An automobile collision avoidance simulation control method, device, medium and equipment

Abstract

The application discloses a kind of automobile collision avoidance simulation control method, device, medium and equipment, it is related to automobile collision avoidance technical field, including the real-time position of automatic driving car and obstacle under different simulation driving scene type based on acquisition, the distance between automatic driving car and obstacle is determined;When distance is less than the distance radius of pre-set safety range, then collision behavior occurs, based on the number of collision behavior times total test times, determine collision probability;Collision probability includes the collision probability of deceleration straight, the collision probability of deceleration steering and the collision probability of constant speed steering;The collision probability of deceleration straight is set as P1, the collision probability of deceleration steering is set as P2, the collision probability of constant speed steering is set as P3, when P1

Description

Technical Field

[0001] The present invention relates to the field of automobile collision avoidance, in particular to a simulation control method, device, medium and equipment for automobile collision avoidance. Background Art

[0002] At present, automobile collision avoidance technology mainly relies on active braking systems to prevent vehicle rear-end collisions, which reduces collision accidents for vehicles driving in the same direction. However, in complex scenes involving vulnerable road users such as pedestrians or obstacles, especially when the distance between pedestrians and vehicles is less than the effective braking distance, it is impossible to effectively avoid collisions relying solely on braking, which leads to limitations in the decision-making ability of automobile collision avoidance. Summary of the Invention

[0003] The present invention provides a simulation control method, device, medium and equipment for automobile collision avoidance, so as to solve the above-mentioned problems existing in the prior art, that is, how to realize collision avoidance of autonomous vehicles in complex driving scenarios in the prior art. The present invention provides a simulation control method for automobile collision avoidance, which includes: Determining the distance between the autonomous vehicle and the obstacle based on the obtained real-time positions of the autonomous vehicle and the obstacle under different simulated driving scenario types; When the distance is less than a preset safety range distance radius, a collision occurs, and the collision probability is determined based on the ratio of the number of collisions to the total number of tests; the collision probability includes the collision probability of deceleration and straight driving, the collision probability of deceleration and turning, and the collision probability of constant speed turning; wherein, the collision probability of deceleration and straight driving is set as P1, the collision probability of deceleration and turning is set as P2, and the collision probability of constant speed turning is set as P3. When P1<P2 and P1<P3, the autonomous vehicle is controlled to decelerate and go straight; when P2<P1 and P2<P3, the autonomous vehicle is controlled to decelerate and turn; when P3<P1 and P3<P2, the autonomous vehicle is controlled to turn at constant speed.

[0004] Optionally, the obtaining of the real-time positions of the autonomous vehicle and the obstacle specifically includes: Based on the obtained initial position (x10, y10) of the autonomous vehicle and the initial speed v10 of the autonomous vehicle, the real-time position of the autonomous vehicle is obtained in the following manner: x1 t =x10+(v10*t+a1*t 2 / 2)cosθ; y1 t =y10+(v10*t+a1*t 2 / 2)sinθ; Based on the initial position (x20, y20) of the obstacle and the initial speed v20 of the obstacle, the real-time position of the obstacle is obtained in the following manner: x2 t =x20+(v20*t+a2*t 2 / 2)cosθ; y2 t =y20+(v20*t+a2*t 2 / 2)sinθ; Where t is the time interval between the autonomous vehicle detecting an obstacle and the most likely collision, θ is the angle between the line connecting the autonomous vehicle and the obstacle and the horizontal direction, and x1 t and y1 t These represent the current real-time lateral and longitudinal positions of the autonomous vehicle, respectively, x2 t and y2 t These represent the current real-time lateral and longitudinal positions of the obstacle, respectively, while a1 and a2 represent the accelerations of the autonomous vehicle and the obstacle during their movement, respectively.

[0005] Optionally, obtaining the distance between the autonomous vehicle and the obstacle specifically includes: Distance = sqrt((x1) t -x2 t ) 2 +(y1 t -y2 t ) 2 ); Where Distance is the distance between the autonomous vehicle and the obstacle, and sqrt represents solving for the square root.

[0006] Optionally, multiple feature parameters can be obtained under different simulated driving scenario types; wherein, the multiple feature parameters include the speed of the autonomous vehicle, the speed of the obstacle, and the acceleration of the autonomous vehicle and the obstacle; Multiple feature parameters are sampled using a uniform or normal distribution to determine the sampled feature parameters; based on the sampled feature parameters, the real-time positions of the autonomous vehicle and obstacles are determined.

[0007] Optionally, the standard deviation of the normal distribution is 0.3 to 0.5.

[0008] Optionally, the simulated driving scenario types specifically include: Single-lane obstacle scenarios, two-lane obstacle scenarios, and multi-lane obstacle scenarios.

[0009] Optionally, the preset safety range radius is 2.5 meters.

[0010] This invention provides a vehicle collision avoidance simulation control device to implement the above-mentioned vehicle collision avoidance simulation control method.

[0011] The present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described vehicle collision avoidance simulation control method.

[0012] The present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described vehicle collision avoidance simulation control method.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a vehicle collision avoidance simulation control method. This method calculates the collision probability of various collision avoidance behaviors by statistically analyzing the number of collisions of different collision avoidance behaviors, and saves the scene type and collision probability. Based on the principle of minimizing the collision probability, the collision avoidance behavior in the actual scene is determined, thereby realizing collision avoidance of autonomous vehicles in complex driving scenarios. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0015] Figure 1 A flowchart of a vehicle collision avoidance simulation control method provided in an embodiment of the present invention; Figure 2 A technical roadmap for a vehicle collision avoidance simulation control method provided in this embodiment of the invention; Figure 3 This is a schematic diagram of a collision avoidance scenario provided in an embodiment of the present invention; Figure 4 A schematic diagram of a computer device for a car collision avoidance simulation control method provided in an embodiment of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0017] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0018] Figure 1This is a flowchart of a vehicle collision avoidance simulation control method provided in an embodiment of the present invention, such as... Figure 1 As shown in the figure, this embodiment illustrates a vehicle collision avoidance simulation control method, including: S1: Based on the real-time positions of autonomous vehicles and obstacles under different simulated driving scenario types, determine the distance between autonomous vehicles and obstacles.

[0019] For example, this embodiment can design various training scenarios based on characteristic parameters, such as the distance between the vehicle and obstacles, vehicle speed, ground coefficient, and obstacles on the lane, and select and design relevant parameters for various collision avoidance behaviors. For example, for decelerating straight, it is necessary to select and design parameters such as the initial position, speed, acceleration, and ground coefficient of the vehicle and obstacles; for decelerating steering, in addition to the above parameters, it is also necessary to add parameters such as steering angle, and ensure that the steering angle is small to avoid rollover; for constant speed steering, it is also necessary to consider parameters such as position, speed, ground coefficient, and steering angle, but the steering angle is larger. The relevant parameters are randomly distributed. For example, the initial position of the obstacle can be centered on the vehicle, with the initial longitudinal position X of the obstacle distributed in Uniform(1,100) and the lateral position Y distributed in Uniform(0,3.5). The speed of the vehicle and the moving obstacle is also randomly distributed in Uniform(V). min V max The vehicle acceleration a1 is set to a normal distribution N (u=1.0, σ=0.3), and the aggressive case is a normal distribution (u=2.0, σ=0.5). The acceleration a2 of the moving obstacle is also set to a normal distribution N (u=0.7, σ=0.3). The deceleration steering angle θ is set to a uniform (0, 10°) random distribution. The average speed steering angle θ is also set to a uniform (0, 90°) random distribution.

[0020] For example, the acquisition of the real-time location of the autonomous vehicle and obstacles specifically includes: Based on the initial position (x10, y10) and initial velocity v10 of the autonomous vehicle, the real-time position of the autonomous vehicle is obtained in the following manner: x1 t =x10+(v10*t+a1*t 2 / 2)cosθ; y1 t =y10+(v10*t+a1*t 2 / 2)sinθ; Based on the obstacle's initial position (x20, y20) and initial velocity v20, the obstacle's real-time position is obtained as follows: x2t =x20+(v20*t+a2*t 2 / 2)cosθ; y2 t =y20+(v20*t+a2*t 2 / 2)sinθ; wherein, t is the time interval between the detection of an obstacle by the autonomous driving vehicle and the maximum possible collision, θ is the included angle between the connecting line of the autonomous driving vehicle and the obstacle and the horizontal direction, x1 t and y1 t respectively represent the current real-time lateral and longitudinal positions of the autonomous driving vehicle, x2 t and y2 t respectively represent the current real-time lateral and longitudinal positions of the obstacle, a1 and a2 are respectively the accelerations of the autonomous driving vehicle and the obstacle during movement.

[0021] Exemplarily, acquiring the distance between the autonomous driving vehicle and the obstacle specifically comprises: Distance=sqrt((x1 t -x2 t ) 2 +(y1 t -y2 t ) 2 ); wherein, Distance is the distance between the autonomous driving vehicle and the obstacle, sqrt represents square root calculation.

[0022] S2: when the distance is less than a preset safety range distance radius, a collision occurs, and the collision probability is determined based on the ratio of the number of collision occurrences to the total number of tests; the collision probabilities comprise a collision probability of decelerating and going straight, a collision probability of decelerating and turning, and a collision probability of turning at constant speed; wherein, the collision probability of decelerating and going straight is set as P1, the collision probability of decelerating and turning is set as P2, and the collision probability of turning at constant speed is set as P3, when P1<P2 and P1<P3, the autonomous driving vehicle is controlled to decelerate and go straight; when P2<P1 and P2<P3, the autonomous driving vehicle is controlled to decelerate and turn; when P3<P1 and P3<P2, the autonomous driving vehicle is controlled to turn at constant speed.

[0023] Exemplarily, when the distance between the autonomous driving vehicle and the obstacle is less than the preset safety range distance radius (generally set to 2.5 meters), the scenario is considered to have a collision; otherwise, no collision occurs; for each of the foregoing scenarios, the set number of tests is 100,000 times, the number of collisions is counted, and the collision probability under each collision avoidance behavior is calculated as shown in the following formula, and the feature parameters of the training scenario and the collision probability are saved; Collision probability P=(number of counted collisions / 100,000)*100%.

[0024] As Figure 2 shown, the automatic driving vehicle detection system detects and measures parameters such as the performance of the automatic driving vehicle and the surrounding environment, including vehicle speed, types, speeds and quantities of obstacles, and longitudinal and lateral distances between the vehicle and obstacles, to obtain relevant parameter values; then, the scene type is determined according to the parameter values of the scene, such as long-distance vehicle-obstacle scene (>100m), medium-distance scene (50m<s<100m) and short-distance scene (<50m); scenes can also be classified according to the number of obstacles in the lane, such as single-lane obstacle, two-lane obstacle and multi-lane obstacle scenes; finally, according to the actual scene type, the collision probabilities of various collision avoidance behaviors under this type of scene stored in the automatic driving vehicle are obtained, the collision avoidance behavior with the minimum collision probability is selected for execution and operation, the actual collision avoidance result data is saved, and the collision probability data in the training stage is further improved.

[0025] Taking Figure 3 the illustrated scene as an example, first, the automatic driving vehicle detection system determines the scene type based on parameters including vehicle speed, longitudinal and lateral distances between the vehicle and the pedestrian, vehicle acceleration, as well as pedestrian position, running speed and acceleration, for example, whether the scene belongs to a long-distance, medium-distance or short-distance type scene. Then, after the scene type is determined, according to the collision probabilities of various collision avoidance behaviors in the training scene, the collision probability of decelerating and going straight is 20%, the collision probability of decelerating and steering is 30%, and the collision probability of constant-speed steering is 25%. Therefore, according to the principle of minimum collision probability, decelerating and going straight is selected to determine the collision avoidance behavior; finally, the automatic driving vehicle executes the determined collision avoidance behavior: decelerating and going straight, so as to avoid collision to the maximum extent possible.

[0026] The above is one or more embodiments of the present specification provide a vehicle collision avoidance simulation control method. Based on the same concept, the present specification also provides a corresponding vehicle collision avoidance simulation control device. For specific limitations on the vehicle collision avoidance simulation control system, reference may be made to the above limitations on the vehicle collision avoidance simulation control method, which will not be repeated herein. All or part of each module in the above vehicle collision avoidance simulation control device can be implemented by software, hardware and combinations thereof. The above modules can be embedded in or independent of a processor in computer equipment in the form of hardware, or stored in a memory in computer equipment in the form of software, so that a processor can call and execute operations corresponding to the above modules.

[0027] The present invention also provides a computer-readable storage medium, which stores a computer program, and the computer program can be used to execute the above-provided vehicle collision avoidance simulation control method.

[0028] The present invention also provides Figure 4 a structural schematic diagram of the illustrated computer device, as Figure 4As shown, at the hardware level, the computer device includes a processor, an internal bus, a network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to implement the vehicle collision avoidance simulation control method provided in the above embodiment.

[0029] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0030] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this invention.

Claims

1. A vehicle collision avoidance simulation control method, characterized in that, Comprising: determining the distance between the autonomous driving vehicle and an obstacle based on obtained real-time positions of the autonomous driving vehicle and the obstacle under different simulated driving scenario types; when the distance is less than a preset safe range distance radius, a collision behavior is determined to occur, and a collision probability is determined based on a ratio of the number of collision behaviors to the total number of tests; said collision probabilities comprise a collision probability for decelerating straight traveling, a collision probability for decelerated steering and a collision probability for constant-speed steering; wherein, the collision probability for decelerating straight traveling is set as P1, the collision probability for decelerated steering is set as P2, and the collision probability for constant-speed steering is set as P3, when P1<P2 and P1<P3, the autonomous driving vehicle is controlled to travel straight while decelerating; when P2<P1 and P2<P3, the autonomous driving vehicle is controlled to steer while decelerating; when P3<P1 and P3<P2, the autonomous driving vehicle is controlled to steer at a constant speed.

2. The vehicle collision avoidance simulation control method as described in claim 1, characterized in that, obtaining the real-time positions of the autonomous driving vehicle and the obstacle specifically comprises: based on the obtained initial position (x10, y10) and initial speed v10 of the autonomous driving vehicle, obtaining the real-time position of the autonomous driving vehicle by adopting the following method: x1 t =x10+(v10*t+a1*t 2 / 2)cosθ; y1 t =y10+(v10*t+a1*t 2 / 2)sinθ; based on the initial position (x20, y20) and initial speed v20 of the obstacle, obtaining the real-time position of the obstacle by adopting the following method: x2 t =x20+(v20*t+a2*t 2 / 2)cosθ; y2 t =y20+(v20*t+a2*t 2 / 2)sinθ; Where t is the time interval between the autonomous vehicle detecting an obstacle and the most likely collision, θ is the angle between the line connecting the autonomous vehicle and the obstacle and the horizontal direction, and x1 t and y1 t These represent the current real-time lateral and longitudinal positions of the autonomous vehicle, respectively, x2 t and y2 t These represent the current real-time lateral and longitudinal positions of the obstacle, respectively, while a1 and a2 represent the accelerations of the autonomous vehicle and the obstacle during their movement, respectively.

3. The vehicle collision avoidance simulation control method as described in claim 2, characterized in that, obtaining the distance between the autonomous driving vehicle and the obstacle specifically comprises: Distance=sqrt((x1 t -x2 t ) 2 +(y1 t -y2 t ) 2 ); wherein, Distance is the distance between the autonomous driving vehicle and the obstacle, and sqrt represents square root calculation.

4. The vehicle collision avoidance simulation control method as described in claim 1, characterized in that, obtaining a plurality of characteristic parameters under different simulated driving scenario types; wherein the plurality of characteristic parameters comprise the vehicle speed of the autonomous driving vehicle, the obstacle speed, and the accelerations of the autonomous driving vehicle and the obstacle; performing uniform distribution sampling or normal distribution sampling on the plurality of characteristic parameters to determine sampled characteristic parameters; and determining the real-time positions of the autonomous driving vehicle and the obstacle based on the sampled characteristic parameters.

5. The vehicle collision avoidance simulation control method as described in claim 4, characterized in that, the standard deviation of said normal distribution is 0.3 to 0.

5.

6. The vehicle collision avoidance simulation control method as described in claim 1, characterized in that, said simulated driving scenario types specifically comprise: single-lane obstacle scenarios, dual-lane obstacle scenarios and multi-lane obstacle scenarios.

7. The vehicle collision avoidance simulation control method as described in claim 1, characterized in that, said preset safe range distance radius is 2.5 meters.

8. A car collision avoidance simulation control device, characterized in that, implementing the vehicle collision avoidance simulation control method according to any one of the preceding claims 1 to 7.

9. A computer-readable storage medium, characterized in that, said storage medium stores a computer program, and when executed by a processor, the computer program implements the vehicle collision avoidance simulation control method according to any one of the preceding claims 1 to 7.

10. A computer device, characterized in that, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the vehicle collision avoidance simulation control method according to any one of the preceding claims 1 to 7 is implemented.

Images