Safety control method and safety control device for autonomous driving vehicle

Abstract

The present application relates to artificial intelligence, and provides a safety control method and safety control device for an autonomous driving vehicle, the safety control method comprising obtaining motion planning trajectory information of the autonomous driving vehicle, the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located; obtaining the predicted vehicle posture of the autonomous driving vehicle according to the motion planning trajectory information and the motion controller of the autonomous driving vehicle, the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predicting the collision detection result according to the predicted vehicle posture and obstacle information, the collision detection result is used to indicate whether the autonomous driving vehicle will collide with the obstacle, and the obstacle information is used to indicate the obstacle; and correcting the motion planning trajectory information when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle. The scheme of the present application can improve the accuracy of predicting the vehicle posture.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to a safety control method and a safety control device for an autonomous driving vehicle. Background Art

[0002] Artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making. Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, basic AI theory, etc.

[0003] Autonomous driving is a mainstream application in the field of artificial intelligence. Autonomous driving technology relies on the collaboration of computer vision, radar, monitoring devices and global positioning systems to enable motor vehicles to achieve autonomous driving without the need for active human operation. Autonomous vehicles use various computing systems to help transport passengers from one location to another; some autonomous vehicles may require some initial or continuous input from operators (such as navigators, drivers, or passengers); autonomous vehicles allow operators to switch from manual mode to autonomous driving mode or a mode in between. Since autonomous driving technology does not require humans to drive motor vehicles, it can theoretically effectively avoid human driving errors, reduce the occurrence of traffic accidents, and improve highway transportation efficiency.

[0004] At present, the planning control module in the autonomous driving vehicle is used to plan the motion planning trajectory of the autonomous driving vehicle. The planning control module believes that the autonomous driving vehicle can avoid the risk of collision with pedestrians on the edge of the road through the motion planning trajectory and drive safely on the road; however, when the autonomous driving vehicle drives according to the motion planning trajectory, the lower-level vehicle actuator may have execution errors, which may cause the autonomous driving vehicle to deviate from the motion planning trajectory and collide with pedestrians on the edge of the road. Therefore, how to provide a safety control method for autonomous driving vehicles so that autonomous driving vehicles can drive safely has become an urgent problem to be solved. Summary of the invention

[0005] The present application provides a safety control method and a safety control device for an autonomous driving vehicle, which can improve the accuracy of the predicted vehicle posture of the autonomous driving vehicle, thereby avoiding collision between the autonomous driving vehicle and obstacles.

[0006] In a first aspect, a method for safety control of an autonomous driving vehicle is provided, comprising: obtaining motion planning trajectory information of the autonomous driving vehicle, wherein the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located; obtaining a predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and a motion controller of the autonomous driving vehicle, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predicting a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; and correcting the motion planning trajectory information when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle.

[0007] Among them, the above-mentioned motion planning trajectory information may refer to the driving trajectory information of the autonomous driving vehicle obtained by the upper-level motion planning module of the autonomous driving vehicle based on the environmental information around the autonomous driving vehicle.

[0008] It should be understood that the above-mentioned predicted vehicle posture can be the vehicle posture of the autonomous driving vehicle during actual driving predicted based on the motion planning trajectory information and the execution error of the actuator (e.g., motion controller) simulating the autonomous driving vehicle.

[0009] It should also be understood that the above-mentioned motion controller must ensure that the same controller is used when the autonomous driving vehicle is actually driving to ensure the homology of the control links; in this way, the movement of the autonomous driving vehicle in the real scene can be simulated, so as to obtain the error introduced by the motion controller and obtain the predicted driving trajectory of the autonomous driving vehicle based on the motion planning trajectory.

[0010] In one possible implementation, collision detection may be performed based on the predicted vehicle posture of the autonomous driving vehicle and obstacle information in the environmental perception results to obtain a collision detection result; wherein the obstacles may include static obstacles and dynamic obstacles. Static obstacles may refer to obstacles whose positions do not change or rarely change, such as obstacles at rest on the side of the road; dynamic obstacles may refer to obstacles whose positions frequently change, such as moving vehicles or moving pedestrians.

[0011] In an embodiment of the present application, by inputting motion planning trajectory information into the motion controller of the autonomous driving vehicle, the predicted vehicle posture when the autonomous driving vehicle is actually driving based on the motion planning trajectory can be simulated; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at a future moment can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, ensuring the safety of the autonomous driving vehicle during driving, and improving the accuracy of the predicted vehicle posture of the autonomous driving vehicle.

[0012] In combination with the first aspect, in certain implementations of the first aspect, the safety control method also includes: saving vehicle information of the autonomous driving vehicle, wherein the vehicle information includes planned trajectory information of the autonomous driving vehicle in a global coordinate system; obtaining the motion planning trajectory information of the autonomous driving vehicle includes: when it is monitored that the autonomous driving vehicle is in an abnormal state, obtaining the planned trajectory information of the autonomous driving vehicle in the global coordinate system from the saved vehicle information; and performing coordinate conversion on the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain the motion planning trajectory information.

[0013] It should be understood that the above-mentioned autonomous driving vehicle being in an abnormal state may refer to a situation where any one or more components in the autonomous driving vehicle fail. For example, it may refer to a failure in the computing platform of the autonomous driving vehicle, or it may refer to an abnormality in some sensors of the autonomous driving vehicle.

[0014] In one possible implementation, when the autonomous driving vehicle is in a normal state, important information output by the upper-level planning module or sensor can be saved to generate cache data, such as recording environmental perception results, vehicle information, and motion planning results.

[0015] In one possible implementation, when the autonomous driving vehicle is in an abnormal state, it may be impossible to obtain information output by the upper-level planning module or sensor system of the autonomous driving vehicle. In this case, data can be called from the cached data to plan and control the autonomous driving vehicle.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the vehicle information also includes driving position information of the autonomous driving vehicle, and the safety control method further includes: when it is monitored that the autonomous driving vehicle is in an abnormal state, obtaining the positioning information of the autonomous driving vehicle at a current moment according to the driving position information, the state information of the autonomous driving vehicle and the dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the speed of the autonomous driving vehicle at a current moment and the steering wheel angle at a current moment; the coordinate transformation according to the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain the motion planning trajectory information includes: obtaining the motion planning trajectory information according to the positioning information of the autonomous driving vehicle at a current moment and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

[0017] Among them, the above-mentioned abnormal situation of the autonomous driving vehicle may refer to an abnormality of the positioning module in the autonomous driving vehicle, that is, the autonomous driving vehicle cannot obtain the vehicle's positioning information in real time.

[0018] In one possible implementation, the vehicle positioning can be performed based on a dead reckoning algorithm. For example, the positioning information of the autonomous driving vehicle at the current moment can be obtained according to the following formula:

[0019]

[0020] Among them, x k and k can represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the kth moment, x0 and y0 can represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the starting moment, S i represents the distance the autonomous driving vehicle travels in the i-th sampling period, θ i It represents the angle between the forward direction of the autonomous driving vehicle and the x-axis direction of the ground coordinate system in the i-th sampling period.

[0021] In an embodiment of the present application, when an abnormal state of an autonomous driving vehicle is monitored, the cached data can be quickly called and the current positioning information of the autonomous driving vehicle can be obtained through a dead reckoning algorithm. Then, based on the positioning information, the trajectory information of the autonomous driving vehicle in the global coordinate system obtained from the cached data is converted into trajectory information in the local coordinate system, that is, trajectory information in the coordinate system where the autonomous driving vehicle is located; thereby avoiding the problem that the autonomous driving vehicle cannot correctly plan its path when it is in an abnormal state, causing the autonomous driving vehicle to drive out of the target road or lane and cause a traffic accident, thereby improving the safety of the autonomous driving vehicle during driving.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the predicted vehicle posture of the autonomous driving vehicle is obtained based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle, including: inputting the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain control instructions, wherein the control instructions are used to instruct the adjustment of the steering wheel control amount, throttle control amount and brake control amount of the autonomous driving vehicle; and inputting the control instructions into the vehicle dynamics model to obtain the predicted vehicle posture.

[0023] In one possible implementation, the motion planning trajectory information may be input into a lateral controller of an autonomous driving vehicle to obtain a control instruction for adjusting the steering wheel control amount of the autonomous driving vehicle; the motion planning trajectory information may be input into a longitudinal controller of the autonomous driving vehicle to obtain a control instruction for adjusting the throttle control amount and the brake control amount of the autonomous driving vehicle.

[0024] It should be noted that the lateral controller and the longitudinal controller must ensure that the same lateral controller and the longitudinal controller are used when the autonomous driving vehicle is actually driving to ensure the homology of the control links; in this way, the movement of the autonomous driving vehicle in the real scene can be simulated, so as to obtain the error introduced by the motion control and accurately predict the vehicle posture of the autonomous driving vehicle.

[0025] In an embodiment of the present application, by inputting the motion planning trajectory information into the lateral controller and longitudinal controller of the autonomous driving vehicle, the execution error of the autonomous driving vehicle when actually driving based on the motion planning trajectory can be simulated, thereby obtaining the motion parameters of the autonomous driving vehicle, and the predicted vehicle posture of the autonomous driving vehicle can be obtained based on the motion parameters; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at future moments can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, and ensuring the safety of the autonomous driving vehicle during driving.

[0026] In combination with the first aspect, in certain implementations of the first aspect, when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correcting the motion planning trajectory includes: when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correcting the motion planning trajectory information according to the vehicle posture when the autonomous driving vehicle is about to collide with the obstacle.

[0027] In one possible implementation, if it is detected that there is a risk of collision between the predicted vehicle position of the autonomous driving vehicle and an obstacle, the possible collision time and collision position can be recorded, and a dangerous virtual wall can be generated; wherein the virtual wall can be an abstract representation of inaccessible areas such as the vehicle ahead, the end point, and the red light stop line, indicating that the autonomous driving vehicle is not allowed to pass through here, so that the autonomous driving vehicle can slow down or even stop to avoid obstacles that may collide.

[0028] In an embodiment of the present application, when the collision detection result obtained by performing collision detection on the autonomous driving vehicle and the obstacle information is that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory of the autonomous driving vehicle can be corrected according to the vehicle posture when the autonomous driving vehicle collides with the obstacle, so that the autonomous driving vehicle can avoid the obstacle and avoid collision with the obstacle, thereby improving the safety of the autonomous driving vehicle during driving.

[0029] In a second aspect, a safety control device for an autonomous driving vehicle is provided, comprising: an acquisition unit, for acquiring motion planning trajectory information of the autonomous driving vehicle, wherein the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located; a processing unit, for obtaining a predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and a motion controller of the autonomous driving vehicle, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predicting a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; and correcting the motion planning trajectory information when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle.

[0030] Exemplarily, the safety control device of the above-mentioned autonomous driving vehicle may be an on-board device in the autonomous driving vehicle, or may be a chip configured in the on-board device of the autonomous driving vehicle.

[0031] Among them, the above-mentioned motion planning trajectory information may refer to the driving trajectory information of the autonomous driving vehicle obtained by the upper-level motion planning module of the autonomous driving vehicle based on the environmental information around the autonomous driving vehicle.

[0032] It should be understood that the above-mentioned predicted vehicle posture can be the vehicle posture of the autonomous driving vehicle during actual driving predicted based on the motion planning trajectory information and the execution error of the actuator (e.g., motion controller) simulating the autonomous driving vehicle.

[0033] It should also be understood that the above-mentioned motion controller must ensure that the same controller is used when the autonomous driving vehicle is actually driving to ensure the homology of the control links; in this way, the movement of the autonomous driving vehicle in the real scene can be simulated, so as to obtain the error introduced by the motion controller and obtain the predicted driving trajectory of the autonomous driving vehicle based on the motion planning trajectory.

[0034] In one possible implementation, collision detection may be performed based on the predicted vehicle posture of the autonomous driving vehicle and obstacle information in the environmental perception results to obtain a collision detection result; wherein the obstacles may include static obstacles and dynamic obstacles. Static obstacles may refer to obstacles whose positions do not change or rarely change, such as obstacles at rest on the side of the road; dynamic obstacles may refer to obstacles whose positions frequently change, such as moving vehicles or moving pedestrians.

[0035] In an embodiment of the present application, by inputting motion planning trajectory information into the motion controller of the autonomous driving vehicle, the predicted vehicle posture when the autonomous driving vehicle is actually driving based on the motion planning trajectory can be simulated; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at a future moment can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, ensuring the safety of the autonomous driving vehicle during driving, and improving the accuracy of the predicted vehicle posture of the autonomous driving vehicle.

[0036] In combination with the second aspect, in certain implementations of the second aspect, the processing unit is further used to: save vehicle information of the autonomous driving vehicle, wherein the vehicle information includes planned trajectory information of the autonomous driving vehicle in a global coordinate system; the acquisition unit is specifically used to: when it is monitored that the autonomous driving vehicle is in an abnormal state, obtain the planned trajectory information of the autonomous driving vehicle in the global coordinate system from the saved vehicle information; and perform coordinate system conversion on the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain the motion planning trajectory information.

[0037] It should be understood that the above-mentioned autonomous driving vehicle being in an abnormal state may refer to a situation where any one or more components in the autonomous driving vehicle fail. For example, it may refer to a failure in the computing platform of the autonomous driving vehicle, or it may refer to an abnormality in some sensors of the autonomous driving vehicle.

[0038] In one possible implementation, when the autonomous driving vehicle is in a normal state, important information output by the upper-level planning module or sensor can be saved to generate cache data, such as recording environmental perception results, vehicle information, and motion planning results.

[0039] In one possible implementation, when the autonomous driving vehicle is in an abnormal state, it may be impossible to obtain information output by the upper-level planning module or sensor system of the autonomous driving vehicle. In this case, data can be called from the cached data to plan and control the autonomous driving vehicle.

[0040] In combination with the second aspect, in certain implementations of the second aspect, the vehicle information also includes driving position information of the autonomous driving vehicle, and the processing unit is further used to: when it is monitored that the autonomous driving vehicle is in an abnormal state, obtain the positioning information of the autonomous driving vehicle at a current moment according to the driving position information, the state information of the autonomous driving vehicle and the dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the speed of the autonomous driving vehicle at a current moment, the steering wheel angle at a current moment, the throttle control amount at a current moment and the brake control amount at a current moment; the acquisition unit is specifically used to: obtain the motion planning trajectory information according to the positioning information of the autonomous driving vehicle at a current moment and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

[0041] Among them, the above-mentioned abnormal situation of the autonomous driving vehicle may refer to an abnormality of the positioning module in the autonomous driving vehicle, that is, the autonomous driving vehicle cannot obtain the vehicle's positioning information in real time.

[0042] In one possible implementation, the vehicle positioning can be performed based on a dead reckoning algorithm. For example, the positioning information of the autonomous driving vehicle at the current moment can be obtained according to the following formula:

[0043]

[0044] Among them, x k and k can represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the kth moment, x0 and y0 can represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the starting moment, S i represents the distance the autonomous driving vehicle travels in the i-th sampling period, θ i It represents the angle between the forward direction of the autonomous driving vehicle and the x-axis direction of the ground coordinate system in the i-th sampling period.

[0045] In an embodiment of the present application, when an autonomous driving vehicle is in an abnormal state, the cached data can be quickly called and the current positioning information of the autonomous driving vehicle can be obtained through a dead reckoning algorithm. Then, based on the positioning information, the trajectory information of the autonomous driving vehicle in the global coordinate system obtained from the cached data is converted into trajectory information in the local coordinate system, that is, trajectory information in the coordinate system where the autonomous driving vehicle is located; thereby avoiding the problem that the autonomous driving vehicle cannot correctly plan its path when it is in an abnormal state, causing the autonomous driving vehicle to drive out of the target road or lane and cause a traffic accident, thereby improving the safety of the autonomous driving vehicle during driving.

[0046] In combination with the second aspect, in certain implementations of the second aspect, the predicted vehicle posture of the autonomous driving vehicle is obtained based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle, including: inputting the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain control instructions, wherein the control instructions are used to instruct the adjustment of the steering wheel control amount, throttle control amount and brake control amount of the autonomous driving vehicle; inputting the control instructions into the vehicle dynamics model to obtain the predicted vehicle posture.

[0047] In one possible implementation, the motion planning trajectory information may be input into a lateral controller of an autonomous driving vehicle to obtain a control instruction for adjusting the steering wheel control amount of the autonomous driving vehicle; the motion planning trajectory information may be input into a longitudinal controller of the autonomous driving vehicle to obtain a control instruction for adjusting the throttle control amount and the brake control amount of the autonomous driving vehicle.

[0048] It should be noted that the lateral controller and the longitudinal controller must ensure that the same lateral controller and the longitudinal controller are used when the autonomous driving vehicle is actually driving to ensure the homology of the control links; in this way, the movement of the autonomous driving vehicle in the real scene can be simulated, so as to obtain the error introduced by the motion control and accurately predict the vehicle posture of the autonomous driving vehicle.

[0049] In an embodiment of the present application, by inputting the motion planning trajectory information into the lateral controller and longitudinal controller of the autonomous driving vehicle, the execution error of the autonomous driving vehicle when actually driving based on the motion planning trajectory can be simulated, thereby obtaining the motion parameters of the autonomous driving vehicle, and the predicted vehicle posture of the autonomous driving vehicle can be obtained based on the motion parameters; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at future moments can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, and ensuring the safety of the autonomous driving vehicle during driving.

[0050] In combination with the second aspect, in certain implementations of the second aspect, when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correcting the motion planning trajectory includes: when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correcting the motion planning trajectory information according to the vehicle posture when the autonomous driving vehicle is about to collide with the obstacle.

[0051] In one possible implementation, if it is detected that there is a risk of collision between the predicted vehicle position of the autonomous driving vehicle and an obstacle, the possible collision time and collision position can be recorded, and a dangerous virtual wall can be generated; wherein the virtual wall can be an abstract representation of inaccessible areas such as the vehicle ahead, the end point, and the red light stop line, indicating that the autonomous driving vehicle is not allowed to pass through here, so that the autonomous driving vehicle can slow down or even stop to avoid obstacles that may collide.

[0052] In an embodiment of the present application, when the collision detection result obtained by performing collision detection on the autonomous driving vehicle and the obstacle information is that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory of the autonomous driving vehicle can be corrected according to the vehicle posture when the autonomous driving vehicle collides with the obstacle, so that the autonomous driving vehicle can avoid the obstacle and avoid collision with the obstacle, thereby improving the safety of the autonomous driving vehicle during driving.

[0053] In a third aspect, a safety control device for an autonomous driving vehicle is provided, comprising: a memory for storing a program; a processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is used to perform the following process: obtaining motion planning trajectory information of the autonomous driving vehicle, wherein the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located; obtaining a predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and a motion controller of the autonomous driving vehicle, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predicting a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; and correcting the motion planning trajectory information when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle.

[0054] In a possible implementation manner, the processor included in the above-mentioned device is also used to execute the security control method in the first aspect and any one of the implementation manners of the first aspect.

[0055] Optionally, the memory may be located inside the processor, for example, it may be a cache memory in the processor. The memory may also be located outside the processor, thus being independent of the processor.

[0056] It should be understood that the expansion, limitation, explanation and description of the relevant contents in the above-mentioned first aspect also apply to the same contents in the third aspect.

[0057] In a fourth aspect, an autonomous driving vehicle is provided, comprising the safety control device in the above-mentioned second aspect and any one of the implementation methods of the second aspect.

[0058] In a fifth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the security control method in the first aspect and any one of the implementations of the first aspect.

[0059] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or separately packaged with the processor, and the embodiments of the present application do not specifically limit this.

[0060] In a sixth aspect, a computer-readable medium is provided, wherein the computer-readable medium stores a program code, and when the computer program code runs on a computer, the computer executes the security control method in the above-mentioned first aspect and any one of the implementation methods of the first aspect.

[0061] In the seventh aspect, a chip is provided, comprising a processor and a data interface, wherein the processor reads instructions stored in a memory through the data interface to execute the security control method in the above-mentioned first aspect and any one of the implementation methods of the first aspect.

[0062] Optionally, as an implementation method, the chip may also include a memory, in which instructions are stored, and the processor is used to execute the instructions stored in the memory. When the instructions are executed, the processor is used to execute the security control method in the above-mentioned first aspect and any one of the implementation methods of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 is a structural schematic diagram of a vehicle provided in an embodiment of the present application;

[0064] Figure 2 is a schematic diagram of the structure of a computer system provided in an embodiment of the present application;

[0065] Figure 3This is a schematic diagram of an application of a cloud-side commanded autonomous driving vehicle provided in an embodiment of the present application;

[0066] Figure 4 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0067] Figure 5 is a schematic diagram of the system architecture of an autonomous driving vehicle provided in an embodiment of the present application;

[0068] Figure 6 is a schematic diagram of another application scenario provided by an embodiment of the present application;

[0069] Figure 7 is a schematic flow chart of a safety control method for an autonomous driving vehicle provided in an embodiment of the present application;

[0070] Figure 8 is a schematic flow chart of predicting vehicle posture of an autonomous driving vehicle provided in an embodiment of the present application;

[0071] Fig. 9 is a schematic diagram of a predicted vehicle posture of an autonomous driving vehicle provided in an embodiment of the present application;

[0072] Fig.10 is a schematic flow chart of the motion planning trajectory correction of the autonomous driving vehicle provided in the embodiment of the present application;

[0073] Fig.11 This is a schematic diagram of an application scenario of an autonomous driving vehicle performing motion planning trajectory correction provided by an embodiment of the present application;

[0074] Fig.12 is a schematic diagram of a virtual wall provided in an embodiment of the present application;

[0075] Fig.13 is a schematic flow chart of an abnormality handling method for an autonomous driving vehicle provided in an embodiment of the present application;

[0076] Fig.14 is a schematic diagram of collision detection provided by an embodiment of the present application;

[0077] Fig.15 is a schematic block diagram of a safety control device for an autonomous driving vehicle provided in an embodiment of the present application;

[0078] Fig.16 It is a schematic diagram of the hardware structure of the safety control device for the autonomous driving vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0079] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0080] Figure 1 1 is a functional block diagram of a vehicle 100 provided in an embodiment of the present application. The vehicle 100 may be a manually driven vehicle, or the vehicle 100 may be configured to be in a fully or partially automatic driving mode.

[0081] In one example, the vehicle 100 can control itself while in the autonomous driving mode, and can determine the current state of the vehicle and its surrounding environment through human operation, determine the possible behavior of at least one other vehicle in the surrounding environment, and determine the confidence level corresponding to the possibility of the other vehicle performing the possible behavior, and control the vehicle 100 based on the determined information. When the vehicle 100 is in the autonomous driving mode, the vehicle 100 can be set to operate without human interaction.

[0082] Various subsystems may be included in the vehicle 100 , such as a travel system 110 , a sensing system 120 , a control system 130 , one or more peripheral devices 140 , as well as a power source 160 , a computer system 150 , and a user interface 170 .

[0083] Alternatively, the vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple elements. In addition, each subsystem and element of the vehicle 100 may be interconnected by wire or wirelessly.

[0084] Exemplarily, the travel system 110 may include components for providing powered motion to the vehicle 100. In one embodiment, the travel system 110 may include an engine 111, a transmission 112, an energy source 113, and wheels 114 / tires. The engine 111 may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines; for example, a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air compression engine. The engine 111 may convert the energy source 113 into mechanical energy.

[0085] For example, the energy source 113 may include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. The energy source 113 may also provide energy for other systems of the vehicle 100 .

[0086] Exemplarily, the transmission 112 may include a gearbox, a differential, and a drive shaft; wherein the transmission 112 may transmit mechanical power from the engine 111 to the wheels 114 .

[0087] In one embodiment, the transmission 112 may further include other devices, such as a clutch. The drive shaft may include one or more shafts that may be coupled to one or more wheels 114 .

[0088] For example, the sensing system 120 may include several sensors that sense information about the environment surrounding the vehicle 100 .

[0089] For example, the sensing system 120 may include a positioning system 121 (e.g., a GPS system, a BeiDou system, or other positioning systems), an inertial measurement unit 122 (IMU), a radar 123, a laser rangefinder 124, and a camera 125. The sensing system 120 may also include sensors of the internal systems of the monitored vehicle 100 (e.g., an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors may be used to detect objects and their corresponding characteristics (position, shape, direction, speed, etc.). Such detection and recognition are key functions for the safe operation of the autonomous vehicle 100.

[0090] Among them, the positioning system 121 can be used to estimate the geographic location of the vehicle 100. The IMU 122 can be used to sense the position and orientation changes of the vehicle 100 based on inertial acceleration. In one embodiment, the IMU 122 can be a combination of an accelerometer and a gyroscope.

[0091] For example, the radar 123 may utilize radio signals to sense objects within the surrounding environment of the vehicle 100. In some embodiments, in addition to sensing objects, the radar 123 may also be used to sense the speed and / or heading of the object.

[0092] For example, the laser rangefinder 124 may utilize laser light to sense objects in the environment in which the vehicle 100 is located. In some embodiments, the laser rangefinder 124 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components.

[0093] For example, the camera 125 may be used to capture multiple images of the surrounding environment of the vehicle 100. For example, the camera 125 may be a still camera or a video camera.

[0094] like Figure 1As shown, the control system 130 controls the operation of the vehicle 100 and its components. The control system 130 may include various elements, such as a steering system 131 , a throttle 132 , a brake unit 133 , a computer vision system 134 , a route control system 135 , and an obstacle avoidance system 136 .

[0095] For example, the steering system 131 can be operated to adjust the forward direction of the vehicle 100. For example, in one embodiment, it can be a steering wheel system. The throttle 132 can be used to control the operating speed of the engine 111 and thus control the speed of the vehicle 100.

[0096] For example, the brake unit 133 can be used to control the deceleration of the vehicle 100; the brake unit 133 can use friction to slow down the wheel 114. In other embodiments, the brake unit 133 can convert the kinetic energy of the wheel 114 into electric current. The brake unit 133 can also take other forms to slow down the rotation speed of the wheel 114 to control the speed of the vehicle 100.

[0097] like Figure 1 As shown, the computer vision system 134 can be operated to process and analyze the images captured by the camera 125 in order to identify objects and / or features in the surrounding environment of the vehicle 100. The above-mentioned objects and / or features may include traffic signals, road boundaries, and obstacles. The computer vision system 134 may use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system 134 can be used to map the environment, track objects, estimate the speed of objects, and the like.

[0098] For example, the route control system 135 can be used to determine the driving route of the vehicle 100. In some embodiments, the route control system 135 can combine data from sensors, GPS, and one or more predetermined maps to determine the driving route for the vehicle 100.

[0099] like Figure 1 As shown, obstacle avoidance system 136 may be used to identify, assess, and avoid or otherwise negotiate potential obstacles in the environment of vehicle 100 .

[0100] In one example, the control system 130 may include additional or alternative components other than those shown and described, or may also include a portion of the components shown above reduced.

[0101] like Figure 1As shown, the vehicle 100 can interact with external sensors, other vehicles, other computer systems or users through the peripheral device 140; wherein the peripheral device 140 may include a wireless communication system 141, an onboard computer 142, a microphone 143 and / or a speaker 144.

[0102] In some embodiments, the peripheral device 140 can provide a means for the vehicle 100 to interact with the user interface 170. For example, the onboard computer 142 can provide information to the user of the vehicle 100; the user interface 116 can also operate the onboard computer 142 to receive input from the user; the onboard computer 142 can be operated through a touch screen. In other cases, the peripheral device 140 can provide a means for the vehicle 100 to communicate with other devices located in the vehicle. For example, the microphone 143 can receive audio (e.g., voice commands or other audio input) from the user of the vehicle 100. Similarly, the speaker 144 can output audio to the user of the vehicle 100.

[0103] like Figure 1 As described, the wireless communication system 141 can communicate wirelessly with one or more devices directly or via a communication network. For example, the wireless communication system 141 can use 3G cellular communication; for example, code division multiple access (CDMA), EVDO, global system for mobile communications (GSM) / general packet radio service (GPRS), or 4G cellular communication, such as long term evolution (LTE); or, 5G cellular communication. The wireless communication system 141 can communicate with a wireless local area network (WLAN) using wireless Internet access (WiFi).

[0104] In some embodiments, the wireless communication system 141 can communicate directly with the device using an infrared link, Bluetooth, or ZigBee protocol; other wireless protocols, such as various vehicle communication systems, for example, the wireless communication system 141 may include one or more dedicated short range communications (DSRC) devices, which may include public and / or private data communications between vehicles and / or roadside stations.

[0105] like Figure 1As shown, power source 160 can provide power to various components of vehicle 100. In one embodiment, power source 160 can be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such batteries can be configured as a power source to provide power to various components of vehicle 100. In some embodiments, power source 160 and energy source 113 can be implemented together, such as in some all-electric vehicles.

[0106] Exemplarily, some or all functions of the vehicle 100 may be controlled by a computer system 150, which may include at least one processor 151 that executes instructions 153 stored in a non-transitory computer-readable medium such as a memory 152. The computer system 150 may also be a plurality of computing devices that control individual components or subsystems of the vehicle 100 in a distributed manner.

[0107] For example, processor 151 may be any conventional processor, such as a commercially available CPU.

[0108] Alternatively, the processor may be a dedicated device such as an ASIC or other hardware-based processor. Figure 1 Functionally illustrated are processors, memories, and other elements of computers in the same block, but those of ordinary skill in the art will appreciate that the processors, computers, or memories may or may not actually include multiple processors, computers, or memories that may or may not be stored in the same physical housing. For example, the memory may be a hard drive or other storage medium that is located in a housing different from the computer. Therefore, references to processors or computers will be understood to include references to a collection of processors or computers or memories that may or may not operate in parallel. Different from using a single processor to perform the steps described herein, some components such as steering components and deceleration components may each have their own processors that only perform calculations related to component-specific functions.

[0109] In various aspects described herein, the processor may be located remote from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle and others are performed by a remote processor, including taking the necessary steps to perform a single maneuver.

[0110] In some embodiments, the memory 152 may include instructions 153 (e.g., program logic) that may be executed by the processor 151 to perform various functions of the vehicle 100, including those described above. The memory 152 may also include additional instructions, such as instructions for sending data to, receiving data from, interacting with, and / or controlling one or more of the travel system 110, the sensor system 120, the control system 130, and the peripheral device 140.

[0111] For example, in addition to instructions 153, memory 152 may store data such as road maps, route information, the vehicle's location, direction, speed, and other such vehicle data, and other information. Such information may be used by vehicle 100 and computer system 150 during operation of vehicle 100 in autonomous, semi-autonomous, and / or manual modes.

[0112] like Figure 1 As shown, the user interface 170 can be used to provide information to or receive information from a user of the vehicle 100. Optionally, the user interface 170 can include one or more input / output devices within the set of peripheral devices 140, such as a wireless communication system 141, an onboard computer 142, a microphone 143, and a speaker 144.

[0113] In an embodiment of the present application, the computer system 150 may control functions of the vehicle 100 based on inputs received from various subsystems (e.g., the travel system 110, the sensing system 120, and the control system 130) and from the user interface 170. For example, the computer system 150 may utilize inputs from the control system 130 in order to control the brake unit 133 to avoid obstacles detected by the sensing system 120 and the obstacle avoidance system 136. In some embodiments, the computer system 150 is operable to provide control over many aspects of the vehicle 100 and its subsystems.

[0114] Alternatively, one or more of the above-mentioned components may be installed or associated separately from the vehicle 100. For example, the memory 152 may exist partially or completely separately from the vehicle 100. The above-mentioned components may be communicatively coupled together in a wired and / or wireless manner.

[0115] Optionally, the above components are only examples. In actual applications, the components in the above modules may be added or deleted according to actual needs. Figure 1 It should not be understood as limiting the embodiments of the present application.

[0116] Alternatively, vehicle 100 may be an autonomous vehicle traveling on a road and may identify objects in its surroundings to determine adjustments to the current speed. Objects may be other vehicles, traffic control devices, or other types of objects. In some examples, each identified object may be considered independently and based on the object's respective characteristics, such as its current speed, acceleration, spacing from the vehicle, etc., may be used to determine the speed to be adjusted by the autonomous vehicle.

[0117] Optionally, the vehicle 100 or a computing device associated with the vehicle 100 (eg, Figure 1 The computer system 150, computer vision system 134, memory 152) can predict the behavior of the identified object based on the characteristics of the identified object and the state of the surrounding environment (e.g., traffic, rain, ice on the road, etc.).

[0118] Optionally, each identified object is dependent on the behavior of each other, so all identified objects can also be considered together to predict the behavior of a single identified object. The vehicle 100 can adjust its speed based on the predicted behavior of the identified objects. In other words, the autonomous vehicle can determine that the vehicle will need to adjust to (e.g., accelerate, decelerate, or stop) a stable state based on the predicted behavior of the objects. In this process, other factors can also be considered to determine the speed of the vehicle 100, such as the lateral position of the vehicle 100 in the road it is traveling on, the curvature of the road, the proximity of static and dynamic objects, etc.

[0119] In addition to providing instructions to adjust the speed of the autonomous vehicle, the computing device may also provide instructions to modify the steering angle of vehicle 100 so that the autonomous vehicle follows a given trajectory and / or maintains a safe lateral and longitudinal distance from objects near the autonomous vehicle (e.g., cars in adjacent lanes on the road).

[0120] The vehicle 100 may be a car, a truck, a motorcycle, a bus, a ship, an airplane, a helicopter, a lawn mower, an entertainment vehicle, an amusement park vehicle, construction equipment, a tram, a golf cart, a train, a cart, etc., and the embodiments of the present application are not particularly limited.

[0121] In a possible implementation, the above Figure 1 The vehicle 100 shown may be an autonomous driving vehicle, and an autonomous driving system is described in detail below.

[0122] Figure 2 It is a schematic diagram of the autonomous driving system provided in an embodiment of the present application.

[0123] like Figure 2The illustrated automatic driving system includes a computer system 201, wherein the computer system 201 includes a processor 203, and the processor 203 is coupled to a system bus 205. The processor 203 may be one or more processors, wherein each processor may include one or more processor cores. A display adapter 207 (video adapter) may drive a display 209, and the display 209 is coupled to the system bus 205. The system bus 205 may be coupled to an input / output (I / O) bus 213 via a bus bridge 211, and an I / O interface 215 is coupled to the I / O bus. The I / O interface 215 communicates with a variety of I / O devices, such as an input device 217 (e.g., keyboard, mouse, touch screen, etc.), a media tray 221 (e.g., CD-ROM, multimedia interface, etc.). The transceiver 223 may send and / or receive radio communication signals, and the camera 255 may capture scene and dynamic digital video images. The interface connected to the I / O interface 215 may be a USB port 225.

[0124] The processor 203 may be any conventional processor, such as a reduced instruction set computer (RISC) processor, a complex instruction set computer (CISC) processor, or a combination thereof.

[0125] Optionally, the processor 203 may be a dedicated device such as an application specific integrated circuit (ASIC); the processor 203 may be a neural network processor or a combination of a neural network processor and the above-mentioned traditional processor.

[0126] Alternatively, in various embodiments described herein, the computer system 201 may be located remotely from the autonomous vehicle and may communicate wirelessly with the autonomous vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the autonomous vehicle, and others are performed by a remote processor, including taking actions required to perform a single maneuver.

[0127] Computer system 201 can communicate with software deployment server 249 via network interface 229. Network interface 229 can be a hardware network interface, such as a network card. Network 227 can be an external network, such as the Internet, or an internal network, such as Ethernet or a virtual private network (VPN). Optionally, network 227 can also be a wireless network, such as a wifi network, a cellular network, etc.

[0128] like Figure 2 As shown, the hard disk drive interface is coupled to the system bus 205, the hardware driver interface 231 can be connected to the hard disk drive 233, and the system memory 235 is coupled to the system bus 205. The data running in the system memory 235 may include an operating system 237 and an application 243. Among them, the operating system 237 may include a parser 239 (shell) and a kernel 241 (kernel). The shell 239 is an interface between the user and the kernel of the operating system. The shell may be the outermost layer of the operating system; the shell may manage the interaction between the user and the operating system, such as waiting for the user's input, interpreting the user's input to the operating system, and processing various operating system output results. The kernel 241 may be composed of those parts of the operating system used to manage memory, files, peripherals, and system resources. Directly interacting with the hardware, the operating system kernel usually runs processes and provides communication between processes, provides CPU time slice management, interrupts, memory management, IO management, etc. Application 243 includes programs related to controlling the automatic driving of the car, such as a program for managing the interaction between the automatic driving car and obstacles on the road, a program for controlling the route or speed of the automatic driving car, and a program for controlling the interaction between the automatic driving car and other automatic driving cars on the road. Application 243 also exists on the system of software deployment server 249. In one embodiment, when it is necessary to execute the automatic driving related program 247, computer system 201 can download the application from software deployment server 249.

[0129] For example, application 243 may also be a program for controlling an autonomous driving vehicle to perform automatic parking.

[0130] For example, the sensor 253 may be associated with the computer system 201 , and the sensor 253 may be used to detect the environment around the computer 201 .

[0131] For example, sensor 253 can detect animals, cars, obstacles and crosswalks, etc. Further, the sensor can also detect the environment around the above-mentioned objects such as animals, cars, obstacles and crosswalks, such as: the environment around the animals, for example, other animals appearing around the animals, weather conditions, the brightness of the surrounding environment, etc.

[0132] Alternatively, if the computer 201 is located in an autonomous vehicle, the sensor may be a camera, an infrared sensor, a chemical detector, a microphone, etc.

[0133] In one example, Figure 1The computer system 150 shown may also receive information from or transfer information to other computer systems. Alternatively, sensor data collected from the sensor system 120 of the vehicle 100 may be transferred to another computer for processing.

[0134] For example, Figure 3 As shown, data from computer system 312 can be transmitted to cloud-side server 320 via the network for further processing. The network and intermediate nodes can include various configurations and protocols, including the Internet, the World Wide Web, an intranet, a virtual private network, a wide area network, a local area network, a private network using one or more company's proprietary communication protocols, Ethernet, WiFi and HTTP, and various combinations of the foregoing; such communication can be by any device capable of transmitting data to and from other computers, such as a modem and a wireless interface.

[0135] In one example, server 320 may include a server having multiple computers, such as a load-balancing server farm, which exchanges information with different nodes of the network for the purpose of receiving, processing, and transmitting data from computer system 312. The server may be configured similarly to computer system 312, having a processor 330, memory 340, instructions 350, and data 360.

[0136] Exemplarily, the data 360 of the server 320 may include information related to the road conditions around the autonomous driving vehicle. For example, the server 320 may receive, detect, store, update, and transmit information related to the road conditions of the autonomous driving vehicle.

[0137] Combine the following Figures 4 to 14 The safety control method for the autonomous driving vehicle provided in the embodiment of the present application is described in detail.

[0138] First, the relevant terms in the autonomous driving technology involved in the embodiments of the present application are briefly described.

[0139] 1. Parallel systems

[0140] A parallel system refers to a common system composed of a natural real system and one or more corresponding virtual or ideal artificial systems.

[0141] 2. Behavioral safety

[0142] Behavioral safety refers to the behavioral decision-making and motion planning of autonomous vehicles that can ensure no collision risk while complying with traffic regulations.

[0143] 3. Functional safety

[0144] Functional safety means that in the event of a failure, the autonomous vehicle can still operate safely until it stops.

[0145] 4. Passable area

[0146] The traversable area refers to the physical world described by a grid map, where each grid can be in a state of occupied, unoccupied, or unknown.

[0147] 5. Virtual Wall

[0148] A virtual wall is an abstract representation of an inaccessible area such as the vehicle ahead, the end point, or a red light stop line. Setting up a virtual wall can indicate that passage is not allowed there.

[0149] like Figure 4 As shown in the schematic diagram, the planning and control module of the autonomous driving vehicle currently believes that the autonomous driving vehicle can avoid the risk of collision with pedestrians on the roadside by predicting the driving trajectory and drive safely on the road, such as Figure 4 The planned trajectory of the vehicle shown in (a) is the motion planning trajectory of the autonomous vehicle; however, the actual driving situation of the autonomous vehicle is as follows Figure 4 The actual vehicle trajectory shown in (b) is the real motion trajectory of the autonomous vehicle. When the autonomous vehicle is driving according to the motion planning trajectory, the lower-level vehicle actuator may have execution errors, which may cause the autonomous vehicle to deviate from the predicted driving trajectory and collide with pedestrians on the side of the road, resulting in safety risks during the driving of the autonomous vehicle.

[0150] In view of this, an embodiment of the present application provides a safety control method for an autonomous driving vehicle, so that when planning the predicted driving trajectory of the autonomous driving vehicle, possible errors in the motion control and vehicle actuators of the autonomous driving vehicle are taken into account, thereby accurately predicting the vehicle position and posture of the autonomous driving vehicle at future moments, avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, thereby ensuring the safety of the autonomous driving vehicle.

[0151] Figure 5 Schematic diagram of the system architecture of the autonomous driving vehicle provided in the embodiment of the present application. Figure 5 As shown, in the embodiments of the present application, the backup small system introduced can be carried on physical hardware, such as carried on a microcontroller unit (MCU). The MCU is also called a single chip microcomputer or a single chip microcomputer MCU, which can be deployed between the computing platform and the actuator; wherein the MCU may include a system detection module, an exception handling module, a dead reckoning positioning module, a parallel system safety protection module and a motion control module.

[0152] It should be understood that the computing platform 410 may refer to a computing module in an autonomous driving vehicle, the backup subsystem 420 may be a control module in an autonomous driving vehicle, the backup subsystem 420 may be deployed in the same module as other control modules in the autonomous driving vehicle, or the backup subsystem 420 may be a module deployed independently of other control modules in the autonomous driving vehicle.

[0153] For example, Figure 5 As shown, the system monitoring module can be used to monitor the health status of the system and feed it back to the exception handling module; the exception handling module can receive the health status of the system monitoring module and generate the data required by the parallel system safety protection module; the parallel system safety protection module can be used to generate the predicted position and posture of the autonomous driving vehicle at a future moment according to the acquired data (for example, the data transmitted by the computing platform, or the data generated by the exception handling module), perform collision detection according to the predicted position and posture and the perception detection result, and modify the vehicle planning information of the autonomous driving vehicle according to the collision detection result; the dead reckoning positioning module can be used to trigger the generation of the real-time positioning result of the autonomous driving vehicle according to the wheel speed meter when the system detection result is abnormal; the motion control module can be used to generate the control instructions of the autonomous driving vehicle (for example, gear, throttle, brake or steering wheel) according to the behavior planning data generated by the parallel system safety protection module, and send it to the actuator, wherein the actuator may refer to the operating mechanism such as the accelerator pedal, brake pedal and steering wheel of the autonomous driving vehicle.

[0154] In one example, when the computer platform is running normally, the above-mentioned exception handling module can transmit the motion planning results, vehicle information, environmental perception results and other data issued by the computing platform to the backup small system for use; at the same time, the exception handling module can also generate cache data, for example, record environmental perception results, vehicle information and motion planning results.

[0155] In another example, when a computer platform operates abnormally or some sensors of an autonomous vehicle are abnormal, such as Figure 6 As shown in (a) in the figure, the exception handling module can quickly call the cached data, and use the dead reckoning method to locate the vehicle using the dead reckoning positioning module, and predict the body posture of the automatic vehicle through the parallel system safety protection module, so that the backup small system can perform subsequent motion planning and control of the autonomous driving vehicle.

[0156] For example, during the driving process of an autonomous vehicle, due to the influence of various environmental factors such as weather, lighting, magnetic fields, vibrations, and the working state of the autonomous vehicle itself, sensors may work abnormally or even the computing platform system may be abnormal. In this case, the autonomous vehicle may have abnormal body positioning and be unable to correctly plan the travel path, causing the autonomous vehicle to drive off the target road or lane and cause a traffic accident. Even if the autonomous vehicle can be accurately positioned, it may not be able to accurately perceive obstacles in the environment due to abnormal perception systems, especially it may not be able to accurately predict the travel trajectory of dynamic obstacles, and there is a risk of collision.

[0157] For the above-mentioned usage scenarios, the backup subsystem in the embodiment of the present application can monitor the working status of the on-board computing platform and sensors, and store important data information in the cache when the on-board computing platform is operating normally; when the data given by the computing platform is detected to be abnormal, the cached data will be called to locate the vehicle by dead reckoning; at the same time, based on the parallel system safety protection module, the safety control method of the autonomous driving vehicle provided in the embodiment of the present application can be used to accurately predict the position and posture of the autonomous driving vehicle, and perform collision prediction with the obstacle information in the cache, so that the autonomous driving vehicle can be planned to slow down and stop when there is a risk of collision with the autonomous driving vehicle, thereby ensuring the safety of the autonomous driving vehicle.

[0158] Combine the following Figure 7 The safety control method for the autonomous driving vehicle provided in the embodiment of the present application is described in detail. Figure 7 The safety control method 500 shown can be performed by Figure 1 The autonomous vehicle shown, or Figure 2 The automated driving system shown is used to perform, or, Figure 5 The backup subsystem 420 of the autonomous driving vehicle is shown to be executed. Figure 7 The safety control method 500 shown includes steps 510 to 540, and these steps are described in detail below.

[0159] Step 510: Obtain information about the motion planning trajectory of the autonomous driving vehicle, where the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located.

[0160] Exemplarily, the motion planning trajectory may refer to the desired trajectory of the autonomous driving vehicle obtained by the upper-level motion planning module of the autonomous driving vehicle based on the environmental information around the autonomous driving vehicle. For example, the trajectory information of the autonomous driving vehicle under the global coordinates (e.g., the northeast sky coordinate system) planned by the motion planning module may be converted to the trajectory information under the coordinates of the autonomous driving vehicle.

[0161] For example, Figure 5 As shown, the motion planning trajectory can be calculated by the computing platform 410.

[0162] In one possible implementation, the motion planning trajectory of the autonomous driving vehicle can be obtained by transparently transmitting the motion results output by the upper-level motion planning module.

[0163] Furthermore, when transparently transmitting data from the upper computing platform, cache data can also be generated, for example, recording important data such as environmental perception results, vehicle information, and motion planning results.

[0164] In another possible implementation, when the autonomous driving vehicle is detected to be in an abnormal state, the motion planning trajectory can be obtained based on the cached data.

[0165] It should be understood that an autonomous driving vehicle being in an abnormal situation may refer to a situation where any one or more components of the autonomous driving vehicle fail. For example, it may refer to a failure in the computing platform of the autonomous driving vehicle, or it may refer to an abnormality in some sensors of the autonomous driving vehicle.

[0166] Exemplarily, the above-mentioned safety control method also includes: saving vehicle information of the autonomous driving vehicle, wherein the vehicle information may include planned trajectory information of the autonomous driving vehicle in a global coordinate system; the above-mentioned acquisition of information on the planned motion trajectory of the autonomous driving vehicle may include: when it is monitored that the autonomous driving vehicle is in an abnormal state, acquiring the planned trajectory information in the global coordinate system from the saved vehicle information; and performing coordinate conversion on the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain motion planning trajectory information.

[0167] In an embodiment of the present application, when an abnormal state of an autonomous driving vehicle is monitored, the saved vehicle information of the autonomous driving vehicle (for example, cached data) can be quickly called up, and the autonomous driving vehicle can be planned and controlled according to the saved vehicle information, thereby avoiding the problem that the autonomous driving vehicle is unable to correctly plan its path when it is in an abnormal state, causing the autonomous driving vehicle to drive out of the target road or lane and cause a traffic accident, thereby improving the safety of the autonomous driving vehicle during driving.

[0168] Exemplarily, the above-mentioned vehicle information may also include the driving position information of the autonomous driving vehicle, and the safety control method further includes: when the autonomous driving vehicle is monitored to be in an abnormal state, the positioning information of the autonomous driving vehicle at the current moment can be obtained according to the driving position information, the state information of the autonomous driving vehicle and the dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the current speed of the autonomous driving vehicle, the current steering wheel angle, the current throttle control amount and the current brake control amount of the autonomous driving vehicle; the above-mentioned coordinate transformation according to the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain the motion planning trajectory information includes: obtaining the above-mentioned motion planning trajectory information according to the current positioning information of the autonomous driving vehicle and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

[0169] In an embodiment of the present application, when an autonomous driving vehicle is in an abnormal state, for example, when a positioning module of the autonomous driving vehicle is abnormal, the cached data can be quickly called to obtain the vehicle posture of the autonomous driving vehicle at the current moment, and then the autonomous driving vehicle can be planned and controlled; thereby avoiding the problem that the autonomous driving vehicle is unable to correctly plan the travel path when it is in an abnormal state, causing the autonomous driving vehicle to drive out of the target road or lane and cause a traffic accident, thereby improving the safety of the autonomous driving vehicle during driving.

[0170] For example, Figure 5 As shown, the autonomous driving vehicle in an abnormal state may not be able to directly obtain the motion planning trajectory from the computing platform 410, but the state information of the autonomous driving vehicle can be obtained from the cached data, and the vehicle position of the autonomous driving vehicle at the current moment when it is driving in the abnormal state can be obtained according to the dead reckoning algorithm.

[0171] Step 520: obtain a predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information.

[0172] It should be noted that the motion planning trajectory information may refer to the expected driving trajectory of the autonomous driving vehicle; the predicted vehicle posture may be the vehicle posture of the autonomous driving vehicle during actual driving predicted based on the motion planning trajectory and the execution error of the actuator (for example, a motion controller) simulating the autonomous driving vehicle, or the vehicle posture close to the actual driving. The trajectory composed of the predicted vehicle postures at multiple moments is the true trajectory of the autonomous driving vehicle during actual driving.

[0173] Exemplarily, predicting vehicle posture may refer to predicting vehicle position and predicting vehicle attitude (roll pitchyaw), wherein the predicted vehicle attitude may include a predicted heading angle of the autonomous driving vehicle.

[0174] It should be understood that the above-mentioned motion controller must ensure that the same controller is used when the autonomous driving vehicle is actually driving to ensure the homology of the control links; in this way, it is possible to simulate the movement of the autonomous driving vehicle in a real scene, thereby obtaining the error introduced by the motion control and predicting the actual motion trajectory of the autonomous driving vehicle based on the motion planning trajectory.

[0175] The above process of obtaining the predicted vehicle posture of the autonomous vehicle based on the motion planning trajectory and the motion controller of the autonomous vehicle can be found in the subsequent Figure 8 shown.

[0176] Optionally, in one possible implementation, obtaining the predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle may include inputting the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain control instructions, wherein the control instructions are used to instruct the adjustment of the steering wheel control amount, throttle control amount and brake control amount of the autonomous driving vehicle; and inputting the control instructions into the vehicle dynamics model to obtain the predicted vehicle posture.

[0177] In one possible implementation, the motion planning trajectory information may be input into a lateral controller of an autonomous driving vehicle to obtain a control instruction for adjusting the steering wheel control amount of the autonomous driving vehicle; the motion planning trajectory information may be input into a longitudinal controller of the autonomous driving vehicle to obtain a control instruction for adjusting the throttle control amount and the brake control amount of the autonomous driving vehicle.

[0178] It should be noted that the above-mentioned lateral controller and longitudinal controller need to ensure that the same lateral controller and longitudinal controller are used when the autonomous driving vehicle is actually driving, so as to ensure the homology of the control links; in this way, the movement of the autonomous driving vehicle in the real scene can be simulated, so as to obtain the error introduced by the motion control and accurately predict the vehicle posture.

[0179] Step 530: predict a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with the obstacle, and the obstacle information is used to indicate the obstacle.

[0180] Exemplarily, collision detection can be performed based on the predicted vehicle posture of the autonomous driving vehicle and obstacles in the environmental perception results, where the obstacles can include static obstacles and dynamic obstacles. Static obstacles may refer to obstacles whose positions will not change, such as obstacles at rest on the side of the road; dynamic obstacles may refer to obstacles whose positions will change, such as moving vehicles or moving pedestrians.

[0181] The above process of obtaining collision detection results based on the predicted vehicle posture and obstacle information of the autonomous driving vehicle can be found in the subsequent Fig.10 shown.

[0182] Step 540: When the collision detection result indicates that the autonomous driving vehicle will collide with an obstacle, correct the motion planning trajectory information.

[0183] For example, when the collision detection result shows that the autonomous driving vehicle will collide with an obstacle, the corrected motion planning trajectory information of the autonomous driving vehicle can be determined based on the vehicle posture when the autonomous driving vehicle collides with the obstacle, so that the autonomous driving vehicle can avoid the obstacle and avoid collision with the obstacle.

[0184] In one possible implementation, if it is detected that there is a risk of collision between the predicted vehicle position of the autonomous driving vehicle and an obstacle, the possible collision time and collision position can be recorded, and a dangerous virtual wall can be generated; wherein the virtual wall can be an abstract representation of inaccessible areas such as the vehicle ahead, the end point, and the red light stop line, indicating that the autonomous driving vehicle is not allowed to pass through here, so that the autonomous driving vehicle can slow down or even stop to avoid obstacles that may collide.

[0185] In an embodiment of the present application, by inputting motion planning trajectory information into the motion controller of the autonomous driving vehicle, the execution error of the autonomous driving vehicle when actually driving based on the motion planning trajectory can be simulated, thereby obtaining the vehicle posture of the autonomous driving vehicle during actual driving; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at future moments can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, and ensuring the safety of the autonomous driving vehicle during driving.

[0186] In addition, in an embodiment of the present application, when an autonomous driving vehicle is in an abnormal state, cached data can be quickly called to plan and control the autonomous driving vehicle based on the cached data, thereby avoiding the problem that the autonomous driving vehicle is unable to correctly plan its path when in an abnormal state, causing the autonomous driving vehicle to drive out of the target road or lane and cause a traffic accident, thereby improving the safety of the autonomous driving vehicle during driving.

[0187] Figure 8 A method for predicting vehicle posture of an autonomous driving vehicle provided in an embodiment of the present application; Figure 8 The method 600 shown may be performed by Figure 1 The autonomous vehicle shown, or Figure 2 The automated driving system shown is used to perform, or, Figure 5The backup subsystem 420 of the autonomous driving vehicle shown is executed; wherein, the method 600 may include steps 601 to 609, and these steps are described in detail below.

[0188] Step 601: Obtain motion planning results;

[0189] Among them, the motion planning result can refer to Figure 5 The motion planning information shown.

[0190] For example, Figure 5 As shown, the motion planning result can obtain the motion planning result obtained by the computing platform.

[0191] For example, the planning result obtained by the upper-level planning can be S g ={s i (x,y,v)|i=1,2,...,n},S g A line of points in a global coordinate system (eg, a northeast celestial coordinate system) can be represented, wherein the (x, y) of each point can be used to represent the position, and v can be used to represent a given vehicle speed corresponding to the position (eg, the vehicle speed expected at the position).

[0192] For example, Figure 4 As shown in (a) of the figure, the upper planning link believes that there will be no collision with the pedestrian in front of the right, so there will be no deceleration behavior; here it is assumed that the vehicle speed v = 30km / h is given at all the position points of the trajectory, that is, S g ={s i (x,y,30)|i=1,2,...,n}.

[0193] Step 602: Obtain vehicle information of the autonomous driving vehicle.

[0194] For example, the vehicle information of an autonomous driving vehicle may include the current position information p0(x, y, θ) of the autonomous driving vehicle, where (x, y) can be used to indicate the position of the autonomous driving vehicle, and θ can be used to indicate the direction of the autonomous driving vehicle; the current gear g0, assuming it is the forward gear D; and the current vehicle speed v0 = 20 km / h.

[0195] It should be understood that the above-mentioned step 601 and step 602 can be obtained simultaneously, or can be executed one after the other, for example, step 601 is executed first and then step 602, or step 602 is executed first and then step 601. This application does not impose any limitation on this.

[0196] Step 603: preprocessing.

[0197] Among them, it is used to pre-process the data obtained in step 601 and step 602, so as to generate the input data required by the lateral controller and the longitudinal controller.

[0198] For example, the vehicle posture p0(x, y, θ) of the autonomous driving vehicle at the current time T0 is obtained, and the gear position g0 and vehicle speed v0 of the autonomous driving vehicle at the time T0 are obtained; the trajectory S in the above global coordinate system is converted into g ={s i (x, y, v)|i=1,2,...,n} is generated by transforming the vehicle posture p0(x, y, θ) of the autonomous driving vehicle at time T0 into the local coordinate system. i (x,y,v)|i=1,2,...,n}.

[0199] Step 604: Input the pre-processed data into the horizontal controller.

[0200] For example, the data of the autonomous driving vehicle at time T0 obtained by the preprocessing in step 603 is input into the lateral controller to generate a given steering wheel angle

[0201] It should be noted that the lateral controller must ensure that the same lateral controller is used when the autonomous driving vehicle is actually driving to ensure the same control link; this is the only way to simulate the movement of the autonomous driving vehicle in a real scene and obtain the error introduced by the motion control.

[0202] Exemplarily, the lateral controller may employ any method for lateral motion control of an autonomous vehicle; for example, fuzzy control-based lateral control strategies, model predictive control, and the like.

[0203] Step 605: input the preprocessed data into the longitudinal controller.

[0204] For example, the data of the automatic driving vehicle at time T0 obtained through the preprocessing in step 603 is input into the longitudinal controller to generate a given throttle or brake control amount C0.

[0205] It should be noted that the longitudinal controller must ensure that the same longitudinal controller is used when the autonomous driving vehicle is actually driving to ensure the same control links; this is the only way to simulate the movement of the autonomous driving vehicle in a real scene and obtain the error introduced by the motion control.

[0206] Exemplarily, the longitudinal controller may employ any method used for longitudinal motion control of an autonomous vehicle; for example, proportional-integral-derivative control (PID control).

[0207] For example, the current vehicle speed v0 = 20 km / h, and the expected vehicle speed at the waypoint is vg =30km / h, according to the PID control strategy, generate the vehicle's given throttle or brake control amount C0=+0.1; here, the given throttle or brake control amount can be expressed as a proportional coefficient, where + can represent acceleration and - can represent deceleration; for example, +0.1 can represent 10% throttle pedal amount control.

[0208] Step 606: Input the motion parameters obtained in step 604 and step S605 into the dynamics model.

[0209] The motion parameters may include the steering wheel angle obtained through the above steps. Throttle or brake control amount C0.

[0210] In one example, motion parameters (eg, also referred to as motion instructions) output by the lateral controller and the longitudinal controller may be input into a dynamics model.

[0211] In another example, if the dynamic model cannot process the output parameters of the lateral controller and the longitudinal controller at the same time, in the implementation of the present application, the parameters output by the lateral controller can be input into the kinematic model, and the parameters output by the longitudinal controller can be input into the dynamic model.

[0212] Exemplarily, a dynamic model of the autonomous driving vehicle is established based on the dynamic characteristics of the autonomous driving vehicle. For example, the acceleration a0 of the autonomous driving vehicle can be generated based on the longitudinal control amount C0 generated by the longitudinal motion controller; based on the vehicle speed v0 at time T0, the ΔT time is predicted forward to generate the vehicle speed v1 at time T1.

[0213] Exemplarily, the vehicle speed v1 at time T1 may be generated by the following formula.

[0214] F a =F T -F w -F r -F i ;

[0215]

[0216] v1=v0+a0ΔT;

[0217] Among them, F T ∝C0 refers to the driving force of the autonomous vehicle; F w Represents air resistance, which is related to the speed and frontal area of ​​the autonomous vehicle; F r =f·mg represents the friction resistance, f is the friction coefficient, and mg represents the vehicle gravity of the autonomous driving vehicle; F i =mg·sin(α) represents the slope resistance, and α represents the slope.

[0218] For example, a dynamic model is established based on the dynamic characteristics of the vehicle; based on the longitudinal control quantity C0 generated by the longitudinal motion controller, the vehicle acceleration a0 = 3m / s is generated. 2 According to the vehicle speed v0=20km / h at time T0, the forward prediction time ΔT=0.1s is used to generate the vehicle speed v1=20+3·0.1·3.6=21.08km / h at time T1.

[0219] For example, based on the Ackerman steering principle, a kinematic model of an autonomous vehicle is established. Based on the steering wheel angle generated by the above lateral motion controller The vehicle speed v1 generated by the vehicle dynamics model, the initial position p0(x, y, θ) of the autonomous driving vehicle, and the vehicle position p1(x1, y1, θ1) at time T1 can be generated based on the kinematic model.

[0220] Exemplarily, the vehicle posture at time T1 can be generated by the following formula.

[0221]

[0222] Step 607: Generate an accurate outline.

[0223] For example, based on the vehicle posture and vehicle shape envelope of the autonomous driving vehicle at time T1, the accurate coverage area of ​​the autonomous driving vehicle can be generated. For example, the coverage area of ​​the contour shape of the rearview mirror can be reflected.

[0224] It should be noted that in the embodiments of the present application, by simulating the execution error of the motion controller of the autonomous driving vehicle when executing the motion planning trajectory, the predicted vehicle posture when the vehicle is driving can be obtained; the predicted vehicle posture is more accurate, so that more vehicle information can be obtained and an accurate outline of the coverage area can be generated.

[0225] Step 608: Determine whether the predicted time has been reached.

[0226] If the predicted time is reached, step 609 is executed to end the vehicle posture prediction of the autonomous driving vehicle; if the predicted time is not reached, the process returns to step 603.

[0227] For example, through the above steps 601 to 607, the predicted vehicle posture at time T1 can be generated according to the vehicle information at time T0; the predicted vehicle posture at time T2 can be generated according to the vehicle information at time T1, and so on. Fig. 9 As shown, T0 to T n List of predicted vehicle poses at time.

[0228] For example, Fig. 9As shown in (a), it is a schematic diagram of predicting the predicted vehicle posture of the autonomous driving vehicle at time T1 based on the vehicle information at time T0; Fig. 9 As shown in (b), it is a schematic diagram of predicting the predicted vehicle posture of the autonomous driving vehicle at time T2 based on the vehicle information at time T1; Fig. 9 As shown in (c) of FIG. 1 , it is a schematic diagram of predicting the predicted vehicle posture of the autonomous driving vehicle at time T3 based on the vehicle information at time T2; and so on, as Fig. 9 As shown in (d) in the figure, according to T n-1 The vehicle information at the moment predicts the autonomous driving vehicle T n Schematic diagram of the predicted vehicle pose at time .

[0229] It should be understood that the above-mentioned predicted vehicle posture may refer to the actual vehicle posture of the autonomous driving vehicle during actual driving, which is obtained based on the motion planning trajectory of the autonomous driving vehicle, taking into account the execution error of the actuator of the autonomous driving vehicle.

[0230] For example, the motion parameter information of the autonomous driving vehicle generated at time T1 can be used as the input data for preprocessing in step 603 to generate the input data required for the next iteration. Repeat the above steps 604 to 607 to predict the vehicle posture at time T2 based on the motion parameter information of the autonomous driving vehicle at time T1; and so on, the vehicle posture at time T0 to T2 can be generated. n The vehicle position at the moment, for example, P = {p0(x0,y0,20),p1(x1,y1,21.08),...p n (x n ,y n ,30)}.

[0231] Through the above Figure 8 and Fig. 9 The behavior planning method shown can generate a list of predicted vehicle postures of the autonomous driving vehicle; further, in an embodiment of the present application, obstacle collision detection can be performed based on the obtained list of predicted vehicle postures and the information of the obstacles included in the perception detection results to obtain collision detection results; based on the collision detection results, the motion parameters of the generated autonomous driving vehicle can be corrected to obtain a corrected vehicle posture of the autonomous driving vehicle.

[0232] For example, if it is detected that there is a risk of collision between the predicted vehicle position of the autonomous driving vehicle and an obstacle, the possible collision time and collision position can be recorded, and a dangerous virtual wall can be generated; wherein the virtual wall can be an abstract representation of inaccessible areas such as the vehicle ahead, the end point, and the red light stop line, indicating that the autonomous driving vehicle is not allowed to pass through here, so that the autonomous driving vehicle can slow down or even stop to avoid obstacles that may collide.

[0233] In an embodiment of the present application, when the collision detection result obtained by performing collision detection on the autonomous driving vehicle and the obstacle information is that the autonomous driving vehicle will collide with the obstacle, the vehicle posture of the autonomous driving vehicle can be corrected according to the vehicle posture when the autonomous driving vehicle collides with the obstacle, so that the autonomous driving vehicle can avoid the obstacle and avoid collision with the obstacle, thereby improving the safety of the autonomous driving vehicle during driving.

[0234] Combine the following Fig.10 The process of correcting the motion planning trajectory of an autonomous vehicle is described in detail.

[0235] Fig.10 It is a schematic diagram of the process of correcting the motion planning trajectory of the autonomous driving vehicle provided in an embodiment of the present application. Fig.10 The method 700 shown may be performed by Figure 1 The autonomous vehicle shown, or Figure 2 The automated driving system shown is used to perform, or, Figure 5 The backup subsystem 420 of the autonomous driving vehicle shown is executed; Fig.10 The method 700 shown may be Figure 5 The method 700 is executed in the backup mini-system shown, and includes steps 701 to 706, which are described in detail below.

[0236] Step 701: Obtain the predicted vehicle posture of the autonomous driving vehicle.

[0237] Exemplarily, the above-mentioned predicted vehicle posture may refer to a predicted vehicle posture list. Figure 7 or Figure 8 The schematic flow chart shown in FIG. 1 is used to obtain the predicted vehicle posture of the autonomous driving vehicle while driving.

[0238] It should be understood that the predicted vehicle posture can be the vehicle posture of the autonomous driving vehicle during actual driving, obtained based on the motion planning trajectory and the execution error of the actuator (for example, a motion controller) that simulates the autonomous driving vehicle, and the trajectory composed of multiple predicted vehicle postures can be the driving trajectory of the autonomous driving vehicle during actual driving or a trajectory close to the driving trajectory of the autonomous driving vehicle during actual driving.

[0239] Step 702: Obtain the environmental perception results of the autonomous driving vehicle.

[0240] For example, environmental information around the autonomous driving vehicle can be sensed by the sensing system of the autonomous driving vehicle.

[0241] For example, Figure 1The illustrated sensing system 120 may include several sensors that sense information about the environment surrounding the vehicle 100 .

[0242] Step 703: Static collision detection.

[0243] For example, Fig.11 As shown in (a) in the figure, based on the environmental perception results detected by the perception fusion module of the autonomous driving vehicle, the grid map information of the traversable area near the autonomous driving vehicle including static obstacles can be obtained; based on the information obtained on the predicted vehicle posture, the location where the autonomous driving vehicle may collide with the static obstacles in the traversable area within a period of time in the future can be predicted.

[0244] Step 704: dynamic collision detection.

[0245] For example, Fig.11 As shown in (b) in the figure, the predicted vehicle posture information of the autonomous driving vehicle at each future moment can be compared with the motion prediction results of the dynamic obstacle at each future moment to obtain the possible collision position and collision time.

[0246] Step 705: Generate a dangerous virtual wall.

[0247] For example, if it is detected that the predicted vehicle posture of the autonomous driving vehicle has a risk of collision with an obstacle, the possible collision time and collision position can be recorded, and a dangerous virtual wall can be generated; wherein the virtual wall can be an abstract representation of an inaccessible area such as a vehicle ahead, an end point, a red light stop line, etc., indicating that the autonomous driving vehicle is not allowed to pass through here, and the virtual wall can include information on distance, speed and time, such as Fig.11 The virtual wall shown in (b).

[0248] In an embodiment of the present application, when it is detected that an autonomous driving vehicle may collide with a dynamic obstacle, a virtual wall can be generated according to the posture where the collision may occur, so that the autonomous driving vehicle will not pass through the collision position at some point in the future, thereby effectively avoiding the autonomous driving vehicle from colliding with the dynamic obstacle and ensuring the safety of the autonomous driving vehicle.

[0249] Step 706: Generate target motion parameters (eg, also called target motion instructions).

[0250] For example, target motion parameters that enable the autonomous driving vehicle to avoid collision with obstacles can be generated based on the predicted vehicle posture of the autonomous driving vehicle and information about the virtual wall. The target motion parameters may include speed information of the autonomous driving vehicle.

[0251] For example, suppose the obstacles in the driving area of ​​the autonomous vehicle are O = {oi |i=1,2...,n}, where n=1, that is, there is only one pedestrian in the driving area of ​​the autonomous vehicle. Fig.12 As shown; through the above step 703, based on the collision detection of the static drivable area, it is determined that there are no obstacles in the drivable area, so there is no risk of collision.

[0252] Through the above step 704, based on the collision detection of dynamic obstacles, the obstacle list O={o i |i=1}sum Figure 8 The predicted vehicle posture P shown in the figure is used for collision detection. For example, the separating axis theorem can be used for collision detection, and it is found that the autonomous driving vehicle is at P m There is a risk of collision with pedestrians at the location. Fig. 9 The predicted vehicle pose list shown in the figure shows that when reaching P m The speed of the autonomous vehicle at the position will reach 30km / h. m A safety protection virtual wall w(s,v,t) is added at the position, where s represents the distance between the autonomous driving vehicle and the pedestrian, v represents the speed of the pedestrian, and t represents the time when the collision occurs.

[0253] Furthermore, target motion parameters can be generated based on the virtual wall and the predicted vehicle posture; for example, a new given vehicle speed can be generated based on the given vehicle speed of the planning module and the dangerous virtual wall to avoid the risk of collision.

[0254] It should be noted that the speed correction here does not refer to the correction of the predicted vehicle posture P, but the correction of the planning result S g ={s i (x,y,30)|i=1,2,...,n} for correction.

[0255] For example, the speed correction method can adopt a nonlinear speed generation method based on an empirical formula, or other correction methods can be adopted. The corrected planning result can be S g ={s0(x0,y0,20),s1(x1,y1,19.0),...s n (x n ,y n ,0)}, so that the autonomous driving vehicle drives to P m The vehicle slows down or stops at the location to avoid collision with obstacles.

[0256] In an embodiment of the present application, by acquiring the trajectory planning results of the upper-level planning link, the vehicle's status information (for example, the current vehicle speed, gear position, steering wheel angle, etc.), the environmental perception results (for example, the passable area, obstacle list) and other data, by introducing the errors existing in the actuators of the autonomous driving vehicle, the predicted vehicle posture of the autonomous driving vehicle is more accurately predicted, and collision detection is performed based on the predicted vehicle posture and the environmental perception results, so as to correct the motion planning trajectory of the autonomous driving vehicle, so that the autonomous driving vehicle can effectively avoid collisions with obstacles, thereby ensuring the safety of the autonomous driving vehicle during driving.

[0257] In one example, if Figure 6 In the scenario where the autonomous driving vehicle shown in (a) is in an abnormal state, for example, when the sensor system of the autonomous driving vehicle fails, or the computing platform of the autonomous driving vehicle fails, the autonomous driving vehicle may not be able to accurately perceive obstacles in the surrounding environment and cannot correctly plan the travel path; at this time, in an embodiment of the present application, the backup small system in the autonomous driving vehicle can be used to handle the exception.

[0258] For example, due to environmental factors and the working state of the autonomous vehicle itself, sensors may malfunction; or even the computing platform system in the autonomous vehicle may malfunction. In this case, the autonomous vehicle may have abnormal positioning of the vehicle body and be unable to correctly plan the path of travel, causing the autonomous vehicle to drive off the target road or lane and cause a traffic accident. Even if the autonomous vehicle can be accurately positioned, it may not be able to accurately perceive obstacles in the environment due to abnormal perception systems, especially it may not be able to accurately predict the trajectory of dynamic obstacles, causing the autonomous vehicle to be at risk of collision. Fig.13 Describe the process of abnormal handling of autonomous vehicles in detail

[0259] Fig.13 It is a schematic flowchart of the abnormality handling method of the autonomous driving vehicle provided in an embodiment of the present application. Fig.13 The exception handling method 800 shown may be performed by Figure 1 The autonomous vehicle shown, or Figure 2 The automated driving system shown is used to perform, or, Figure 5 The backup subsystem 420 of the autonomous driving vehicle shown is executed; the exception handling method 800 may include steps 801 to 806, and these steps are described in detail below.

[0260] Step 801, start.

[0261] For example, Figure 5The system monitoring module shown starts to monitor whether the autonomous driving vehicle is in normal working condition.

[0262] Step 802: Determine whether the system of the autonomous driving vehicle is normal. If the system is normal, execute step 803; if the system is abnormal, execute step 805.

[0263] Step 803: Generate cache.

[0264] For example, when the motion planning results, vehicle information, environmental perception results and other data issued by the computing platform of the autonomous driving vehicle are transmitted to the vehicle execution unit, buffered data can be generated based on the environmental perception results, vehicle information and motion planning results.

[0265] Step 804: Call cache data.

[0266] For example, when the system monitoring module detects that the autonomous driving vehicle is in an abnormal state, the cached data can be called.

[0267] It should be understood that the above-mentioned autonomous driving vehicle being in an abnormal state may refer to a situation where any one or more components in the autonomous driving vehicle fail, for example, it may refer to a failure in the computing platform of the autonomous driving vehicle, or it may refer to an abnormality in some sensors of the autonomous driving vehicle.

[0268] For example, during the driving of an autonomous vehicle, due to the influence of various environmental factors such as weather, light, magnetic field, vibration, and the working state of the autonomous vehicle itself, sensors may malfunction or even the computing platform system may malfunction.

[0269] For example, at time T0, the system monitoring module finds that the positioning result of the autonomous driving vehicle has changed significantly, or the positioning noise has increased abnormally; at this time, it can be judged that the positioning module in the computing platform is abnormal and cannot provide accurate positioning for the autonomous driving vehicle. In view of this situation, in the embodiment of the present application, the backup small system can quickly respond to read the cached data, such as the cached information when the positioning is normal.

[0270] Step 805: Start dead reckoning positioning.

[0271] For example, the vehicle positioning can be performed according to the dead reckoning method. For example, the vehicle position and posture of the autonomous driving vehicle at the kth moment can be obtained according to the following formula.

[0272]

[0273] Among them, x k and kcan represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the kth moment, x0 and y0 can represent the horizontal coordinate and vertical coordinate of the autonomous driving vehicle in the ground coordinate system at the starting moment, S i represents the distance the autonomous driving vehicle travels in the i-th sampling period, θ i It represents the angle between the forward direction of the autonomous driving vehicle and the x-axis direction of the ground coordinate system in the i-th sampling period.

[0274] Step 806: Send the called cache data to the parallel system to predict the predicted vehicle posture of the autonomous driving vehicle.

[0275] For example, the positioning results of the vehicle's dead reckoning can be used to calculate the trajectory of the autonomous vehicle in the next 10 seconds based on the vehicle's dynamic model and kinematic model. Fig.14 As shown in (b) of ; at the same time, the autonomous driving vehicle can call the system cache data to perform collision detection of dynamic and static obstacles and static obstacles respectively. The specific process can be parameterized as above Fig.10 As shown, no further description is given here.

[0276] For example, for example, Fig.14 As shown in (a), the autonomous vehicle can drive on a right-turn lane and move forward along the reference trajectory given by the motion planning module. The vehicle uses on-board sensors to perform real-time environmental perception, fusion, and precise positioning of the vehicle body. The data processing of the perception, fusion, positioning, and motion planning modules of the autonomous vehicle is completed by the high-performance computing platform, and the perception fusion results, vehicle positioning information, and motion planning information are sent to the backup small system through the bus. If the original motion planning trajectory is followed, the autonomous vehicle can continue to drive along the reference trajectory with a forward speed of 30km / h; it is assumed that the origin of the coordinate system where the autonomous vehicle is located is the midpoint of the rear axle of the autonomous vehicle, the x-axis is forward along the front of the autonomous vehicle, the y-axis is left along the front of the autonomous vehicle, and the z-axis is upward along the front of the autonomous vehicle; the autonomous vehicle can perceive static obstacles in the two-dimensional plane area where x is [-20m, 90m] and y is [-30m, 30m], and generate a grid map; the grid state value is used to represent the grid occupancy, and the passable area considering static obstacles is obtained. When the autonomous driving vehicle is in an abnormal state, the cached data in the backup system can be called to use the vehicle's dead reckoning to calculate the positioning result of the autonomous driving vehicle. The parallel system can predict the operating parameters of the autonomous driving vehicle based on the cached data.

[0277] For example, Fig.14As shown in (b), the autonomous driving vehicle will not collide with static obstacles in the drivable area in the next 10 seconds; however, the autonomous driving vehicle may collide with dynamic obstacle ③ at T0+1.24s; for example, the vehicle origin at the time of collision is at [x=10.34m, y=-0.87m] in the vehicle coordinate system at T0, and the collision point is at [x=13.46m, y=-0.96m] in the vehicle coordinate system at T0.

[0278] Furthermore, since collision detection finds that the autonomous driving vehicle will collide with a dynamic obstacle, in order to avoid a collision, the backup system can generate a dangerous virtual wall perpendicular to the reference trajectory at the collision point in the vehicle coordinate system [x = 13.46m, y = -0.96m], such as Fig.14 As shown in (c) in the figure, due to the existence of the dangerous virtual wall, the backup subsystem can call the motion planning module to generate a correction strategy for the motion parameters of the autonomous driving vehicle, give a new motion planning result, and then use the controller to realize the lateral and longitudinal control of the vehicle, stop in front of the virtual wall in time, and thus avoid collision with dynamic obstacles.

[0279] For example, target motion parameters for the autonomous driving vehicle to avoid collision with obstacles can be generated based on the predicted vehicle posture of the autonomous driving vehicle and the information of the virtual wall. The target motion parameters may include the speed information of the autonomous driving vehicle. The virtual wall may be an abstract representation of an impassable area such as a vehicle ahead, an end point, a red light stop line, etc., indicating that the autonomous driving vehicle is not allowed to pass through. The virtual wall may include information on distance, speed, and time.

[0280] In an embodiment of the present application, by inputting motion planning trajectory information into the motion controller of the autonomous driving vehicle, the execution error of the autonomous driving vehicle when actually driving based on the motion planning trajectory can be simulated, thereby obtaining the vehicle posture of the autonomous driving vehicle during actual driving; by predicting the vehicle posture, the vehicle posture of the autonomous driving vehicle at future moments can be accurately obtained, thereby avoiding collisions between the autonomous driving vehicle and obstacles or pedestrians on the road, and ensuring the safety of the autonomous driving vehicle during driving.

[0281] In addition, when the on-board computing platform operates normally, important data information will be stored in the cache; when the data given by the computing platform is monitored to be abnormal, the cached data will be called to locate the vehicle by dead reckoning; at the same time, based on the parallel system safety protection module, the behavior planning method of the autonomous driving vehicle provided in the embodiment of the present application can accurately predict the position and posture of the autonomous driving vehicle, and predict the collision with the obstacle information in the cache, so that the autonomous driving vehicle can be planned to slow down and stop when there is a risk of collision with the autonomous driving vehicle, thereby ensuring the safety of the autonomous driving vehicle during driving.

[0282] Combination of the above Figures 1 to 14 , describes in detail the safety control method of the autonomous driving vehicle provided by the embodiment of the present application, and will now be combined with Figure 15 to Figure 16 , describes the device embodiment of the present application in detail. It should be understood that the safety control device in the embodiment of the present application can execute the safety control methods of various autonomous driving vehicles in the aforementioned embodiments of the present application, that is, the specific working processes of the following various products can refer to the corresponding processes in the aforementioned method embodiments.

[0283] Fig.15 is a schematic block diagram of a safety control device for an autonomous driving vehicle provided by an embodiment of the present application. It should be understood that Fig.15 The safety control device 800 shown is only an example, and the device of the embodiment of the present application may also include other modules or units. It should be understood that the safety control device 800 can perform Figures 7 to 14 To avoid repetition, the steps in the method are not described in detail here.

[0284] like Fig.15 As shown, the safety control device 800 may include an acquisition unit 810 and a processing unit 820, wherein the acquisition unit 810 is used to acquire the motion planning trajectory information of the autonomous driving vehicle, and the motion planning trajectory information refers to the planning trajectory information in the coordinate system where the autonomous driving vehicle is located; the processing unit 820 is used to obtain the predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle, and the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predict a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correct the motion planning trajectory.

[0285] Optionally, in a possible implementation manner, the processing unit 820 is further configured to:

[0286] Saving vehicle information of the autonomous driving vehicle, wherein the vehicle information includes planned trajectory information of the autonomous driving vehicle in a global coordinate system;

[0287] The acquisition unit 810 is specifically used for:

[0288] When the autonomous driving vehicle is detected to be in an abnormal state, obtaining the planned trajectory information of the autonomous driving vehicle in the global coordinate system from the stored vehicle information;

[0289] The planned trajectory information of the autonomous driving vehicle in the global coordinate system is transformed into the motion planning trajectory information.

[0290] Optionally, in a possible implementation manner, the vehicle information further includes driving position information of the autonomous driving vehicle, and the processing unit 820 is specifically configured to:

[0291] When it is detected that the autonomous driving vehicle is in an abnormal state, obtaining the current positioning information of the autonomous driving vehicle according to the driving position information, the state information of the autonomous driving vehicle and the dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the current speed of the autonomous driving vehicle, the current steering wheel angle, the current throttle control amount and the current brake control amount;

[0292] The acquisition unit 810 is specifically used for:

[0293] The motion planning trajectory information is obtained according to the current positioning information of the autonomous driving vehicle and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

[0294] Optionally, in a possible implementation manner, the processing unit 820 is further configured to:

[0295] Inputting the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain a control instruction, wherein the control instruction is used to instruct the adjustment of the steering wheel control amount, the throttle control amount, and the brake control amount of the autonomous driving vehicle;

[0296] Optionally, in a possible implementation manner, when the collision detection result indicates that the autonomous driving vehicle will collide with an obstacle, the processing unit 820 is further configured to:

[0297] When the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory information is corrected according to the vehicle posture when the autonomous driving vehicle is about to collide with the obstacle.

[0298] It should be noted that the above-mentioned safety control device 800 is embodied in the form of a functional unit. The term "unit" here can be implemented in the form of software and / or hardware, and is not specifically limited to this.

[0299] For example, a "unit" may be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a dedicated processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, a combined logic circuit, and / or other suitable components that support the described functions.

[0300] Therefore, the units of each example described in the embodiments of the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0301] Fig.16 It is a schematic diagram of the hardware structure of the safety control device for the autonomous driving vehicle provided in an embodiment of the present application.

[0302] like Fig.16 As shown, the safety control device 900 (the safety control device 900 may be a computer device) includes a memory 901, a processor 902, a communication interface 903 and a bus 904. The memory 901, the processor 902 and the communication interface 903 are connected to each other through the bus 904.

[0303] The memory 901 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 901 may store a program. When the program stored in the memory 901 is executed by the processor 902, the processor 902 is used to execute each step of the safety control method of the autonomous driving vehicle of the embodiment of the present application, for example, to execute Figures 7 to 14 The steps shown.

[0304] It should be understood that the safety control device of the autonomous driving vehicle shown in the embodiment of the present application may be a vehicle-mounted device, or may be a chip configured in the vehicle-mounted device.

[0305] Processor 902 can adopt a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC) or one or more integrated circuits to execute relevant programs to implement the safety control method of the autonomous driving vehicle of the method embodiment of the present application.

[0306] The processor 902 may also be an integrated circuit chip with signal processing capability. In the implementation process, each step of the safety control method of the autonomous driving vehicle of the present application may be completed by an integrated logic circuit of hardware in the processor 902 or by instructions in the form of software.

[0307] The processor 902 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, or the like. The storage medium is located in the memory 901, and the processor 902 reads the information in the memory 901, and completes the implementation of the present application in combination with its hardware. Fig.15 The functions required to be performed by the units included in the safety control device shown, or the functions required to perform the method embodiments of the present application Figures 7 to 14 The safety control method shown.

[0308] The communication interface 903 uses a transceiver device such as, but not limited to, a transceiver to implement communication between the security control device 900 and other devices or a communication network.

[0309] For example, the communication interface 903 can be used with Fig.15 Corresponding to the acquisition unit 810 in the safety control device shown, the information of the motion planning trajectory of the autonomous driving vehicle can be obtained through the communication interface 903.

[0310] The bus 904 may include a path for transmitting information between various components of the safety control device 900 (eg, the memory 901 , the processor 902 , and the communication interface 903 ).

[0311] It should be noted that although the above-mentioned safety control device 900 only shows a memory, a processor, and a communication interface, in the specific implementation process, those skilled in the art should understand that the safety control device 900 may also include other devices necessary for normal operation. At the same time, those skilled in the art should understand that according to specific needs, the above-mentioned safety control device 900 may also include hardware devices for realizing other additional functions.

[0312] In addition, those skilled in the art should understand that the above-mentioned safety control device 900 may also only include the components necessary to implement the embodiment of the present application, and does not necessarily include Fig.16 All devices shown in .

[0313] It should be understood that the above examples are intended to help those skilled in the art understand the embodiments of the present application, rather than to limit the embodiments of the present application to the specific numerical values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the above examples, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0314] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0315] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0316] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0317] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0318] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0319] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0320] In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0321] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0322] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A safety control method for an autonomous driving vehicle, characterized in that: include: Acquire motion planning trajectory information of the autonomous driving vehicle, wherein the motion planning trajectory information refers to planning trajectory information in the coordinate system where the autonomous driving vehicle is located; According to the motion planning trajectory information and the motion controller of the autonomous driving vehicle, a predicted vehicle posture of the autonomous driving vehicle is obtained, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; The step of obtaining a predicted vehicle posture of the autonomous driving vehicle based on the motion planning trajectory information and the motion controller of the autonomous driving vehicle includes: Inputting the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain a control instruction, wherein the control instruction is used to instruct the adjustment of the steering wheel control amount, the throttle control amount, and the brake control amount of the autonomous driving vehicle; Inputting the control command into a vehicle dynamics model to obtain the predicted vehicle posture; Predicting a collision detection result based on the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; When the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory information is corrected.

2. The safety control method according to claim 1, characterized in that: The safety control method further includes: Saving vehicle information of the autonomous driving vehicle, wherein the vehicle information includes planned trajectory information of the autonomous driving vehicle in a global coordinate system; The obtaining of motion planning trajectory information of the autonomous driving vehicle includes: When the autonomous driving vehicle is detected to be in an abnormal state, obtaining the planned trajectory information of the autonomous driving vehicle in the global coordinate system from the stored vehicle information; The planned trajectory information of the autonomous driving vehicle in the global coordinate system is transformed into the motion planning trajectory information.

3. The safety control method according to claim 2, characterized in that: The vehicle information also includes the driving position information of the autonomous driving vehicle. The safety control method also includes: When it is detected that the autonomous driving vehicle is in an abnormal state, obtaining the current positioning information of the autonomous driving vehicle according to the driving position information, the state information of the autonomous driving vehicle and a dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the current speed of the autonomous driving vehicle and the current steering wheel angle; The step of performing coordinate transformation according to the planned trajectory information of the autonomous driving vehicle in the global coordinate system to obtain the motion planning trajectory information includes: The motion planning trajectory information is obtained according to the current positioning information of the autonomous driving vehicle and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

4. The safety control method according to any one of claims 1 to 3, characterized in that: When the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, correcting the motion planning trajectory information includes: When the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory information is corrected according to the vehicle posture when the autonomous driving vehicle is about to collide with the obstacle.

5. A safety control device for an autonomous driving vehicle, characterized in that: include: An acquisition unit, configured to acquire motion planning trajectory information of the autonomous driving vehicle, wherein the motion planning trajectory information refers to planning trajectory information in a coordinate system where the autonomous driving vehicle is located; A processing unit, configured to obtain a predicted vehicle posture of the autonomous driving vehicle according to the motion planning trajectory information and the motion controller of the autonomous driving vehicle, wherein the predicted vehicle posture refers to the vehicle posture obtained by the motion controller executing the motion planning trajectory information; predict a collision detection result according to the predicted vehicle posture and obstacle information, wherein the collision detection result is used to indicate whether the autonomous driving vehicle will collide with an obstacle, and the obstacle information is used to indicate the obstacle; and correct the motion planning trajectory information when the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle; The processing unit is specifically used to: input the motion planning trajectory information into the motion controller of the autonomous driving vehicle to obtain a control instruction, wherein the control instruction is used to instruct the adjustment of the steering wheel control amount, the throttle control amount and the brake control amount of the autonomous driving vehicle; The control command is input into a vehicle dynamics model to obtain the predicted vehicle posture.

6. The safety control device according to claim 5, characterized in that: The processing unit is also used for: Saving vehicle information of the autonomous driving vehicle, wherein the vehicle information includes planned trajectory information of the autonomous driving vehicle in a global coordinate system; The acquisition unit is specifically used for: When the autonomous driving vehicle is detected to be in an abnormal state, obtaining the planned trajectory information of the autonomous driving vehicle in the global coordinate system from the stored vehicle information; The planned trajectory information of the autonomous driving vehicle in the global coordinate system is converted into the motion planning trajectory information.

7. The safety control device according to claim 6, characterized in that: The vehicle information also includes driving position information of the autonomous driving vehicle, and the processing unit is further used for: When it is detected that the autonomous driving vehicle is in an abnormal state, obtaining the current positioning information of the autonomous driving vehicle according to the driving position information, the state information of the autonomous driving vehicle and a dead reckoning algorithm, wherein the state information of the autonomous driving vehicle includes the current speed of the autonomous driving vehicle and the current steering wheel angle; The acquisition unit is specifically used for: The motion planning trajectory information is obtained according to the current positioning information of the autonomous driving vehicle and the planned trajectory information of the autonomous driving vehicle in the global coordinate system.

8. The safety control device according to any one of claims 5 to 7, characterized in that: The processing unit is specifically used for: When the collision detection result indicates that the autonomous driving vehicle will collide with the obstacle, the motion planning trajectory information is corrected according to the vehicle posture when the autonomous driving vehicle is about to collide with the obstacle.

9. A safety control device for an autonomous driving vehicle, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to call the program instructions to execute the safety control method according to any one of claims 1 to 4.

10. An autonomous driving vehicle, characterized in that: A safety control device comprising any one of claims 5 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, and when the program instructions are executed by a processor, the safety control method according to any one of claims 1 to 4 is implemented.

12. A chip, characterized in that: The chip includes a processor and a data interface, and the processor reads instructions stored in a memory through the data interface to execute the safety control method according to any one of claims 1 to 4.

Images