式，充分考虑了车辆与障碍物的形状，相较于现有技术而言，可以提高碰撞检测的精度，为后续确定车辆的风险等级以及障碍物的风险等级提供了便利。
应理解，在collisionResult＝0的情况下，这表示车辆与障碍物之间不会发生碰撞，此时，障碍物的风险等级为0，车辆的风险等级为0。
应理解，在collisionResult＝1的情况下，这表示车辆与障碍物之间会发生碰撞，此时，控制装置获取如下预测碰撞信息，其中，预测碰撞信息包括：车辆相对于障碍物的速度Δv、车辆与障碍物可能发生碰撞时相交的体积、车辆与障碍物可能发生碰撞时的碰撞夹角、车辆与障碍物之间的中心距离、障碍物的所属类别中的至少一个。
此外，控制装置还可以获取碰撞时刻t0。
在本申请实施例中，可以根据预测碰撞信息获取障碍物的风险等级以及车辆的风险等级。在具体实现中，可以通过风险评估函数来获取障碍物的风险等级以及车辆的风险等级。 其中，该风险评估函数可以为根据预测碰撞信息构建的函数。
在一种可行的实施例中，该风险评估函数可以表示为：
R＝m(w to×t0,w |v(to)|×|v(to)|,w |V(max)|×|V(max)|,w |θ(to)|×|θ(to)|,w |o(x)|×|o(x)|,w c×class) T
其中，m表示各个预测碰撞信息在当前状况下的风险等级向量，例如，m＝(3,2,1,2,1,0,3),w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c分别表示每个预测碰撞信息对应的权重，t 0表示碰撞时刻，|v(to)|表示车辆相对于障碍物的速度Δv，|V(max)|表示车辆与障碍物可能发生碰撞时相交的体积，|θ(to)|表示车辆与障碍物可能发生碰撞时的碰撞夹角，o(x)表示车辆与障碍物之间的中心距离，class表示障碍物的所属类别。
一般来说，障碍物的所属类别可以包括但不限于于：行人、其他车辆、非机动车(例如，自行车、电动摩托车等)。
在一种可行的实施例中，上述w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c可以满足：
w to+w |v(to)|+w |V(max)|+w |θ(to)|+w |o(x)|+w c＝1
在一种可行的实施例中，上述w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c的取值可以通过判断其是否为关键因素来确定，例如，以|V(max)|为例，在判断出|V(max)|为关键因素的情况下，其对应的权重较大；在判断出|V(max)|不是关键因素时，其对应的权重较小。
应理解，如果获取的碰撞时间越短，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆相对于障碍物的速度Δv越大，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆与障碍物可能发生碰撞时相交的体积越大，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆与障碍物可能发生碰撞时的碰撞夹角越大，对车辆来说，障碍物对其带来的风险越大。
控制装置根据车辆信息、障碍物信息，并结合车辆的可行驶区域获取了M条规划路径，以及通过上述描述的方法确定了每条规划路径对应的通行代价之后，控制装置可以基于每条规划路径对应的通行代价执行第一处理，该第一处理可以包括但不限于如下步骤：
步骤S302-1、确定目标规划路径，其中，目标规划路径为M条规划路径中通行代价最小的路径。
在实际应用中，控制装置可以基于M条规划路径各自对应的通行代价对M条规划路 径进行排序，得到排序结果；然后，在获取的排序结果中，将通行代价最小的规划路径确定为目标规划路径。那么，当控制装置按照上述确定好的目标规划路径进行驾驶时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
如图3j所示，在执行上述步骤S302-1之后，还可以包括如下步骤：
步骤S302-2、判断目标规划路径对应的通行代价是否小于目标阈值；若是，则执行步骤S302-3；若否，则执行步骤S302-4。
在本申请实施例中，目标阈值用于指示可以接受的最大通行代价。在一些实施例中，控制装置可以通过分析用户的历史交通数据(例如，历史交通数据可以包括历史车祸数据)来确定目标阈值。在一些实施例中，目标阈值可以为用户根据自身需求设置的。
步骤S302-3、在判断出目标规划路径小于目标阈值的情况下，按照目标规划路径进行驾驶。
步骤S302-4、在判断出目标规划路径不小于(例如，可以大于或等于)目标阈值的情况下，控制车辆保持静止。
现有技术中，控制装置进行路径规划时，只考虑碰撞或不碰撞，在预测出所有规划路径均会与障碍物发生碰撞的情况下，路径规划失败。本申请相较于现有技术来说，当车辆与障碍物会出现碰撞的情况下，仍然可以规划出碰撞伤害最小的避险路径，供驾驶员紧急处理，一方面，可以有效避免路径规划失败的情形；另一方面，还可以有效避让障碍物，可以在最大程度上保证车辆行驶的安全性。
实施本申请实施例，由于M条规划路径对应各自的通行代价，该通行代价与以下信息中的至少一种有关：障碍物的风险等级、车辆的风险等级，其中，障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度，车辆的风险等级用于表征车辆可能对障碍物造成的损失程度，通过这一实现方式，可以实现更为优化的路径规划，当控制装置面对有障碍物入侵时，可以有效避让障碍物，保证了车辆行驶的安全性和平顺性。
在前述所描述的方法实施例中，如图3k所示，可以在车辆的中控屏501上显示车辆的几何模型与障碍物在t时刻的几何模型之间出现交集的示意图，并基于相交的情形发出预警提示信息，例如，该预警提示信息可以为：请注意，请注意，在5秒过后，车辆将与障碍物发生碰撞。又例如，该预警提示信息还可以为：请谨慎驾驶，车辆将与障碍物发生碰撞。通过这一实现方式，可以提高驾驶者的行车注意力，在这种情况下，驾驶者可以将自动驾驶模式切换为人工驾驶模式，也可以降低自动驾驶车辆的驾驶等级，例如，将自动驾驶等级L5切换为自动驾驶等级L3，等等。
参见图4，图4为本申请实施例提供的一种风险评估方法的流程示意图，该方法可以包括但不限于如下步骤：
步骤S401、根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；预测碰撞信息为预测车辆和障碍物可能发生碰撞时获取的信息。
在本申请实施例中，预测碰撞信息包括：车辆相对于障碍物的速度Δv、车辆与障碍物可能发生碰撞时相交的体积、车辆与障碍物可能发生碰撞时的碰撞夹角、车辆与障碍物之 间的中心距离、障碍物的所属类别中的至少一个。
步骤S402、根据预测碰撞信息获取障碍物的风险等级和/或车辆的风险等级；障碍物的风险等级用于表征障碍物可能侵占车辆的可行驶区域且障碍物对车辆可能造成的损失程度；车辆的风险等级用于表征车辆可能对障碍物造成的损失程度。
在一种可行的实施例中，控制装置可以通过风险评估函数来获取障碍物的风险等级以及车辆的风险等级。其中，该风险评估函数可以为根据预测碰撞信息构建的函数。
在一种可行的实施例中，该风险评估函数可以表示为：
R＝m(w to×t0,w |v(to)|×|v(to)|,w |V(max)|×|V(max)|,w |θ(to)|×|θ(to)|,w |o(x)|×|o(x)|,w c×class) T
其中，m表示各个预测碰撞信息在当前状况下的风险等级向量，例如，m＝(3,2,1,2,1,0,3),w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c分别表示每个预测碰撞信息对应的权重，t0表示碰撞时刻，|v(to)|表示车辆相对于障碍物的速度Δv，|V(max)|表示车辆与障碍物可能发生碰撞时相交的体积，|θ(to)|表示车辆与障碍物可能发生碰撞时的碰撞夹角，o(x)表示车辆与障碍物之间的中心距离，class表示障碍物的所属类别。
一般来说，障碍物的所属类别可以包括但不限于于：行人、其他车辆、非机动车(例如，自行车、电动摩托车等)。
在一种可行的实施例中，上述w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c可以满足：
w to+w |v(to)|+w |V(max)|+w |θ(to)|+w |o(x)|+w c＝1
在一种可行的实施例中，上述w to、w |v(to)|、w |V(max)|、w |θ(to)|、w |o(x)|、w c的取值可以通过判断其是否为关键因素来确定，例如，以|V(max)|为例，在判断出|V(max)|为关键因素的情况下，其对应的权重较大；在判断出|V(max)|不是关键因素时，其对应的权重较小。
应理解，如果获取的碰撞时间越短，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆相对于所述障碍物的速度Δv越大，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆与障碍物可能发生碰撞时相交的体积越大，对车辆来说，障碍物对其带来的风险越大。
还应理解，如果车辆与障碍物可能发生碰撞时的碰撞夹角越大，对车辆来说，障碍物对其带来的风险越大。
在实际应用中，车辆可以基于上述方法确定好的障碍物的风险等级以及车辆的风险等 级进行路径规划，还可以进行预警提醒等等，此处不作具体限定。
实施本申请实施例，控制装置可以基于预测碰撞信息来确定障碍物的风险等级和/或车辆的风险等级，相比于现有技术，降低了对传感器精度的依赖性。
前述实施例重点阐述了控制装置可以如何基于M条路径规划各自对应的通行代价来获取目标规划路径的，接下来具体介绍本申请涉及的装置。需要说明的是，对于本申请装置实施例中未披露的细节，请参照本申请方法实施例。
如图5所示，本申请实施例提供了一种控制装置，该装置50可以包括：
获取单元500，用于获取车辆信息、障碍物信息以及所述车辆的可行驶区域；其中，所述车辆的可行驶区域用于指示所述车辆可以安全行驶的区域；
处理单元510，用于根据所述车辆信息、障碍物信息，并结合所述车辆的可行驶区域，执行第一处理；其中，所述车辆信息、所述障碍物信息以及所述车辆的可行驶区域指示了M条规划路径，M为大于0的整数；所述M条规划路径对应各自的通行代价，所述通行代价与以下信息中的至少一种有关：所述障碍物的风险等级、所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
在一种可能的实现方式中，所述车辆信息包括所述车辆的坐标和尺寸，所述障碍物信息包括障碍物的坐标和尺寸，所述车辆的坐标和所述障碍物的坐标为在大地坐标系ENU下的坐标；上述处理单元510，还用于：
对所述车辆的可行驶区域进行栅格化处理，得到栅格地图；
根据所述车辆的坐标将所述障碍物的坐标从所述ENU下转换到车辆坐标系下，并结合所述障碍物的尺寸获取所述障碍物在所述栅格地图上的占据区域；
基于所述占据区域，获取M条从起始点到目标点的规划路径。
在一种可能的实现方式中，所述处理单元510，具体用于：
确定目标规划路径，所述目标规划路径为所述M条规划路径中通行代价最小的路径。
在一种可能的实现方式中，所述目标规划路径对应的通行代价小于目标阈值。
在一种可能的实现方式中，上述获取单元，还用于获取预测碰撞信息；其中，所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；处理单元，还于根据所述预测碰撞信息确定所述障碍物的风险等级和/或所述车辆的风险等级。
在一种可能的实现方式中，所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
需要说明的是，本申请实施例中所描述的路径规划装置可参见上述图3a、图3j中所述的方法实施例中的控制方法的相关描述，此处不再赘述。
如图6所示，本申请实施例提供了一种风险评估装置，该装置60可以包括：
获取单元600，用于根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信 息；所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；
处理单元610，用于根据所述预测碰撞信息获取所述障碍物的风险等级和/或所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
在一种可能的实现方式中，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
需要说明的是，本申请实施例中所描述的风险评估装置可参见上述图4所述的方法实施例中的风险评估方法的相关描述，此处不再赘述。
请参见图7，图7是本申请实施例提供的一种控制装置的结构示意图。该控制装置70包括至少一个处理器701以及至少一个通信接口703。可选的，还可以包括至少一个存储器702。该控制装置还可以包括天线等通用部件，在此不再详述。
处理器701可以是通用中央处理器(CPU)，微处理器，特定应用集成电路(application-specific integrated circuit，ASIC)，或一个或多个用于控制以上方案程序执行的集成电路。
通信接口703，用于与其他设备或通信网络通信。
存储器702，可以是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，EEPROM)、只读光盘(Compact Disc Read-Only Memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。存储器可以是独立存在，通过总线与处理器相连接。存储器也可以和处理器集成在一起。
其中，所述存储器702用于存储执行以上方案的应用程序代码，并由处理器701来控制执行。所述处理器701用于执行所述存储器702中存储的应用程序代码。例如，存储器702存储的代码可执行以上图3a、图3j提供的控制方法以及图4提供的风险评估方法。
具体地，处理器701用于调用存储器中的数据和程序代码，执行：
获取车辆信息、障碍物信息以及所述车辆的可行驶区域；其中，所述车辆的可行驶区域用于指示所述车辆可以安全行驶的区域；
根据所述车辆信息、障碍物信息，并结合所述车辆的可行驶区域，执行第一处理；
其中，所述车辆信息、所述障碍物信息以及所述车辆的可行驶区域指示了M条规划路径，M为大于0的整数；所述M条规划路径对应各自的通行代价，所述通行代价与以下信息中的至少一种有关：所述障碍物的风险等级、所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造 成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
其中，所述车辆信息包括所述车辆的坐标和尺寸，所述障碍物信息包括障碍物的坐标和尺寸，所述车辆的坐标和所述障碍物的坐标为在大地坐标系ENU下的坐标；所述处理器701还可以用于：
对所述车辆的可行驶区域进行栅格化处理，得到栅格地图；
根据所述车辆的坐标将所述障碍物的坐标从所述ENU下转换到车辆坐标系下，并结合所述障碍物的尺寸获取所述障碍物在所述栅格地图上的占据区域；
基于所述占据区域，获取M条从起始点到目标点的规划路径。
其中，所述处理器701执行第一处理，可以包括：确定目标规划路径，所述目标规划路径为所述M条规划路径中通行代价最小的路径。其中，所述目标规划路径对应的通行代价小于目标阈值。
其中，所述处理器701还可以用于：获取预测碰撞信息；其中，所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；根据所述碰撞信息确定所述障碍物的风险等级和/或所述车辆的风险等级。
其中，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
需要说明的是，本申请实施例中所描述的控制装置70的功能可参见上述图3a、图3j和图4中的所述的方法实施例中的相关描述，此处不再赘述。
本申请实施例还提供了一种计算机可读存储介质，其中，该计算机可读存储介质用于存储计算机程序，该计算机程序使得控制装置执行如上述方法实施例中记载的任何一种控制方法的部分或者全部步骤。
本申请实施例还提供一种计算机程序产品，该计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使电子设备执行如上述方法实施例中记载的任何一种卷积运算方法的部分或者全部步骤。
可以理解，本领域普通技术人员可以意识到，结合本申请各个实施例中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本领域技术人员能够领会，结合本申请各个实施例中公开描述的各种说明性逻辑框、模块和算法步骤所描述的功能可以硬件、软件、固件或其任何组合来实施。如果以软件来实施，那么各种说明性逻辑框、模块、和步骤描述的功能可作为一或多个指令或代码在计算机可读媒体上存储或传输，且由基于硬件的处理单元执行。计算机可读媒体可包含计算机可读存储媒体，其对应于有形媒体，例如数据存储媒体，或包括任何促进将计算机程序从一处传送到另一处的媒体(例如，根据通信协议)的通信媒体。以此方式，计算机可读媒体大体上可对应于(1)非暂时性的有形计算机可读存储媒体，或(2)通信媒体，例如信号或载波。数据存储媒体可为可由一或多个计算机或一或多个处理器存取以检索用于实施本 申请中描述的技术的指令、代码和/或数据结构的任何可用媒体。计算机程序产品可包含计算机可读媒体。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (19)

  1. 一种控制方法，其特征在于，包括：
    获取车辆信息、障碍物信息以及所述车辆的可行驶区域；其中，所述车辆的可行驶区域用于指示所述车辆可以安全行驶的区域；
    根据所述车辆信息、障碍物信息，并结合所述车辆的可行驶区域，执行第一处理；
    其中，所述车辆信息、所述障碍物信息以及所述车辆的可行驶区域指示了M条规划路径，M为大于0的整数；所述M条规划路径对应各自的通行代价，所述通行代价与以下信息中的至少一种有关：所述障碍物的风险等级、所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
  2. 如权利要求1所述的方法，其特征在于，所述车辆信息包括所述车辆的坐标和尺寸，所述障碍物信息包括障碍物的坐标和尺寸，所述车辆的坐标和所述障碍物的坐标为在大地坐标系ENU下的坐标；所述方法还包括：
    对所述车辆的可行驶区域进行栅格化处理，得到栅格地图；
    根据所述车辆的坐标将所述障碍物的坐标从所述ENU下转换到车辆坐标系下，并结合所述障碍物的尺寸获取所述障碍物在所述栅格地图上的占据区域；
    基于所述占据区域，获取M条从起始点到目标点的规划路径。
  3. 如权利要求1或2所述的方法，其特征在于，所述执行第一处理，包括：
    确定目标规划路径，所述目标规划路径为所述M条规划路径中通行代价最小的路径。
  4. 如权利要求3所述的方法，其特征在于，所述目标规划路径对应的通行代价小于目标阈值。
  5. 如权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    获取预测碰撞信息；其中，所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；
    根据所述预测碰撞信息确定所述障碍物的风险等级和/或所述车辆的风险等级。
  6. 如权利要求5所述的方法，其特征在于，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
  7. 一种风险估计方法，其特征在于，包括：
    根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；所述预测碰撞信 息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；
    根据所述预测碰撞信息获取所述障碍物的风险等级和/或所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
  8. 如权利要求7所述的方法，其特征在于，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
  9. 一种控制装置，其特征在于，包括：
    获取单元，用于获取车辆信息、障碍物信息以及所述车辆的可行驶区域；其中，所述车辆的可行驶区域用于指示所述车辆可以安全行驶的区域；
    处理单元，用于根据所述车辆信息、障碍物信息，并结合所述车辆的可行驶区域，执行第一处理；
    其中，所述车辆信息、所述障碍物信息以及所述车辆的可行驶区域指示了M条规划路径，M为大于0的整数；所述M条规划路径对应各自的通行代价，所述通行代价与以下信息中的至少一种有关：所述障碍物的风险等级、所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
  10. 如权利要求9所述的装置，其特征在于，所述车辆信息包括所述车辆的坐标和尺寸，所述障碍物信息包括障碍物的坐标和尺寸，所述车辆的坐标和所述障碍物的坐标为在大地坐标系ENU下的坐标；所述处理单元还用于：
    对所述车辆的可行驶区域进行栅格化处理，得到栅格地图；
    根据所述车辆的坐标将所述障碍物的坐标从所述ENU下转换到车辆坐标系下，并结合所述障碍物的尺寸获取所述障碍物在所述栅格地图上的占据区域；
    基于所述占据区域，获取M条从起始点到目标点的规划路径。
  11. 如权利要求9或10所述的装置，其特征在于，所述处理单元，具体用于：
    确定目标规划路径，所述目标规划路径为所述M条规划路径中通行代价最小的路径。
  12. 如权利要求11所述的装置，其特征在于，所述目标规划路径对应的通行代价小于目标阈值。
  13. 如权利要求9-12任一项所述的装置，其特征在于，
    所述获取单元，还用于获取预测碰撞信息；其中，所述预测碰撞信息为预测所述车辆 和所述障碍物可能发生碰撞时获取的信息；
    所述处理单元，还用于根据所述预测碰撞信息确定所述障碍物的风险等级和/或所述车辆的风险等级。
  14. 如权利要求13所述的装置，其特征在于，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
  15. 一种风险评估装置，其特征在于，包括：
    获取单元，用于根据车辆与障碍物的位置信息和运动状态信息，获取预测碰撞信息；所述预测碰撞信息为预测所述车辆和所述障碍物可能发生碰撞时获取的信息；
    处理单元，用于根据所述预测碰撞信息获取所述障碍物的风险等级和/或所述车辆的风险等级；所述障碍物的风险等级用于表征所述障碍物可能侵占所述车辆的可行驶区域且所述障碍物对所述车辆可能造成的损失程度；所述车辆的风险等级用于表征所述车辆可能对所述障碍物造成的损失程度。
  16. 如权利要求15所述的装置，其特征在于，所述预测碰撞信息包括：所述车辆相对于所述障碍物的速度Δv、所述车辆与所述障碍物可能发生碰撞时相交的体积、所述车辆与所述障碍物可能发生碰撞时的碰撞夹角、所述车辆与所述障碍物之间的中心距离、所述障碍物的所属类别中的至少一个。
  17. 一种终端，其特征在于，包括如权利要求9-14任一项所述的路径规划装置和/或15-16任一项所述的风险评估装置。
  18. 一种控制装置，其特征在于，包括处理器和存储器，所述处理器和存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行如权利要求1-6或7-8任一项所述的方法。
  19. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求1-6或7-8任一项所述的方法。
PCT/CN2020/138110 2020-12-21 2020-12-21 控制方法、相关设备及计算机可读存储介质 Ceased WO2022133684A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202080004118.5A CN112703144A (zh) 2020-12-21 2020-12-21 控制方法、相关设备及计算机可读存储介质
EP20966265.9A EP4261092B1 (en) 2020-12-21 2020-12-21 Control method, related device, and computer-readable storage medium
PCT/CN2020/138110 WO2022133684A1 (zh) 2020-12-21 2020-12-21 控制方法、相关设备及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/138110 WO2022133684A1 (zh) 2020-12-21 2020-12-21 控制方法、相关设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022133684A1 true WO2022133684A1 (zh) 2022-06-30

Family

ID=75514779

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/138110 Ceased WO2022133684A1 (zh) 2020-12-21 2020-12-21 控制方法、相关设备及计算机可读存储介质

Country Status (3)

Country Link
EP (1) EP4261092B1 (zh)
CN (1) CN112703144A (zh)
WO (1) WO2022133684A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115416651A (zh) * 2022-09-21 2022-12-02 展讯通信(天津)有限公司 行车过程障碍物监控方法、装置和电子设备
CN115431963A (zh) * 2022-09-26 2022-12-06 网络通信与安全紫金山实验室 车辆的控制方法、装置及非易失性存储介质
CN116001819A (zh) * 2023-01-31 2023-04-25 阿波罗智联(北京)科技有限公司 障碍物信息处理方法、装置、电子设备和自动驾驶车辆
CN116225019A (zh) * 2023-03-16 2023-06-06 阿波罗智联(北京)科技有限公司 无人驾驶设备的控制方法、装置、电子设备及存储介质
CN116572996A (zh) * 2023-07-12 2023-08-11 北京易控智驾科技有限公司 一种车辆的控制方法、装置和无人驾驶车辆
WO2024051024A1 (zh) * 2022-09-06 2024-03-14 劢微机器人科技(深圳)有限公司 车辆避障方法、装置、设备及存储介质
WO2024051310A1 (zh) * 2022-09-05 2024-03-14 华为技术有限公司 一种控制方法、装置及车辆
CN118494468A (zh) * 2024-07-17 2024-08-16 罗普特科技集团股份有限公司 基于人工智能的车辆控制方法及系统
WO2024188108A1 (zh) * 2023-03-15 2024-09-19 华为技术有限公司 自动泊车的方法和装置
CN120756472A (zh) * 2025-09-11 2025-10-10 纽劢科技(上海)有限公司 障碍物侵入意图识别方法及车辆控制方法
CN120886273A (zh) * 2025-09-29 2025-11-04 北京大学南昌创新研究院 一种具备自主导航的人形机器人融合系统

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113296500B (zh) * 2021-04-30 2023-04-25 浙江吉利控股集团有限公司 一种局部路径规划方法及系统
CN115542888A (zh) * 2021-06-30 2022-12-30 未来机器人（深圳）有限公司 车辆路径生成方法、装置、计算机设备和存储介质
CN113479199B (zh) * 2021-07-30 2022-08-30 三一专用汽车有限责任公司 开放区域避障方法、车辆和计算机可读存储介质
CN113895459B (zh) * 2021-11-11 2023-06-16 北京经纬恒润科技股份有限公司 一种障碍物的筛选方法及系统
CN113908551B (zh) * 2021-12-14 2022-03-11 腾讯科技（深圳）有限公司 导航路径的确定方法、装置、设备、存储介质及程序产品
CN114212106B (zh) * 2021-12-17 2023-10-10 东软睿驰汽车技术（沈阳）有限公司 一种车辆的可行驶区域内安全概率的确定方法及装置
JP7766505B2 (ja) 2022-02-01 2025-11-10 本田技研工業株式会社 移動体制御装置、移動体制御方法、およびプログラム
CN114611586A (zh) * 2022-02-22 2022-06-10 武汉路特斯汽车有限公司 一种道路场景识别方法、装置、车辆及计算机存储介质
CN114590248B (zh) * 2022-02-23 2023-08-25 阿波罗智能技术(北京)有限公司 行驶策略的确定方法、装置、电子设备和自动驾驶车辆
CN114802225B (zh) * 2022-03-04 2024-01-12 湖北国际物流机场有限公司 一种飞机引导车控制方法、系统及电子设备
CN114701502B (zh) * 2022-03-31 2025-03-04 广州文远知行科技有限公司 障碍物的识别方法、装置及电子设备
CN114954520B (zh) * 2022-04-20 2025-11-18 北京京东乾石科技有限公司 一种控制无人驾驶车辆的方法和装置
CN114852085A (zh) * 2022-05-13 2022-08-05 清华大学 基于路权侵入度的车辆自动驾驶轨迹规划方法
CN115060279B (zh) * 2022-06-08 2024-04-16 合众新能源汽车股份有限公司 路径规划方法、装置、电子设备和计算机可读介质
CN117289688A (zh) * 2022-06-17 2023-12-26 灵动科技（北京）有限公司 一种机器人避障方法、装置及计算机程序产品
CN115185271B (zh) * 2022-06-29 2023-05-23 禾多科技（北京）有限公司 导航路径生成方法、装置、电子设备和计算机可读介质
CN115309147B (zh) * 2022-06-30 2025-05-09 驭势科技（北京）有限公司 车辆运动规划方法、装置、设备及介质
CN115273512A (zh) * 2022-07-22 2022-11-01 重庆长安汽车股份有限公司 自动驾驶车辆的防碰撞辅助方法、装置、设备及介质
CN115042823B (zh) * 2022-07-29 2024-07-02 浙江吉利控股集团有限公司 一种代客泊车方法、装置、电子设备及存储介质
CN116978198A (zh) * 2022-08-29 2023-10-31 北京东土正创科技有限公司 隧道安全预警方法、相关设备及计算机可读存储介质
CN115328154B (zh) * 2022-09-05 2025-03-18 中煤科工集团重庆研究院有限公司 一种煤矿井下履带车避障学习方法
CN117742308A (zh) * 2022-09-13 2024-03-22 广州汽车集团股份有限公司 车辆路径规划方法、装置及车辆
CN115641748B (zh) * 2022-10-13 2025-02-21 中国第一汽车股份有限公司 一种用于窄路通行的控制方法以及装置
CN115782867B (zh) * 2022-11-17 2024-01-30 上海西井科技股份有限公司 轨迹碰撞风险评估方法、装置、电子设备和存储介质
CN116295473A (zh) * 2022-11-30 2023-06-23 新石器慧通（北京）科技有限公司 无人车路径规划方法、装置、设备及存储介质
CN116052122B (zh) * 2023-01-28 2023-06-27 广汽埃安新能源汽车股份有限公司 一种可行驶空间的检测方法、装置、电子设备及存储介质
CN116215518B (zh) * 2023-03-13 2026-04-07 踏歌智行科技股份有限公司 一种无人驾驶矿卡前方道路碰撞风险预测及量化方法
CN118722635A (zh) * 2023-03-31 2024-10-01 华为技术有限公司 一种车道选择的方法、装置和车辆
CN116353584B (zh) * 2023-03-31 2025-10-14 重庆长安汽车股份有限公司 一种车辆碰撞风险预测系统及车辆
CN116486374B (zh) * 2023-04-21 2025-09-02 北京百度网讯科技有限公司 风险障碍物确定方法、自动驾驶车辆、电子设备及介质
AU2023456637A1 (en) * 2023-06-16 2026-01-08 Yinwang Intelligent Technologies Co., Ltd. Intelligent driving method and apparatus
CN117485364B (zh) * 2023-10-19 2025-02-14 东风商用车有限公司 车辆控制方法、装置、设备及可读存储介质
CN117657129A (zh) * 2023-12-08 2024-03-08 岚图汽车科技有限公司 盲区的行驶控制方法、装置、设备及存储介质
CN120708196A (zh) * 2024-03-26 2025-09-26 北京罗克维尔斯科技有限公司 防撞头报警概率确定方法、装置、电子设备及存储介质
CN118529037A (zh) * 2024-04-25 2024-08-23 岚图汽车科技有限公司 车辆避险方法、装置、设备及存储介质
CN118658344B (zh) * 2024-08-21 2024-11-15 中意智新能源科技有限公司 一种基于物联网的无人机安全监测系统及方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100145618A1 (en) * 2008-12-04 2010-06-10 Institute For Information Industry Vehicle collision management systems and methods
US20100201509A1 (en) * 2009-02-03 2010-08-12 Yoshitaka Hara Collision avoidance assisting system for vehicle
CN105599764A (zh) * 2014-11-12 2016-05-25 现代自动车株式会社 用于自主车辆的行车路线规划装置及方法
CN107031619A (zh) * 2015-12-11 2017-08-11 现代自动车株式会社 用于控制自动驾驶系统的路径的方法和设备
CN110077397A (zh) * 2019-05-14 2019-08-02 芜湖汽车前瞻技术研究院有限公司 一种智能车避障轨迹规划方法及装置
CN110362077A (zh) * 2019-07-03 2019-10-22 上海交通大学 无人驾驶车辆紧急避险决策系统、方法及介质
CN110497909A (zh) * 2019-07-17 2019-11-26 百度在线网络技术（北京）有限公司 应用于车辆的碰撞检测和避免方法及装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10246090B2 (en) * 2016-11-07 2019-04-02 Ford Global Technologies, Llc Vehicle collision severity mitigation
CN106774347A (zh) * 2017-02-24 2017-05-31 安科智慧城市技术（中国）有限公司 室内动态环境下的机器人路径规划方法、装置和机器人
CN107992050B (zh) * 2017-12-20 2021-05-11 广州汽车集团股份有限公司 无人驾驶汽车局部路径运动规划方法和装置
CN110462703A (zh) * 2018-03-08 2019-11-15 百度时代网络技术（北京）有限公司 基于碰撞后分析的自动驾驶车辆的车辆动作优化
CN108646765A (zh) * 2018-07-25 2018-10-12 齐鲁工业大学 基于改进a*算法的四足机器人路径规划方法及系统
JP7263119B2 (ja) * 2019-05-22 2023-04-24 村田機械株式会社 走行決定方法、コントローラ、及び当該コントローラを備える走行システム
EP3977226B1 (en) * 2019-06-03 2025-08-06 Realtime Robotics, Inc. Apparatus and method to facilitate motion planning in environments having dynamic obstacles
CN110550029B (zh) * 2019-08-12 2021-02-09 华为技术有限公司 障碍物避让方法及装置
CN110466513A (zh) * 2019-08-30 2019-11-19 北京小马慧行科技有限公司 车辆控制方法及装置
CN111552284B (zh) * 2020-04-20 2024-07-26 宁波吉利汽车研究开发有限公司 无人驾驶车辆的局部路径规划方法、装置、设备及介质
CN111640323A (zh) * 2020-06-08 2020-09-08 北京享云智汇科技有限公司 一种路况信息获取方法
CN112099493B (zh) * 2020-08-31 2021-11-19 西安交通大学 一种自主移动机器人轨迹规划方法、系统及设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100145618A1 (en) * 2008-12-04 2010-06-10 Institute For Information Industry Vehicle collision management systems and methods
US20100201509A1 (en) * 2009-02-03 2010-08-12 Yoshitaka Hara Collision avoidance assisting system for vehicle
CN105599764A (zh) * 2014-11-12 2016-05-25 现代自动车株式会社 用于自主车辆的行车路线规划装置及方法
CN107031619A (zh) * 2015-12-11 2017-08-11 现代自动车株式会社 用于控制自动驾驶系统的路径的方法和设备
CN110077397A (zh) * 2019-05-14 2019-08-02 芜湖汽车前瞻技术研究院有限公司 一种智能车避障轨迹规划方法及装置
CN110362077A (zh) * 2019-07-03 2019-10-22 上海交通大学 无人驾驶车辆紧急避险决策系统、方法及介质
CN110497909A (zh) * 2019-07-17 2019-11-26 百度在线网络技术（北京）有限公司 应用于车辆的碰撞检测和避免方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4261092A4 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024051310A1 (zh) * 2022-09-05 2024-03-14 华为技术有限公司 一种控制方法、装置及车辆
WO2024051024A1 (zh) * 2022-09-06 2024-03-14 劢微机器人科技(深圳)有限公司 车辆避障方法、装置、设备及存储介质
CN115416651A (zh) * 2022-09-21 2022-12-02 展讯通信(天津)有限公司 行车过程障碍物监控方法、装置和电子设备
CN115431963A (zh) * 2022-09-26 2022-12-06 网络通信与安全紫金山实验室 车辆的控制方法、装置及非易失性存储介质
CN116001819A (zh) * 2023-01-31 2023-04-25 阿波罗智联(北京)科技有限公司 障碍物信息处理方法、装置、电子设备和自动驾驶车辆
WO2024188108A1 (zh) * 2023-03-15 2024-09-19 华为技术有限公司 自动泊车的方法和装置
CN116225019A (zh) * 2023-03-16 2023-06-06 阿波罗智联(北京)科技有限公司 无人驾驶设备的控制方法、装置、电子设备及存储介质
CN116572996A (zh) * 2023-07-12 2023-08-11 北京易控智驾科技有限公司 一种车辆的控制方法、装置和无人驾驶车辆
CN116572996B (zh) * 2023-07-12 2023-09-12 北京易控智驾科技有限公司 一种车辆的控制方法、装置和无人驾驶车辆
CN118494468A (zh) * 2024-07-17 2024-08-16 罗普特科技集团股份有限公司 基于人工智能的车辆控制方法及系统
CN120756472A (zh) * 2025-09-11 2025-10-10 纽劢科技(上海)有限公司 障碍物侵入意图识别方法及车辆控制方法
CN120886273A (zh) * 2025-09-29 2025-11-04 北京大学南昌创新研究院 一种具备自主导航的人形机器人融合系统

Also Published As

Publication number Publication date
EP4261092A4 (en) 2024-05-22
EP4261092B1 (en) 2026-02-11
CN112703144A (zh) 2021-04-23
EP4261092A1 (en) 2023-10-18

Similar Documents

Publication Publication Date Title
WO2022133684A1 (zh) 控制方法、相关设备及计算机可读存储介质
JP6601696B2 (ja) 予測装置、予測方法、およびプログラム
JP6710710B2 (ja) 車両制御装置、車両制御方法、およびプログラム
US11225249B2 (en) Vehicle control device, vehicle control method, and storage medium
CN108778879B (zh) 车辆控制系统、车辆控制方法及存储介质
US20190146519A1 (en) Vehicle control device, vehicle control method, and storage medium
US11661057B2 (en) Vehicle control device, vehicle control method, and storage medium
US20180239361A1 (en) Autonomous Driving At Intersections Based On Perception Data
US11079762B2 (en) Vehicle control device, vehicle control method, and storage medium
US20200001867A1 (en) Vehicle control apparatus, vehicle control method, and program
JP6641583B2 (ja) 車両制御装置、車両制御方法、およびプログラム
JP7085371B2 (ja) 車両制御装置、車両制御方法、およびプログラム
CN108534792A (zh) 车道变更推定装置、车道变更推定方法及存储介质
CN108628300A (zh) 路径决定装置、车辆控制装置、路径决定方法及存储介质
JP6648384B2 (ja) 車両制御装置、車両制御方法、およびプログラム
CN111511621B (zh) 车辆控制装置、车辆控制方法及存储介质
JP2019159427A (ja) 車両制御装置、車両制御方法、およびプログラム
JP7220192B2 (ja) 車両制御装置、車両制御方法、およびプログラム
JP2019160031A (ja) 車両制御装置、車両制御方法、およびプログラム
JP2019156270A (ja) 車両制御装置、車両制御方法、及びプログラム
JP2019185112A (ja) 車両制御装置、車両制御方法、およびプログラム
JP2020083106A (ja) 車両制御装置、車両制御方法、およびプログラム
JP7080091B2 (ja) 車両制御装置、車両制御方法、およびプログラム
JP2021047609A (ja) 周辺認識装置、周辺認識方法、およびプログラム
JP2021009624A (ja) 車両制御装置、車両制御方法、およびプログラム

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: 20966265

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2020966265

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020966265

Country of ref document: EP

Effective date: 20230721

WWG Wipo information: grant in national office

Ref document number: 2020966265

Country of ref document: EP