CN116331237A - Control method for autonomous vehicles - Google Patents

Abstract

The invention discloses a control method of an automatic driving vehicle. Wherein the method comprises the following steps: acquiring abnormal state information of an autonomous vehicle, wherein the abnormal state information comprises: first state information for representing that abnormality occurs in a domain controller in an autonomous vehicle, and second state information for representing that abnormality occurs in a communication state of the autonomous vehicle; determining an anomaly type of the autonomous vehicle based on the anomaly status information, wherein the anomaly type comprises: a first exception type of the domain controller and a second exception type of the data transfer bus; determining a fault grade corresponding to the abnormal type, wherein the fault grade is used for representing the influence degree of the abnormal type on the normal running of the automatic driving vehicle; and controlling the operation of the automatic driving vehicle based on a preset control scheme corresponding to the fault level. The invention solves the technical problems that the related technology can not comprehensively discover the faults of the whole vehicle and adopts corresponding control measures.

Description

Control method for autonomous vehicles

technical field

The present invention relates to the field of vehicle control, in particular to a control method for an automatic driving vehicle.

Background technique

As the actual application scenarios of self-driving cars become more and more complex, people have higher and higher safety requirements for self-driving cars. At present, the existing self-driving car degraded operation measures mainly focus on human-vehicle interaction and The alarm did not take timely and autonomous safety measures to protect passengers and vehicles, and only focused on a certain module failure. The classification and classification of failures were too simple, which greatly reduced the passenger experience and even endangered passenger safety.

For the above problems, no effective solution has been proposed yet.

Contents of the invention

An embodiment of the present invention provides a control method for an automatic driving vehicle, to at least solve the technical problem that related technologies cannot fully detect vehicle faults and take corresponding control measures.

According to an aspect of an embodiment of the present invention, there is provided a method for controlling an automatic driving vehicle, including: acquiring abnormal state information of the automatic driving vehicle, wherein the abnormal state information includes: Abnormal first state information, and second state information used to indicate that the communication state of the autonomous vehicle is abnormal; based on the abnormal state information, determine the abnormal type of the autonomous vehicle, wherein the abnormal type includes: the first state of the domain controller The abnormal type and the second abnormal type of the data transmission bus; determining the fault level corresponding to the abnormal type, wherein the fault level is used to characterize the degree of influence of the abnormal type on the normal driving of the self-driving vehicle; based on the preset control scheme corresponding to the fault level, Control the operation of self-driving vehicles.

Optionally, obtaining the abnormal state information of the self-driving vehicle includes: in response to an abnormality in the domain controller, obtaining the current state information sent by the domain controller and the fault information of the electronic device corresponding to the domain controller to obtain the first state information ; Obtain data transmission status information of the data transmission bus to obtain second status information.

Optionally, determining the fault level corresponding to the abnormal type includes: matching the abnormal type with multiple preset abnormal types to obtain a target abnormal type that successfully matches the abnormal type; determining the preset level corresponding to the target abnormal type as the fault level .

Optionally, in response to failure to match the abnormality type with multiple preset abnormality types, the method further includes: obtaining a fault cause corresponding to the fault type; evaluating the fault cause to obtain a fault level corresponding to the fault type.

Optionally, based on the preset control scheme corresponding to the failure level, control the operation of the self-driving vehicle, including one of the following: controlling the power supply of the self-driving vehicle to disconnect; controlling the self-driving vehicle to perform emergency braking; controlling the self-driving vehicle to Non-emergency braking; control the self-driving vehicle to pull over and stop; control the self-driving vehicle to drive to the target stop point to stop; control the self-driving vehicle to drive to the second stop point to stop after completing the current scheduling task; control the speed of the self-driving vehicle to be less than the preset Setting a value; controlling the self-driving vehicle to maintain a static state; controlling the self-driving vehicle to output warning information, wherein the warning information is used to indicate that the self-driving vehicle is abnormal.

Optionally, controlling the self-driving vehicle to perform emergency braking includes: acquiring first driving information of the self-driving vehicle, wherein the first driving information includes: chassis status information, vehicle positioning information, first Obstacle information and navigation route information; based on the first driving information and the historical planning trajectory of the autonomous vehicle, generate the vehicle trajectory of the autonomous vehicle at a future moment; based on the first obstacle information and the vehicle trajectory, determine the trajectory of the autonomous vehicle An emergency braking system, wherein different emergency braking systems are used to brake the self-driving vehicle in different braking methods; the self-driving vehicle is controlled to brake based on the emergency braking mode.

Optionally, based on the first obstacle information and the vehicle trajectory, determining the emergency braking system of the autonomous vehicle includes: minimizing the vehicle trajectory and maximizing the deceleration of the autonomous vehicle to obtain an automatic driving The first emergency braking trajectory of the vehicle; the sum of the displacement of the first emergency braking trajectory and the parking safety distance of the self-driving vehicle is obtained to obtain a preset distance; in response to the obstacle distance in the obstacle information being greater than the preset distance, determine the emergency braking The braking mode is the first braking mode, wherein the first braking mode is used to control the automatic driving vehicle to brake according to the vehicle trajectory; in response to the obstacle distance being less than or equal to the preset distance, it is determined that the emergency braking mode is the second A braking mode, wherein the second braking mode is used to control the brake pedal of the self-driving vehicle to brake according to a plurality of different opening degrees.

Optionally, controlling the self-driving vehicle to perform non-emergency braking includes: acquiring first driving information of the self-driving vehicle, wherein the driving information includes: chassis state information, vehicle positioning information, and a first obstacle in front of the self-driving vehicle object information and navigation route information; based on the first driving information and the historical planning trajectory of the autonomous vehicle, generate the vehicle trajectory of the autonomous vehicle in the future; maximize the vehicle trajectory, and calculate the deceleration of the autonomous vehicle Minimize to obtain the second emergency braking trajectory of the autonomous vehicle; based on the second emergency braking trajectory, the autonomous vehicle is controlled to brake.

Optionally, controlling the self-driving vehicle to pull over to stop includes: acquiring second driving information of the self-driving vehicle, wherein the second driving information includes: lateral displacement, velocity and acceleration; performing trajectory estimation on the self-driving vehicle based on the second driving information combined to obtain the motion trajectory of the autonomous vehicle; obtain the perception information of the autonomous vehicle, wherein the perception information includes: the second obstacle information in the lateral direction, and the lane line information around the autonomous vehicle; based on the perception information and the motion trajectory , control the self-driving vehicle to pull over and stop.

Optionally, the above method further includes: determining a target failure level in the failure levels, wherein the target failure level is higher than other failure levels in the failure levels; obtaining a control scheme corresponding to the target failure level to obtain a preset control scheme.

According to another aspect of the embodiments of the present invention, there is also provided a control system for an automatic driving vehicle, including: a state data receiving module, configured to obtain abnormal state information of the automatic driving vehicle, wherein the abnormal state information includes: The first state information indicating that the domain controller in the self-driving vehicle is abnormal, and the second state information used to indicate that the communication state of the self-driving vehicle is abnormal; the fault diagnosis and classification module is used to determine the abnormal state information of the self-driving vehicle. , and determine the fault level corresponding to the abnormal type, wherein the abnormal type includes: the first abnormal type of the domain controller and the second abnormal type of the data transmission bus, and the fault level is used to represent the normality of the abnormal type to the automatic driving vehicle The degree of influence of driving; the vehicle control module is used to control the operation of the automatic driving vehicle based on the preset control scheme corresponding to the failure level.

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, and the computer-readable storage medium includes a stored program, wherein, when the program is running, the device where the computer-readable storage medium is located is controlled to execute the above automatic driving vehicle. control method.

According to another aspect of the embodiments of the present invention, a processor is also provided, and the processor is used to run a program, wherein the above method for controlling an automatic driving vehicle is executed when the program is running.

In the embodiment of the present invention, the abnormal state information of the self-driving vehicle is obtained, and based on the abnormal state information, the abnormal type of the self-driving vehicle is determined, and then the failure level corresponding to the abnormal type is determined, and based on the preset control scheme corresponding to the failure level, To control the operation of the self-driving vehicle, it should be noted that the abnormal types include: the first abnormal type of the domain controller and the second abnormal type of the data transmission bus, and the fault level is used to represent the degree of influence of the abnormal type on the normal driving of the automatic driving vehicle By obtaining the abnormal information of the vehicle domain controller and the communication state, determining the abnormal type and the corresponding fault level of the vehicle, and setting the corresponding control scheme based on the fault level, it is possible to effectively evaluate various problems found in the operation of the autonomous vehicle. Class abnormalities and take corresponding downgrading measures, so as to realize the technical effect of comprehensive detection of vehicle faults, and adopt different control schemes for different fault types, and then solve the problem that related technologies cannot comprehensively detect vehicle faults and take corresponding measures Technical aspects of control measures.

Description of drawings

The accompanying drawings described here are used to provide a further understanding of the present invention and constitute a part of the application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations to the present invention. In the attached picture:

Fig. 1 is a flow chart of a control method of an automatic driving vehicle according to an embodiment of the present invention;

2 is a schematic diagram of a degraded operation system for an automatic driving vehicle according to an embodiment of the present invention;

Fig. 3 is a schematic diagram of a control system of an automatic driving vehicle according to an embodiment of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Example 1

According to an embodiment of the present invention, a method for controlling an autonomous vehicle is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, although In the flowcharts, a logical order is shown, but in some cases the steps shown or described may be performed in an order different from that shown or described herein.

Fig. 1 is a flowchart of a method for controlling an autonomous vehicle according to an embodiment of the present invention. As shown in Fig. 1, the method includes the following steps:

Step S102, acquiring abnormal state information of the self-driving vehicle, wherein the abnormal state information includes: first state information used to indicate that the domain controller in the self-driving vehicle is abnormal, and used to indicate that the communication state of the self-driving vehicle is abnormal The second state information of .

Wherein, the domain controller can be a server computer that responds to the security authentication request in the computer network domain, and is used to be responsible for the data calculation and overall control functions of the key functional domains of the self-driving vehicle. The key functional domains of autonomous vehicles are obtained based on the electrical and electronic architecture of autonomous vehicles, including but not limited to the domain of autonomous driving, chassis, power, body and networking. The domain of autonomous driving is responsible for the automatic driving functions of vehicles. The chassis domain is the executive mechanism of the vehicle, which can feed back vehicle driving status data to the automatic driving system, the power domain manages the energy usage status of the vehicle, and the body domain manages the use of vehicle-related components such as lights, doors, windows, wipers, etc. state, and the network connection domain realizes the interconnection and intercommunication of information inside and outside the car, and conducts all-round network links between cars and cloud platforms, cars and cars, cars and roads, cars and people, and the intra-vehicle network. The first status information can be is the state information of the domain controller, and the second state information may be the state information of the vehicle communication.

In an optional embodiment, the first state information may be obtained through an electronic control unit (Electronic Control Unit, ECU for short) and connected sensors, and the second state information may be obtained through data monitoring.

Step S104, based on the abnormal state information, determine the abnormal type of the autonomous vehicle, wherein the abnormal type includes: a first abnormal type of the domain controller and a second abnormal type of the data transmission bus.

Among them, the first abnormal type can be the abnormal type of the domain controller, including but not limited to: no output data, data tampered, abnormal processing results and other unknown abnormalities, and the ECU fault type and sensor fault type are determined by the specific product maintenance manual , the second exception type may be an exception type of the data transmission bus, including but not limited to: exceptions such as communication interruption, communication delay, and communication link attack.

In an optional embodiment, the first abnormal type can be determined through the ECU and the connected sensor, and the data transmission status of the connected CAN bus network and Ethernet network can be monitored, and the network communication status information can be received for detection and confirmation. Communication status exception and specific exception type to obtain the second exception type.

Step S106, determining the failure level corresponding to the abnormality type, wherein the failure level is used to represent the degree of influence of the abnormality type on the normal driving of the automatic driving vehicle.

In an optional embodiment, it is possible to analyze the degree of danger by receiving and obtaining abnormal domain controllers (that is, abnormal communication nodes) and data transmission status abnormalities (that is, abnormal communication status), that is, analyzing abnormal effects on passengers and vehicles. The severity of the possible consequences of the state, and then carry out a reasonable classification of the severity of autonomous vehicle faults, and establish a fault severity level table corresponding to the type of fault to determine the fault level corresponding to the abnormal type.

Specifically, the failure levels may include but not limited to nine failure levels from E0 to E8. Among them, E0 is the highest failure level, E8 is the lowest failure level, and the middle level is deduced by analogy.

Step S108, based on the preset control scheme corresponding to the failure level, control the operation of the self-driving vehicle.

Wherein, the preset control scheme may be preset in advance, and for different fault levels received, the corresponding vehicle control method is invoked in combination with the current state of the vehicle and information of obstacles in front of the vehicle.

Specifically, when the failure level is E0, it can be considered that the current vehicle is uncontrollable and the danger is inevitable. It is necessary and only possible to cut off the power supply of the self-driving vehicle by cutting off the high voltage to reduce the damage caused by the collision to the vehicle; When the fault level is E1, it can be considered that the collision is inevitable or the vehicle is in a critical condition but the vehicle is controllable, and the most urgent braking control method must be adopted to control the vehicle to stop, so as to reduce the damage caused by the collision to people and vehicles or to avoid the collision; When the fault level is E2, it can be considered that the vehicle is controllable, and the collision condition exists but can be avoided, and non-emergency braking can be used to control the vehicle brake, avoiding collisions and improving the comfort of the braking process from the perspective of passengers; when the fault level is E3, It can be considered that the vehicle does not meet the conditions for automatic driving. If the condition of collision may be triggered if the vehicle continues to drive, it can be parked by the side of the road and continue driving after the abnormality is eliminated. When the fault level is E4, it can be considered that the vehicle has short-term automatic driving conditions, but beyond a certain period After the collision condition may be triggered, you can find the nearest stop, control the vehicle to reach the point safely and brake to stop; when the fault level is E5, it can be considered that the vehicle has short-term automatic driving conditions, but the collision condition may be triggered after a certain period of time, and Due to its own task scheduling problem, the vehicle cannot immediately adopt a parking method other than the current planned task. At this time, it is necessary to control the vehicle to complete the current scheduling task, such as loading and unloading passengers, loading and unloading, or leaving the task point, etc., and then find the nearest stop to control the safety of the vehicle Arrive at this point and brake to stop; when the fault level is E6, it can be considered that the vehicle has automatic driving conditions and no collision conditions, but due to special driving scene restrictions, the vehicle speed must be limited below a certain value. At this time, the vehicle is controlled at this limit. Speed value driving; when the fault level is E7, it can be considered that the vehicle is in a stationary state and there is an abnormality. At this time, the automatic driving function of the vehicle needs to be locked, and the vehicle should be kept in a stopped state until the abnormality is eliminated and the vehicle lock state is released; when the fault level is E8, It can be considered that the existing abnormality has no impact on the current running state of the vehicle, and only an alarm prompt is given.

In the embodiment of the present invention, the abnormal state information of the self-driving vehicle is obtained, and based on the abnormal state information, the abnormal type of the self-driving vehicle is determined, and then the failure level corresponding to the abnormal type is determined, and based on the preset control scheme corresponding to the failure level, To control the operation of the self-driving vehicle, it should be noted that the abnormal types include: the first abnormal type of the domain controller and the second abnormal type of the data transmission bus, and the fault level is used to represent the degree of influence of the abnormal type on the normal driving of the automatic driving vehicle By obtaining the abnormal information of the vehicle domain controller and the communication state, determining the abnormal type and the corresponding fault level of the vehicle, and setting the corresponding control scheme based on the fault level, it is possible to effectively evaluate various problems found in the operation of the autonomous vehicle. Class abnormalities and take corresponding downgrading measures, so as to realize the technical effect of comprehensive detection of vehicle faults, and adopt different control schemes for different fault types, and then solve the problem that related technologies cannot comprehensively detect vehicle faults and take corresponding measures Technical aspects of control measures.

Optionally, obtaining the abnormal state information of the self-driving vehicle includes: in response to an abnormality in the domain controller, obtaining the current state information sent by the domain controller and the fault information of the electronic device corresponding to the domain controller to obtain the first state information ; Obtain data transmission status information of the data transmission bus to obtain second status information.

Wherein, the current status information may be the status information of the domain controller in the current working process, the fault information of the electronic device may include but not limited to the fault location and fault degree, and the data transmission status information may include but not limited to normal and abnormal.

In an optional embodiment, the current state information sent by the domain controller can be obtained through the ECU and the connection sensor, and the data transmission state information of the data transmission bus can be obtained through data monitoring.

Optionally, determining the fault level corresponding to the abnormal type includes: matching the abnormal type with multiple preset abnormal types to obtain a target abnormal type that successfully matches the abnormal type; determining the preset level corresponding to the target abnormal type as the fault level .

Wherein, the preset abnormality type may be various types of vehicle abnormalities preset in advance, the target abnormality type may be a preset abnormality type matching the current abnormality type of the vehicle, and the preset level may be a preset failure level, which may be It is represented by a total of nine failure levels from E0 to E8.

In an optional embodiment, the abnormal type can be matched with multiple preset abnormal types through the method of keyword comparison, and the target abnormal type that successfully matches the abnormal type can be obtained, which can be obtained by looking up the table. It is determined that the preset level corresponding to the target abnormal type is the failure level.

Specifically, according to the obtained first state information and second state information, a fault severity level table is formed after the fault risk assessment, and abnormal alarm information is sent to the vehicle terminal. Known abnormalities found later can be directly obtained by checking the table Fault severity rating.

Optionally, in response to failure to match the exception type with multiple preset exception types, the method further includes: obtaining a fault cause corresponding to the fault type; evaluating the fault cause to obtain a fault level corresponding to the fault type.

Wherein, the failure cause may be a factor that causes the vehicle to fail.

It can be understood that when an unknown abnormality occurs in the vehicle, the fault severity level evaluation is performed according to the fault location and description, and the existing fault severity level is matched, and then this type of abnormality and the corresponding fault level are added to the above fault severity level. degree scale.

Optionally, the above method further includes: determining a target failure level in the failure levels, wherein the target failure level is higher than other failure levels in the failure levels; obtaining a control scheme corresponding to the target failure level to obtain a preset control scheme.

Wherein, the target failure level may be the level corresponding to the current failure of the vehicle.

Specifically, as shown in step S108, different failure levels correspond to different control schemes.

Optionally, based on the preset control scheme corresponding to the failure level, control the operation of the self-driving vehicle, including one of the following: controlling the power supply of the self-driving vehicle to disconnect; controlling the self-driving vehicle to perform emergency braking; controlling the self-driving vehicle to Non-emergency braking; control the self-driving vehicle to pull over and stop; control the self-driving vehicle to drive to the target stop point to stop; control the self-driving vehicle to drive to the second stop point to stop after completing the current scheduling task; control the speed of the self-driving vehicle to be less than the preset Setting a value; controlling the self-driving vehicle to maintain a static state; controlling the self-driving vehicle to output warning information, wherein the warning information is used to indicate that the self-driving vehicle is abnormal.

Wherein, the target stop can be the stop closest to the current vehicle, and the current dispatching task can include but not limited to loading and unloading passengers, loading and unloading, or leaving the task point, etc., and the second stop can be the nearest stop after the vehicle completes the current dispatching task. Stopping point, the preset value can be the vehicle speed limited by the special scene.

In an optional embodiment, the vehicle can be controlled by the vehicle control device to execute the above control scheme, and the warning information can be fed back to the user through the sound feedback device, wherein the sound feedback device can be understood as any device that can realize sound feedback , such as a horn, or other equipment loaded with horns. The normal traffic notification fed back by the sound feedback device can be a sound with semantics, or a recognizable sound without semantics. For example, the normal notification of the vehicle status is a "beep", and the abnormal notification of the vehicle status is "Didi Di" Three times.

Specifically, as described in step S108, the above control scheme corresponds to nine failure levels from E0 to E8.

Optionally, controlling the self-driving vehicle to perform emergency braking includes: acquiring first driving information of the self-driving vehicle, wherein the driving information includes: chassis state information, vehicle positioning information, and a first obstacle located in front of the self-driving vehicle information and navigation route information; based on the first driving information and the historical planning trajectory of the autonomous vehicle, generate the vehicle trajectory of the autonomous vehicle at a future moment; based on the first obstacle information and the vehicle trajectory, determine the emergency control of the autonomous vehicle braking system, wherein different emergency braking systems are used to brake the self-driving vehicle with different braking methods; the self-driving vehicle is controlled to brake based on the emergency braking mode.

Among them, the chassis state information can be normal or abnormal, the vehicle positioning information can be the current specific positioning of the vehicle, the first obstacle information can be the perceived obstacle information in front of the vehicle, the navigation route information can be the specific route of the vehicle navigation, historical planning The trajectory may be a historical braking planning trajectory of the vehicle, and the emergency braking system may be a way of controlling the vehicle to perform emergency braking.

In an optional embodiment, the first driving information of the self-driving vehicle may be acquired through devices such as sensors and positioning systems.

Specifically, generating the vehicle trajectory of the self-driving vehicle at a future moment includes establishing a vehicle braking trajectory planning method, that is, the trajectory planning module of the vehicle degraded operation system. According to the chassis state information, vehicle positioning information, perceived obstacle information and navigation route information, combined with the vehicle history planning trajectory, periodically generate the braking trajectory of the vehicle in the advanced prediction state; create a planning module data receiving and processing timer and vehicle driving path reference Line generator, start the corresponding processing thread. According to the received braking signal, call the scene planner for processing; receive external chassis status information, vehicle positioning information, perceived obstacle information and navigation route information in the scene planner, and update the vehicle status information, perception fusion information and Navigation route information; if there is the latest navigation route, according to the latest vehicle status information and navigation route information, call the map data interface to obtain high-precision map data within a certain range in the front and rear of the vehicle, including road information, lane information, intersections, signal lights, Pedestrian crossings, speed limit signs, no parking signs and other information, and generate a set of reference lines for vehicle driving based on the high-precision map data in this local area. If there is no latest navigation route, update the road map data according to the vehicle’s heading direction and a certain range of straight-line paths behind the vehicle planned by the reference line generator, and generate a simplified vehicle driving reference line; according to the current state of the vehicle and historical planning The trajectory, considering the control delay of the vehicle, predicts and updates the pre-control state of the vehicle as the starting point of trajectory planning. The planned starting point and the last planned trajectory of the vehicle are spliced to ensure the continuity of the overall planned trajectory and the smoothness of vehicle control; By traversing the reference line set, call the trajectory planning method to generate the displacement data and speed data of the vehicle along each reference line; the displacement data planning of the vehicle along the reference line is to project the planning starting point to the corresponding reference line in internal coordinates, and then use a certain distance interval The method of linear interpolation intercepts and converts the path points on the reference line as displacement data points.

Optionally, based on the first obstacle information and the vehicle trajectory, determining the emergency braking system of the autonomous vehicle includes: minimizing the vehicle trajectory and maximizing the deceleration of the autonomous vehicle to obtain an automatic driving The first emergency braking trajectory of the vehicle; the sum of the displacement of the first emergency braking trajectory and the parking safety distance of the self-driving vehicle is obtained to obtain a preset distance; in response to the obstacle distance in the obstacle information being greater than the preset distance, determine the emergency braking The braking mode is the first braking mode, wherein the first braking mode is used to control the automatic driving vehicle to brake according to the vehicle trajectory; in response to the obstacle distance being less than or equal to the preset distance, it is determined that the emergency braking mode is the second A braking mode, wherein the second braking mode is used to control the brake pedal of the self-driving vehicle to brake according to a plurality of different opening degrees.

Among them, the first emergency braking trajectory can be the braking trajectory after replanning the vehicle trajectory and deceleration, and the preset distance can be understood as the limit braking distance, which is used to represent the calculated maximum distance between the vehicle and the obstacle after it stops .

Specifically, determining the emergency braking mode of the self-driving vehicle may include: planning the speed data of the vehicle along the reference line, and first judging whether the speed data needs to be re-planned according to the projection of the planning starting point on the planned trajectory in the previous frame. If the remaining distance S _remain from the projected point to the end point of the planned trajectory is less than the distance from the vehicle to the first obstacle in front of the S _obstacle minus the safety distance S A from the obstacle after the vehicle _{stops, that is, S remain <} S _obstacle - S _A , then there is no need To re-plan the speed data, the speed data of the planned trajectory of the previous frame can be used, and the relative distance between the speed data and the planning starting point can be corrected. Otherwise, re-plan the speed data from the starting point of planning, according to the three-stage S-shaped braking curve, switch from the [s=0, v=v _m , a=0] state to [s=s ₁ , v=v ₁ , a=-a _m ] state, the rate of deceleration change is -J, where s, v and a are the state values of vehicle displacement, velocity and acceleration, v _m is the initial braking speed, s ₁ is the vehicle’s first Traveling distance after the end of the first stage, v ₁ is the speed value of the vehicle after the end of the first stage, a _m is the maximum deceleration reached by the vehicle after the end of the first stage, and it is a positive value. And then transform to [s=s ₂ , v=v ₂ , a= _-am ] state with uniform deceleration motion, where s ₂ is the driving distance of the vehicle after the second stage, and v ₂ is the speed of the vehicle after the second stage value. Finally, the state of [s=s _m , v=0, a=0] is converted to the state of [s=s m , v=0, a=0 _] with the deceleration increasing at a constant speed. The final driving distance of the planned trajectory. In these three stages, v _m and J are known quantities, and the constraint relationship between s _m and a _m can be obtained, where s _m ≤ S _barrier - S _safety , and a _m is not greater than the maximum deceleration value in the vehicle accelerator/brake calibration Combined with the vehicle movement process, the velocity data of the vehicle along the reference line is finally established, including time domain state information such as time, displacement, velocity, acceleration and jerk during the vehicle movement process; the displacement data and velocity data of the vehicle along the corresponding reference line, Linearly estimate the state value at fixed time intervals, and finally form the vehicle trajectory along the corresponding reference line;

According to the above-mentioned planning trajectory corresponding to the reference line, the trajectory evaluation equation and comprehensive cost function are established by considering the curvature change of the trajectory curve, lateral offset, distance from obstacles and deviation from the reference line, and the total cost value of each reference line trajectory is calculated. , select the reference line trajectory with the smallest cost value as the final vehicle trajectory, correct the relative time of the trajectory based on the current timestamp information, and release the trajectory data regularly;

Establish the braking control method of the vehicle along the planned trajectory, that is, the control module of the vehicle degraded operation system. According to the vehicle trajectory generated above, combined with the chassis state information, vehicle positioning information and vehicle accelerator/brake calibration information, periodically generate vehicle horizontal and vertical control commands, and control the vehicle to brake along the planned trajectory;

Establish the vehicle lateral control method based on the linear quadratic optimal control algorithm, establish the vehicle dynamics equation according to the vehicle parameters and longitudinal speed, solve the coefficient matrices A and B in the state equation, and discretize the continuous state equation of the vehicle According to the state matrix A and B, the linear quadratic regulator (Linear Quadratic Regulator, referred to as LQR) objective function is established, through iterative optimization to make the objective function meet the iterative accuracy requirements, and the optimal state feedback matrix K is obtained, with a certain The preview time combines the vehicle state and planning trajectory information to predict the state parameters of the vehicle at the preview time point in advance, and compares the vehicle's predicted state with the current state to obtain the vehicle's lateral control error and the curvature information of the preview point, and the optimal state The feedback matrix, together with the vehicle parameter information and the curvature information of the preview point, calculates the feedforward control output to eliminate the steady-state error, and calculates the final control output based on the state feedback matrix, lateral control error, and feedforward control output obtained from the previous calculation. According to the chassis control protocol, the steering command is periodically sent to the vehicle chassis to control the steering process of the vehicle;

Establish a vehicle longitudinal control method based on the proportional, integral and differential (Proportion Integral Differential, PID) control algorithm of double-loop deviation;

Establish the underlying logic of PID control, calculate the PID control output according to the PID discretization calculation formula, initialize the position PID and speed PID parameters according to the control module configuration information, and load the accelerator/brake calibration table, which is the longitudinal dynamic calibration of a specific vehicle in advance test obtained;

Establish a control module timer to regularly receive external chassis status information, vehicle positioning information and trajectory planning information, and perform data verification and receive timeout processing, update vehicle status data according to the received chassis status information and vehicle positioning information, and update vehicle status data according to the planned trajectory. For the initial braking speed, query the PID parameter interpolation table, and set the position PID and speed PID control parameters at a specific initial braking speed to obtain the optimal control parameters at different initial braking speeds. The PID parameter interpolation table is obtained by tuning the position PID and speed PID of different initial braking speeds of a specific vehicle in advance, and predicts the state parameters of the vehicle after the preview time by combining the vehicle state and planning trajectory information with a certain preview time. The vehicle's longitudinal control error is obtained by comparing the vehicle's predicted state with the current state. The error value is calculated and output by the position PID and the speed PID to obtain the acceleration control output value, and then the final output of the acceleration is obtained through acceleration slope compensation and control dead zone acceleration correction. The corresponding accelerator/brake command value is obtained by querying the accelerator/brake calibration table, and the unique brake or accelerator opening is obtained through the accelerator/brake singularity processing. Finally, according to the chassis control protocol, the opening command is periodically sent to the vehicle chassis to control the longitudinal acceleration or deceleration process of the vehicle;

加上安全停车距离时，采用最大开度式紧急制动停车，其中v_车为当前车速，μ为地面摩擦力系数，g为重力加速度。当障碍物距离大于平稳停车所需距离加上安全停车距离时，则采用某一较小的刹车开度进行车辆平稳刹车。当障碍物距离大于极限刹车距离加上安全停车距离且小于平稳停车距离加上安全停车距离时，采用基于时距地安全距离模型进行自车与前车发生碰撞的时间(Time-To-Collision，简称为TTC)分级制动，即当T＞T₁时，无动作，T₂≤T≤T₁时采取某一适中刹车开度进行部分制动，T＜T₂时进行最大刹车开度的完全制动，其中T＝(d-d0)/V，d为障碍物距离，d0为安全停车距离，V为车辆速度，T₁、T₂和车辆平稳刹车开度值和部分制动刹车开度值由实车测试获得。A segmented pressure brake control method is established. When the distance to the first obstacle in front of the vehicle is less than the limit braking distance

When the safe stopping distance is added, the maximum opening emergency brake is used to stop, where v is the current speed _{of the vehicle} , μ is the ground friction coefficient, and g is the acceleration of gravity. When the obstacle distance is greater than the distance required for smooth parking plus the safe parking distance, a smaller brake opening is used to brake the vehicle smoothly. When the obstacle distance is greater than the limit braking distance plus the safe stopping distance and less than the stable stopping distance plus the safe stopping distance, the time-to-collision time between the self-vehicle and the preceding vehicle is calculated using the time-to-ground safe distance model (Time-To-Collision, Abbreviated as TTC) graded braking, that is, when T>T ₁ , there is no action, when T ₂ ≤ T ≤ _{T 1} , a moderate brake opening is used for partial braking, and when T<T ₂ , the maximum brake opening is used. Full braking, where T=(d-d0)/V, d is the obstacle distance, d0 is the safe stopping distance, V is the vehicle speed, T ₁ , T ₂ and the vehicle's smooth brake opening value and partial braking brake opening The values are obtained from real vehicle tests.

A vehicle control method for emergency braking and parking is established. First, the planning module outputs the final emergency braking planning trajectory with the maximum braking deceleration value and the minimum planning trajectory displacement as constraints, and then judges the distance S between the vehicle and the _obstacle in front, the minimum safe distance S after parking _{, and} the emergency braking planning trajectory The relationship between the final displacement and S _gauge , if the S _obstacle > S _gauge + S _safety , the control module adopts emergency braking to stop according to the planned trajectory, otherwise, adopts segmental pressure type emergency braking to stop.

Optionally, controlling the self-driving vehicle to perform non-emergency braking includes: acquiring first driving information of the self-driving vehicle, wherein the driving information includes: chassis state information, vehicle positioning information, and a first obstacle in front of the self-driving vehicle object information and navigation route information; based on the first driving information and the historical planning trajectory of the autonomous vehicle, generate the vehicle trajectory of the autonomous vehicle in the future; maximize the vehicle trajectory, and calculate the deceleration of the autonomous vehicle Minimize to obtain the second emergency braking trajectory of the autonomous vehicle; based on the second emergency braking trajectory, the autonomous vehicle is controlled to brake.

Among them, the chassis state information can be normal or abnormal, the vehicle positioning information can be the current specific positioning of the vehicle, the first obstacle information can be the perceived obstacle information in front of the vehicle, the navigation route information can be the specific route of the vehicle navigation, historical planning The trajectory can be the historical braking planning trajectory of the vehicle, the emergency braking system can be the way to control the vehicle to perform emergency braking, and the second emergency braking trajectory can be the braking trajectory after re-planning the vehicle's driving trajectory and deceleration.

In an optional embodiment, the first driving information of the self-driving vehicle may be acquired through devices such as sensors and positioning systems.

Specifically, controlling the self-driving vehicle to perform non-emergency braking may include: first, the planning module outputs the final emergency braking planning trajectory with the maximum planned trajectory displacement and the minimum braking deceleration value as constraints, and then the control module controls the vehicle Perform non-emergency braking along the planned trajectory.

Optionally, controlling the self-driving vehicle to pull over to stop includes: acquiring second driving information of the self-driving vehicle, wherein the second driving information includes: lateral displacement, velocity and acceleration; performing trajectory estimation on the self-driving vehicle based on the second driving information combined to obtain the motion trajectory of the autonomous vehicle; obtain the perception information of the autonomous vehicle, wherein the perception information includes: the second obstacle information in the lateral direction, and the lane line information around the autonomous vehicle; based on the perception information and the motion trajectory , control the self-driving vehicle to pull over and stop.

Wherein, the second obstacle information may be the position and size of the perceived obstacle in the lateral direction of the vehicle, etc., and the lane line information may be the number and specific position of the lane lines.

In an optional embodiment, the second driving information of the self-driving vehicle may be acquired through a displacement sensor, a speed sensor and an acceleration sensor.

Specifically, controlling the self-driving vehicle to pull over and stop may include: the planning module, according to the vehicle kinematics model, uses five The degree polynomial fits its longitudinal trajectory y(t) and lateral trajectory x(y), where the longitudinal trajectory y(t) is a function of time, and the lateral trajectory x(y) is a function of longitudinal displacement, which is determined by the vehicle determined by the kinematic model. Then convert the horizontal trajectory x(y) to a function x[y(t)] of time to obtain the vehicle's horizontal and vertical time domain motion trajectory;

Call the horizontal and vertical controllers of the control module to control the vehicle to pull over and park along the planned trajectory. In this process, the obstacle information on the side of the vehicle needs to be introduced. Track driving. If there is an obstacle, use the time distance-based safety distance model to calculate the TTC value from the obstacle to the lateral trajectory control point. If the TTC value is greater than the relative time of the lateral trajectory control point, the vehicle is normally controlled to drive along the planned trajectory. If the TTC value is less than is equal to the relative time of the control point of the lateral trajectory, and the change trend gradually decreases, the lateral controller sends the lane keeping signal;

The planning module receives the lane keeping signal, and actively requests the lane centerline information of a certain distance before and after the current vehicle lane from the high-precision map data service. If the request fails to respond, the vehicle perceives the left and right lane line information of the current lane where the vehicle is located to form the lane center line information. Using the lane centerline information as a reference line, generate a constant-speed driving trajectory along the reference line, and at the same time, the control module controls the vehicle to drive along the trajectory;

When the TTC value of the obstacle on the side of the side that the vehicle perceives is greater than a certain threshold and the change trend gradually increases, the vehicle will re-execute the side-by-side parking task.

Specifically, the above method further includes: establishing a vehicle control method for parking at a nearby station. The planning module first obtains the preset necessary point on the navigation route closest to the current position of the vehicle as the end point of this planning. If there is no necessary point, the end point of the navigation route is used as the end point of the planned trajectory. The parking track of the point, and then the control module controls the vehicle to brake along the track.

Establish a vehicle control method for parking after the execution of this scheduling task. First, obtain the execution status of the current planning task by the planning module. If the task is still being executed, the control module will control the vehicle to drive along the planned trajectory of the current planning task. If the planning module has completed the task, the planning module will use the vehicle The non-traveled route with a fixed distance along the navigation route is used as a reference line to plan the vehicle braking trajectory, and then the control module controls the vehicle to brake along the trajectory.

Establish a speed limit vehicle control method. The speed limit of the vehicle is to consider the speed control of the vehicle under the condition of normal driving along the navigation route, that is, the speed value in the speed data of the vehicle along the reference line in the planning module becomes a constant value, the displacement increases at a uniform speed with time, and the acceleration and jerk are Zero, the planning module outputs the vehicle's constant speed trajectory along the navigation route, and then the control module controls the vehicle to drive at a speed limit along the planned trajectory.

A vehicle control method for keeping the vehicle in a parking state and waiting is established. When the vehicle is in a stopped state, if an abnormality is found through system status monitoring, the driving mode of the vehicle is kept in the locked state of the emergency mode, the vehicle is in the parking state and locked, and when the system abnormality disappears, the locked state of the vehicle is canceled.

Establish an intermediate state machine for vehicle mode task switching. When the automatic driving system finds an abnormality and performs degraded operation, the state machine selects the corresponding vehicle control method according to the severity level of the fault to control the vehicle to brake and stop. At the same time, during the execution of a certain vehicle control task, when a more serious fault type occurs and a more urgent vehicle control task needs to be performed, the state machine performs task switching and calls the matching trajectory planning method and vehicle control method. Generate automatic driving control commands and send them to the vehicle chassis to control the vehicle to perform corresponding actions.

Fig. 2 is a schematic diagram of an automatic driving vehicle degraded operation system according to an embodiment of the present invention. As shown in Fig. 2, the device mainly includes: a state data receiving module, which is used to obtain state information of key domain controllers connected to the system , ECU state information to which the domain controller belongs, sensor state information to which the domain controller belongs, and data bus communication state information. The module gives priority to obtaining key domain controllers and bus communication status information. Only when the key domain controller is abnormal, will it receive and filter the ECU status information under the abnormal domain controller and the sensor status information connected to it. Among them, the domain controller Abnormal status includes ECU failure and sensor failure, and abnormal bus communication status includes communication terminals, communication delays, and network attacks.

The fault diagnosis and classification module is used to perform corresponding fault severity evaluation and classification according to the specific abnormal types of each key domain controller or data bus communication abnormal type, and output the highest fault severity level and corresponding abnormal type fault codes. When assessing and grading the faults of critical domain controllers, the operating status of their redundant backup domain controllers is also considered. Only when all controllers in the corresponding functional domain are abnormal, the severity of faults in this functional domain will be evaluated more effectively. High, otherwise the severity of the fault is low, and the fault level can be divided into nine fault levels from E0 to E8.

The vehicle control module is used to execute a specific vehicle control method and fault alarm method according to the highest fault severity level and fault code output by the fault diagnosis and classification module, combined with the degraded operation strategy of the self-driving vehicle, generate a vehicle control command, and send it to the vehicle wire control Chassis, to control the vehicle to perform corresponding actions, including controlling the vehicle to perform emergency braking through the task state machine (graded pressure emergency braking and emergency braking along the planned trajectory), non-emergency braking, parking by the side, parking at the nearest station, and stopping after execution In this dispatching task, stop, drive at a speed limit, keep in a parked state, and only provide fault prompts. Then, the lateral controller and longitudinal controller of the trajectory planner control the vehicle's drive-by-wire chassis.

Example 2

According to another aspect of the embodiments of the present invention, there is also provided a control system for an automatic driving vehicle, which can execute the control method for the automatic driving vehicle in the above-mentioned embodiment 1, the specific implementation scheme and application scenarios in this embodiment It is the same as the above-mentioned embodiment 1, and will not be repeated here.

Fig. 3 is a schematic diagram of a control system of an automatic driving vehicle according to an embodiment of the present invention. As shown in Fig. 3 , the system includes: a state data receiving module 302, which is used to obtain abnormal state information of the automatic driving vehicle, wherein the abnormal The state information includes: the first state information used to characterize the abnormality of the domain controller in the self-driving vehicle, and the second state information used to represent the abnormality of the communication state of the self-driving vehicle; the fault diagnosis classification module 304 is used to Abnormal state information, determine the abnormal type of the self-driving vehicle, and determine the fault level corresponding to the abnormal type, where the abnormal type includes: the first abnormal type of the domain controller and the second abnormal type of the data transmission bus, and the fault level is used to represent The impact degree of the abnormal type on the normal driving of the automatic driving vehicle; the vehicle control module 306 is used to control the operation of the automatic driving vehicle based on the preset control scheme corresponding to the fault level.

The status data receiving module 302 includes: a first acquiring unit, configured to acquire the current status information sent by the domain controller and the failure information of the electronic device corresponding to the domain controller in response to an abnormality of the domain controller, to obtain first status information; The second acquiring unit is configured to acquire data transmission status information of the data transmission bus to obtain second status information.

The fault diagnosis classification module 304 includes: a type matching unit, which is used to match the abnormal type with a plurality of preset abnormal types, and obtains a target abnormal type that matches successfully with the abnormal type; Let the class be the failure class.

In response to the failure of matching the abnormality type with multiple preset abnormality types, the fault diagnosis classification module 304 also includes: a cause acquisition unit, configured to obtain the fault cause corresponding to the fault type; a fault evaluation unit, configured to evaluate the fault cause and obtain the fault The corresponding failure level of the type.

The vehicle control module 306 includes: a power control unit, which is used to control the disconnection of the power supply of the self-driving vehicle; a first brake control unit, which is used to control the self-driving vehicle to perform emergency braking; a second brake control unit, which is used to control the automatic Driving the vehicle for non-emergency braking; the first parking control unit is used to control the self-driving vehicle to pull over to stop; the second parking control unit is used to control the self-driving vehicle to drive to the target stop point to stop; the third parking control unit is used to After controlling the self-driving vehicle to complete the current scheduling task, drive to the second stop and stop; the speed control unit is used to control the speed of the self-driving vehicle to be less than a preset value; the vehicle state control unit is used to control the self-driving vehicle to maintain a stationary state ; An information output unit, configured to control the automatic driving vehicle to output warning information, wherein the warning information is used to indicate that the automatic driving vehicle is abnormal.

The first brake control unit includes: a first acquisition subunit, configured to acquire first driving information of the self-driving vehicle, wherein the first driving information includes: chassis state information, vehicle positioning information, and a first obstacle located in front of the self-driving vehicle object information and navigation route information; the first generating subunit is used to generate the vehicle driving trajectory of the automatic driving vehicle at a future moment based on the first driving information and the historical planning trajectory of the automatic driving vehicle; the system determination subunit is used to generate the vehicle driving trajectory based on the first driving information Obstacle information and vehicle trajectory to determine the emergency braking system of the self-driving vehicle, wherein different emergency braking systems are used to brake the self-driving vehicle in different braking methods; the first control subunit is used to The automatic driving vehicle is controlled to brake based on the emergency braking mode.

The standard determination subunit can be realized by the following steps: minimizing the vehicle trajectory, and maximizing the deceleration of the self-driving vehicle to obtain the first emergency braking trajectory of the self-driving vehicle; obtaining the displacement of the first emergency braking trajectory and the sum of the parking safety distance of the self-driving vehicle to obtain a preset distance; in response to the obstacle distance in the obstacle information being greater than the preset distance, it is determined that the emergency braking mode is the first braking mode, wherein the first braking mode It is used to control the automatic driving vehicle to brake according to the driving track of the vehicle; in response to the obstacle distance being less than or equal to the preset distance, it is determined that the emergency braking mode is the second braking mode, wherein the second braking mode is used to control the automatic driving The brake pedal of the vehicle brakes according to several different opening degrees.

The second braking control unit includes: a second acquiring subunit, configured to acquire first driving information of the self-driving vehicle, wherein the driving information includes: chassis state information, vehicle positioning information, and first obstacle information in front of the self-driving vehicle and navigation route information; the second generation subunit is used to generate the vehicle driving trajectory of the automatic driving vehicle at a future moment based on the first driving information and the historical planning trajectory of the automatic driving vehicle; the first trajectory acquisition subunit is used for the vehicle The driving trajectory is maximized, and the deceleration of the automatic driving vehicle is minimized to obtain the second emergency braking trajectory of the automatic driving vehicle; the second control subunit is used to control the automatic driving vehicle to perform braking based on the second emergency braking trajectory. move.

The first parking control unit includes: a fourth acquisition subunit, used to acquire the second driving information of the self-driving vehicle, wherein the second driving information includes: lateral displacement, speed and acceleration; The second driving information performs trajectory fitting on the self-driving vehicle to obtain the motion trajectory of the self-driving vehicle; the perception information acquisition subunit is used to obtain the perception information of the self-driving vehicle, wherein the perception information includes: the second obstacle in the lateral direction object information, and lane line information around the self-driving vehicle; the third control subunit is used to control the self-driving vehicle to pull over and stop based on the perception information and motion trajectory.

The above device also includes: a level determination module, used to determine a target failure level in the failure level, wherein the target failure level is higher than other failure levels in the failure level; a scheme acquisition module, used to obtain the control scheme corresponding to the target failure level, Get the preset control scheme.

Example 3

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, and the computer-readable storage medium includes a stored program, wherein, when the program is running, the device where the computer-readable storage medium is located is controlled to execute the above automatic driving vehicle. control method.

Example 4

According to another aspect of the embodiments of the present invention, a processor is also provided, and the processor is used to run a program, wherein the above method for controlling an automatic driving vehicle is executed when the program is running.

The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

In the above-mentioned embodiments of the present invention, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be realized in other ways. Wherein, the device embodiments described above are only illustrative. For example, the division of the units may be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or may be Integrate into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of units or modules may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes. .

The above is only a preferred embodiment of the present invention, it should be pointed out that, for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications can also be made. It should be regarded as the protection scope of the present invention.

Claims (13)

1. A control method of an autonomous vehicle, characterized by comprising:

obtaining abnormal state information of the automatic driving vehicle, wherein the abnormal state information comprises: first state information for representing that abnormality occurs in a domain controller in the autonomous vehicle, and second state information for representing that abnormality occurs in a communication state of the autonomous vehicle;

determining an anomaly type of the autonomous vehicle based on the anomaly status information, wherein the anomaly type comprises: a first exception type of the domain controller and a second exception type of the data transfer bus;

determining a fault grade corresponding to the abnormal type, wherein the fault grade is used for representing the influence degree of the abnormal type on the normal running of the automatic driving vehicle;

and controlling the operation of the automatic driving vehicle based on a preset control scheme corresponding to the fault level.

2. The method of claim 1, wherein obtaining abnormal state information of the autonomous vehicle comprises:

responding to the occurrence of abnormality of the domain controller, acquiring current state information sent by the domain controller and fault information of an electronic device corresponding to the domain controller, and obtaining the first state information;

and acquiring data transmission state information of the data transmission bus to obtain the second state information.

3. The method of claim 1, wherein determining the fault level for the anomaly type comprises:

matching the anomaly type with a plurality of preset anomaly types to obtain a target anomaly type successfully matched with the anomaly type;

and determining a preset grade corresponding to the target abnormal type as the fault grade.

4. A method according to claim 3, wherein in response to the anomaly type failing to match a plurality of preset anomaly types, the method further comprises:

acquiring a fault reason corresponding to the fault type;

and evaluating the fault reasons to obtain fault grades corresponding to the fault types.

5. The method according to claim 1, wherein the method further comprises:

Determining a target fault level in the fault levels, wherein the target fault level is higher than other fault levels in the fault levels;

and obtaining a control scheme corresponding to the target fault level to obtain the preset control scheme.

6. The method of claim 1, wherein controlling the autonomous vehicle operation based on the preset control scheme corresponding to the fault level comprises one of:

controlling a power supply disconnection of the autonomous vehicle;

controlling the automatic driving vehicle to perform emergency braking;

controlling the automatic driving vehicle to perform non-emergency braking;

controlling the automatic driving vehicle to stop by side;

controlling the automatic driving vehicle to run to a target stop point for stopping;

after the automatic driving vehicle is controlled to finish the current dispatching task, the automatic driving vehicle is driven to a second stopping point for stopping;

controlling the speed of the automatic driving vehicle to be smaller than a preset value;

controlling the autonomous vehicle to remain stationary;

and controlling the automatic driving vehicle to output alarm information, wherein the alarm information is used for representing that the automatic driving vehicle is abnormal.

7. The method of claim 5, wherein controlling the autonomous vehicle to perform emergency braking comprises:

Acquiring first driving information of the automatic driving vehicle, wherein the first driving information comprises: chassis state information, vehicle positioning information, first obstacle information located in front of the autonomous vehicle, and navigation route information;

generating a vehicle travel track of the autonomous vehicle at a future time based on the first travel information and the historical planned track of the autonomous vehicle;

determining an emergency braking system of the automatic driving vehicle based on the first obstacle information and the vehicle running track, wherein different emergency braking systems are used for braking the automatic driving vehicle in different braking modes;

and controlling the automatic driving vehicle to brake based on the emergency braking mode.

8. The method of claim 6, wherein determining an emergency braking regime of the autonomous vehicle based on the first obstacle information and the vehicle travel trajectory comprises:

minimizing the vehicle running track and maximizing the deceleration of the automatic driving vehicle to obtain a first emergency braking track of the automatic driving vehicle;

Obtaining the sum of the displacement of the first emergency braking track and the parking safety distance of the automatic driving vehicle to obtain a preset distance;

determining the emergency braking mode to be a first braking mode in response to the obstacle distance in the obstacle information being greater than the preset distance, wherein the first braking mode is used for controlling the automatic driving vehicle to brake according to the vehicle running track;

and determining the emergency braking mode to be a second braking mode in response to the obstacle distance being smaller than or equal to the preset distance, wherein the second braking mode is used for controlling a brake pedal of the automatic driving vehicle to brake according to a plurality of different opening degrees.

9. The method of claim 5, wherein controlling the autonomous vehicle to perform non-emergency braking comprises:

acquiring first driving information of the automatic driving vehicle, wherein the driving information comprises: chassis state information, vehicle positioning information, first obstacle information located in front of the autonomous vehicle, and navigation route information;

generating a vehicle travel track of the autonomous vehicle at a future time based on the first travel information and the historical planned track of the autonomous vehicle;

Maximizing the vehicle driving track and minimizing the deceleration of the automatic driving vehicle to obtain a second emergency braking track of the automatic driving vehicle;

and controlling the automatic driving vehicle to brake based on the second emergency braking track.

10. The method of claim 5, wherein controlling the autonomous vehicle to park alongside comprises:

acquiring second driving information of the automatic driving vehicle, wherein the second driving information comprises: lateral displacement, velocity and acceleration;

performing track fitting on the automatic driving vehicle based on the second driving information to obtain a motion track of the automatic driving vehicle;

obtaining perception information of the automatic driving vehicle, wherein the perception information comprises: second obstacle information in a lateral direction and lane line information around the autonomous vehicle;

and controlling the automatic driving vehicle to stop by side based on the perception information and the motion trail.

11. A control system for an autonomous vehicle, comprising:

the state data receiving module is used for acquiring abnormal state information of the automatic driving vehicle, wherein the abnormal state information comprises: first state information for representing that abnormality occurs in a domain controller in the autonomous vehicle, and second state information for representing that abnormality occurs in a communication state of the autonomous vehicle;

The fault diagnosis grading module is used for determining the abnormal type of the automatic driving vehicle based on the abnormal state information and determining a fault grade corresponding to the abnormal type, wherein the abnormal type comprises the following components: the first abnormality type of the domain controller and the second abnormality type of the data transmission bus, the fault level being used to characterize the degree of influence of the abnormality type on the normal running of the autonomous vehicle;

and the vehicle control module is used for controlling the automatic driving vehicle to run based on a preset control scheme corresponding to the fault level.

12. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1 to 10.

13. A processor for running a program, wherein the program when run performs the method of any one of claims 1 to 10.

Images