Boundary analysis method, system and equipment for processing nearby obstacles and medium

Abstract

The invention discloses a boundary analysis method, system and equipment for processing nearby obstacles and a medium, the boundary of the dynamic obstacles is obtained by screening and processing the dynamic obstacles, and the boundary of the dynamic obstacles is compared with a default boundary to obtain a final boundary. Path planning is carried out based on the boundary to obtain a planned path of the vehicle in the current environment, the vehicle runs according to the planned path, and the automatic driving safety and the operation efficiency of the vehicle are improved; in addition, the method can generate more reasonable left and right boundaries, and ensures that the vehicle does not collide with a nearby dynamic obstacle in the automatic driving process; the current position of a near dynamic obstacle and the position of a period of time in the future are analyzed, the purpose of lane keeping and even avoiding is achieved through a boundary cutting method, and the habit of manual driving is met; the scheme has important technical value and application prospect in the aspects of improving the stability, the safety, the humanoid property and the like of the automatic driving system.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving, and specifically relates to a boundary analysis method, system, device and medium for processing nearby obstacles. Background Art

[0002] In modern autonomous driving technology, trajectory planning, as a module that directly faces all autonomous driving scenarios, plays a decisive role in the overall safety and passability of the vehicle. In the field of commercial vehicle autonomous driving, some moving obstacles are often encountered. When some trajectory optimization methods do not properly handle some dynamic obstacles around the vehicle, the vehicle may unexpectedly stop or even have a collision risk, which greatly reduces the operating efficiency and may even cause traffic accidents. The safety and comfort of the vehicle cannot be guaranteed, which is absolutely unacceptable. Therefore, for this problem of nearby obstacles, corresponding boundary analysis methods are needed. Summary of the invention

[0003] In view of the above problems, the main purpose of the present invention is to design a boundary analysis method, system, device and medium for processing nearby obstacles. By adding the process of screening dynamic obstacles and analyzing the boundaries of dynamic obstacles, the problems of unexpected braking and collision with nearby obstacles and low operating efficiency during intelligent driving are solved.

[0004] In order to achieve the above purpose, the present invention adopts the following technical solutions: A boundary parsing method for processing nearby obstacles, the method comprising the following steps: S1: Based on the information upstream of the ego vehicle, make the first observation and determine whether the ego vehicle needs to perform dynamic obstacle analysis; The conditions for dynamic obstacle analysis are: the vehicle is in intelligent driving mode and can obtain its position, the vehicle lane and the left and right lanes have lane center lines, which are reference lines, and there are dynamic obstacles with predicted trajectories within a preset time in the future; S2: Based on the information upstream of the ego vehicle, the dynamic obstacles whose boundaries need to be processed are screened, and the dynamic obstacles are processed to obtain the boundaries of the dynamic obstacles; S3: Solve the dynamic obstacle boundary obtained in step S2 to obtain the path planning trajectory of the vehicle; S4: The vehicle receives the trajectory planning solved in step S3, and drives to avoid dynamic obstacles based on the trajectory planning.

[0005] As a further description of the present invention, in step S1, the information upstream of the ego vehicle includes: the location of the ego vehicle; the status of the ego vehicle; whether the ego vehicle lane and the left and right lane reference lines exist; whether the obstacle is dynamic and there is a predicted trajectory line for the ego vehicle within a preset time in the future; whether the ego vehicle task management module has issued the driving task normally.

[0006] As a further description of the present invention, in step S2, screening dynamic obstacles includes the following steps: S201: According to the position of the ego vehicle, the lane in which the ego vehicle is traveling is obtained, and according to the reference line information, the reference line closest to the ego vehicle is selected, and based on the reference line closest to the ego vehicle, the reference lines of the left and right lanes are queried to obtain the position information of all dynamic obstacles on the reference lines of the left and right lanes; S202: judging the positional relationship between the dynamic obstacle and the vehicle according to the position of the dynamic obstacle; If the dynamic obstacle is not on the left side of the left reference line or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the left side of the vehicle; If the dynamic obstacle is not on the right side of the right reference line, or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the right side of the vehicle; S203: Segment the predicted trajectory of the dynamic obstacle into time segments, and obtain the position of the dynamic obstacle in each time segment, including the position of the dynamic obstacle at the start time and the end time; S204: Compare the positions of the ego vehicle and the dynamic obstacle in a set time period to determine whether the ego vehicle and the dynamic obstacle have an overlapping relationship in the same time period; S205: When the ego vehicle and the dynamic obstacles overlap, the number of all dynamic obstacles is increased by one. When the number of the dynamic obstacles is zero, there is no dynamic obstacle near the ego vehicle and no processing is required.

[0007] As a further description of the present invention, the comparison method between the ego vehicle and the dynamic obstacle in step S204 is that within a preset time period, the longitudinal projection of the dynamic obstacle from the front end to the rear end on the reference line of the ego vehicle lane intersects with the longitudinal projection of the ego vehicle from the rear end to the front end on the reference line, that is, if the dynamic obstacle and the ego vehicle partially overlap in the longitudinal direction of the reference line of the ego vehicle lane, then the ego vehicle and the dynamic obstacle overlap within the time period.

[0008] As a further description of the present invention, in step S2, processing the dynamic obstacle to obtain the boundary of the dynamic obstacle includes the following steps: S211: Based on steps S201-S202, the position information of all dynamic obstacles on the left and right lane reference lines is obtained; S212: For each left and right dynamic obstacle, the longitudinal projection distance of the rear end of the obstacle on the reference line at the start time of the time period is used as the longitudinal starting point for processing the dynamic obstacle boundary, and the longitudinal projection distance of the front end of the obstacle on the reference line at the end time of the time period is used as the longitudinal end point for processing the dynamic obstacle boundary, and the left longitudinal starting point, the right longitudinal starting point, the left longitudinal end point, and the right longitudinal end point are obtained respectively; S213: For the left dynamic obstacle, the lateral projection distance of its right side on the reference line is used as the lateral value for processing the dynamic obstacle. For the right dynamic obstacle, the lateral projection distance of its left side on the reference line is used as the lateral value for processing the dynamic obstacle, thereby obtaining a left lateral value and a right lateral value. S214: generating a left boundary based on the dynamic obstacle according to the determined left longitudinal starting point, left longitudinal end point and left lateral value, and generating a right boundary based on the dynamic obstacle according to the determined right longitudinal starting point, right longitudinal end point and right lateral value; Among them, if any point on the reference line is selected as the origin, the left boundary is positive and the right boundary is negative. The value of the left boundary becomes larger as it moves away from the reference line to the left, and the value of the right boundary becomes smaller as it moves away from the reference line to the right. S215: Compare the left boundary and right boundary generated in step S214 with the default left boundary and right boundary of the dynamic obstacle: if the left boundary generated in step S214 is larger than the default left boundary, the default left boundary is selected as the final left boundary; otherwise, the generated left boundary is selected as the final left boundary; if the right boundary generated in step S214 is larger than the default right boundary, the generated right boundary is selected as the final right boundary; otherwise, the default right boundary is selected as the final right boundary.

[0009] As a further description of the present invention, in step S3, the final left boundary and the final right boundary are both used as inputs, and solved by a solver to obtain a planned path of the vehicle in the current environment.

[0010] A boundary resolution system for processing nearby obstacles, comprising: The upstream module is used to obtain perception, reference lines, vehicle status and task management status; The observation module is used to observe the road conditions of the vehicle lane and the left and right lanes based on the information obtained by the upstream module, and determine whether dynamic obstacles need to be handled; The boundary analysis module is used to process the dynamic obstacles on the left and right sides of the vehicle lane, screen the dynamic obstacles that need to be processed, and process them to obtain the boundaries of the dynamic obstacles; The planning and solving module is used to plan the trajectory of the vehicle path according to the boundary obtained by the boundary analysis module; The control module is used for the vehicle to perform avoidance driving according to the path planning of the planning and solving module.

[0011] An electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus, and the memory is used to store a computer program; The processor is used to execute the above method by running the computer program stored in the memory.

[0012] A computer-readable storage medium stores a computer program, wherein the computer program implements the above method when executed by a processor.

[0013] Compared with the prior art, the technical effects of the present invention are: The present invention provides a boundary parsing method, system, device and medium for processing nearby obstacles. The method obtains the boundary of the dynamic obstacle by screening and processing the dynamic obstacle, compares the boundary of the dynamic obstacle with the default boundary, obtains the final driving boundary of the self-vehicle in the current environment, performs path planning based on the boundary, obtains the planned path of the self-vehicle in the current environment, and the self-vehicle travels according to the planned path to avoid dynamic obstacles, thereby improving the safety of automatic driving when there are dynamic obstacles around the vehicle, and ensuring safety and comfort while improving the operation efficiency of automatic driving; in addition, the method for parsing nearby dynamic obstacles can generate more reasonable left and right boundaries, ensure that the vehicle does not collide with nearby dynamic obstacles during the automatic driving process, improve driving safety, parse the current position of the nearby dynamic obstacle and the position in the future, and achieve the purpose of lane keeping and even avoidance through the method of boundary clipping, which is in line with the habit of manual driving. The method has important technical value and application prospects for improving the stability, safety and human nature of the automatic driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 It is a schematic diagram of the interaction between the modules in the overall system of the present invention; Figure 3 is a position relationship diagram of the ego vehicle and the obstacle vehicle at a certain moment in the method of the present invention; Figure 4 A schematic diagram of processing a left-side dynamic obstacle in the method of the present invention; Figure 5 It is a schematic diagram of processing the dynamic obstacle on the right side in the method of the present invention. DETAILED DESCRIPTION

[0015] The present invention is described in detail below in conjunction with the accompanying drawings: In one embodiment of the present invention, a boundary parsing method for processing nearby obstacles is disclosed, referring to Figure 1 As shown, the method includes the following process: S1: Based on the information upstream of the ego vehicle, make the first observation and determine whether the ego vehicle needs to perform dynamic obstacle analysis; The conditions for dynamic obstacle analysis are: the vehicle is in intelligent driving mode and can obtain its position, the vehicle lane and the left and right lanes have lane center lines, which are reference lines, and there are dynamic obstacles with predicted trajectories within a preset time in the future; S2: Based on the information upstream of the ego vehicle, the dynamic obstacles whose boundaries need to be processed are screened, and the dynamic obstacles are processed to obtain the boundaries of the dynamic obstacles; S3: Solve the dynamic obstacle boundary obtained in step S2 to obtain the path planning trajectory of the vehicle; S4: The vehicle receives the trajectory planning solved in step S3, and drives to avoid dynamic obstacles based on the trajectory planning.

[0016] Specifically, in this embodiment, in step S1, the information upstream of the ego vehicle includes: the location of the ego vehicle; the state of the ego vehicle; whether the reference lines of the ego vehicle lane and left and right lanes exist; whether the obstacle is dynamic and there is a predicted trajectory line for the ego vehicle within a preset time (10s) in the future; whether the ego vehicle task management module normally issues the driving task; for the first observation, based on the input original lane center position information (x, y and other coordinates), a series of lane center points that meet the kinematic constraints are calculated through the vehicle's kinematic equations, and the set of these points is the reference line. Then, the positional relationship between the ego vehicle and the reference line is determined based on the ego vehicle position in the intelligent driving state input from the upstream, and the reference line closest to the ego vehicle is obtained. If the obstacle output by the upstream contains a vehicle speed greater than 5 km / h, it is considered to be a dynamic obstacle. Then observe whether the upstream gives a predicted trajectory line within the next 10 seconds. Combined with the vehicle position, find the reference line coordinates on the left and right sides of the vehicle and the lane width information, and compare the coordinate points of the dynamic obstacle. If the center of the dynamic obstacle is within the range of the left lane or the right lane, the dynamic obstacle is considered to be valid and meets the basic conditions for processing dynamic obstacles. Then, the boundary resolution method of processing nearby obstacles in this embodiment is used.

[0017] In this embodiment, the first step of processing dynamic obstacles is to screen all dynamic obstacles whose boundaries need to be processed. Specifically, in step S2, screening dynamic obstacles includes the following steps: S201: According to the position of the ego vehicle, the lane in which the ego vehicle is traveling is obtained, and according to the reference line information, the reference line closest to the ego vehicle is selected, and based on the reference line closest to the ego vehicle, the reference lines of the left and right lanes are queried to obtain the position information of all dynamic obstacles on the reference lines of the left and right lanes; S202: judging the positional relationship between the dynamic obstacle and the vehicle according to the position of the dynamic obstacle; If the dynamic obstacle is not on the left side of the left reference line or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the left side of the vehicle; If the dynamic obstacle is not on the right side of the right reference line, or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the right side of the vehicle; S203: Segment the predicted trajectory of the dynamic obstacle into time segments, and obtain the position of the dynamic obstacle in each time segment, including the position of the dynamic obstacle at the start time and the end time; S204: Compare the positions of the ego vehicle and the dynamic obstacle in a set time period to determine whether the ego vehicle and the dynamic obstacle have an overlapping relationship in the same time period; S205: When the ego vehicle and the dynamic obstacles overlap, the number of all dynamic obstacles is increased by one. When the number of the dynamic obstacles is zero, there is no dynamic obstacle near the ego vehicle and no processing is required.

[0018] Assume that the trajectory time (seconds) required for dynamic obstacle prediction is [0, 5], and the Fibonacci sequence is divided into 9 time periods with an interval of 0.1. Each time period contains the start and end time of the time period. The obstacle positions in the 9 time periods of [0, 5] seconds on the predicted trajectory are obtained as follows: (0, 0.1], (0.1, 0.2], (0.2, 0.3], (0.3, 0.5], (0.5, 0.8], (0.8, 1.3], (1.3, 2.1], (2.1, 3.4], (3.4, 5], and then compare the position of the vehicle in the corresponding time period with the position of the dynamic obstacle at the same time to determine whether there is an overlapping relationship in time and space, such as Figure 3 As shown in Figure 1, it is the position relationship between the ego vehicle and the obstacle vehicle at a certain moment.

[0019] Specifically, in this embodiment, the comparison method between the ego vehicle and the dynamic obstacle in the above step S204 is that within a preset time period, the longitudinal projection of the dynamic obstacle from the front end to the rear end on the reference line of the ego vehicle lane intersects with the longitudinal projection of the ego vehicle from the rear end to the front end on the reference line, that is, if the dynamic obstacle and the ego vehicle partially overlap in the longitudinal direction of the reference line of the ego vehicle lane, then the ego vehicle and the dynamic obstacle overlap within the time period.

[0020] In this embodiment, the second step of processing the dynamic obstacles is to process the boundaries of all the near dynamic obstacles obtained by the above screening. Specifically, in step S2, processing the dynamic obstacles to obtain the boundaries of the dynamic obstacles includes the following steps: 1. Left border processing, such as Figure 4 As shown: S211-L: Based on steps S201-S202, obtain the position information of all dynamic obstacles on the left lane reference line; S212-L: For each left dynamic obstacle, the longitudinal projection distance of its rear end on the reference line at the start time of the time period is used as the longitudinal starting point for processing the dynamic obstacle boundary, and the longitudinal projection distance of its front end on the reference line at the end time of the time period is used as the longitudinal end point for processing the dynamic obstacle boundary, and the left longitudinal starting point and left longitudinal end point are obtained respectively; S213-L: The lateral projection distance of the right side of the left dynamic obstacle on the reference line is used as the lateral value for processing the dynamic obstacle to obtain the left lateral value; S214-L: Generate a left boundary based on the dynamic obstacle according to the determined left longitudinal starting point, left longitudinal end point and left lateral value; Among them, if any point on the reference line is selected as the origin, the left boundary is positive, and the value of the left boundary becomes larger as it moves away from the reference line to the left; S215-L: Compare the left boundary generated in step S214-L with the default left boundary of the dynamic obstacle. If the left boundary generated in step S214-L is larger than the default left boundary, the default left boundary is selected as the final left boundary. Otherwise, the generated left boundary is selected as the final left boundary.

[0021] 2. Right boundary processing, such as Figure 5 As shown: S211-R: Based on steps S201-S203, obtain the position information of all dynamic obstacles on the right lane reference line; S212-R: For each right-side dynamic obstacle, the longitudinal projection distance of its rear end on the reference line at the start time of the time period is used as the longitudinal starting point for processing the dynamic obstacle boundary, and the longitudinal projection distance of its front end on the reference line at the end time of the time period is used as the longitudinal end point for processing the dynamic obstacle boundary, to obtain the right-side longitudinal starting point and the right-side longitudinal end point respectively; S213-R: The lateral projection distance of the left side of the right dynamic obstacle on the reference line is used as the lateral value for processing the dynamic obstacle to obtain the right lateral value; S214-R: Generate a right boundary based on the dynamic obstacle according to the determined right longitudinal start point, right longitudinal end point and right lateral value; Among them, if any point on the reference line is selected as the origin, the right boundary is negative, and the value becomes smaller as it moves away from the right boundary of the reference line. S215-R: Compare the right boundary generated in step S214-R with the default right boundary of the dynamic obstacle. If the right boundary generated in step S214-R is greater than the default right boundary, the generated right boundary is selected as the final right boundary; otherwise, the default right boundary is selected as the final right boundary.

[0022] In this embodiment, in the above step S3, the final left boundary and the final right boundary are both used as feasible areas of the trajectory, and the lateral distance of the trajectory point from the nearest reference line of the vehicle is set as a constraint to obtain a trajectory that satisfies kinematics and has smooth curvature as the final planned path.

[0023] It should be noted that the above-mentioned solution method is not limited to one, and also includes any solution method in the prior art that can obtain a planned path through input.

[0024] Through the above content, a boundary parsing method for processing nearby obstacles is disclosed, which has the following advantages over the prior art: 1. The present invention obtains the planned path of the vehicle in the current environment, and the vehicle drives according to the planned path to avoid dynamic obstacles, thereby improving the safety of automatic driving when there are dynamic obstacles around the vehicle, ensuring safety and comfort while improving the efficiency of automatic driving operation; 2. The method for analyzing nearby dynamic obstacles of the present invention can generate more reasonable left and right boundaries, ensuring that the vehicle does not collide with nearby dynamic obstacles during the automatic driving process, thereby improving driving safety; 3. The present invention achieves the purpose of lane keeping or even avoidance by analyzing the current position of nearby dynamic obstacles and their positions in the future through boundary clipping, which is in line with the habits of manual driving.

[0025] In this embodiment, the above-mentioned boundary analysis method for processing nearby obstacles has important technical value and application prospects for improving the stability, safety and human-likeness of the autonomous driving system.

[0026] In another embodiment of the present invention, a boundary resolution system for processing nearby obstacles is disclosed, referring to Figure 2 As shown, the system includes: The upstream module is used to obtain perception, reference lines, vehicle status and task management status; The observation module is used to observe the road conditions of the vehicle lane and the left and right lanes based on the information obtained by the upstream module, and determine whether dynamic obstacles need to be handled; The boundary analysis module is used to process the dynamic obstacles on the left and right sides of the vehicle lane, screen the dynamic obstacles that need to be processed, and process them to obtain the boundaries of the dynamic obstacles; The planning and solving module is used to plan the trajectory of the vehicle path according to the boundary obtained by the boundary analysis module; The control module is used for the vehicle to perform avoidance driving according to the path planning of the planning and solving module.

[0027] It should be noted that based on the information obtained by the upstream module, according to the vehicle status, reference line, obstacle status and task management status, it is observed whether the planning and solving module is needed for trajectory planning and trajectory optimization; if the status of the upstream modules is normal, the boundary analysis module of dynamic obstacles will work if: there are reference lines between the vehicle and the adjacent lanes, and there are dynamic obstacles near the vehicle. If all the above conditions are met, the boundary analysis module will perform special processing on the dynamic obstacle boundary before trajectory optimization; finally, the boundary after dynamic obstacle processing is sent to the planning and solving module for optimization. Compared with the trajectory without the boundary analysis module, the optimized trajectory can avoid dynamic obstacles and improve safety.

[0028] In another embodiment of the present invention, an electronic device is also included. The electronic device may include a processor and a memory storing computer program instructions.

[0029] Specifically, in this embodiment, the processor may include a central processing unit (CPU), or a specific integrated circuit, or may be configured as one or more integrated circuits of this embodiment; the memory may include a large-capacity memory for data or instructions, including but not limited to a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these; where appropriate, the memory may include a removable or non-removable (or fixed) medium; in a specific embodiment, the memory is a non-volatile solid-state memory. In a specific embodiment, the memory includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0030] The processor implements the boundary parsing method disclosed above in the present invention by reading and executing computer program instructions stored in the memory.

[0031] It should also be noted that the electronic device of this embodiment may also include a communication interface and a communication bus. Among them, the processor, memory, and communication interface are connected through the communication bus and communicate with each other. The communication interface is mainly used to realize the communication between the various units, modules, devices or equipment in the embodiment of the present invention.

[0032] The communication bus mentioned above includes hardware, software or a combination of hardware and software, coupling the components of the online data flow device to each other. Where appropriate, the communication bus may include one or more buses.

[0033] In addition, in combination with the boundary parsing method in the above embodiment, the embodiment of the present invention can be implemented by providing a computer storage medium, on which computer program instructions are stored; the computer program instructions are executed by a processor to execute the above boundary parsing method.

[0034] It should be clear that the present invention is not limited to the methods, systems, and devices disclosed above, but also includes various changes, modifications, and additions made by those skilled in the art based on the ideas of the present invention, or changes in the order of steps.

[0035] When the present invention is implemented in hardware, it can be an electronic circuit, a dedicated integrated circuit, appropriate firmware, plug-in, function card, etc.; when implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks, and the programs or code segments can be stored in a machine-readable medium, or uploaded on a transmission medium or communication link through a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information, such as: electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, optical disks, hard disks, optical fiber media, radio frequency links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0036] The above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in this field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.

Claims

1. A boundary analysis method for processing nearby obstacles, characterized in that: The method comprises the following steps: S1: Based on the information upstream of the ego vehicle, make the first observation and determine whether the ego vehicle needs to perform dynamic obstacle analysis; The conditions for dynamic obstacle analysis are: the vehicle is in intelligent driving state and the location of the vehicle can be obtained; The vehicle lane and the left and right lanes all have lane center lines, which are reference lines; there are dynamic obstacles with predicted trajectory lines within a preset time in the future; S2: Based on the information upstream of the ego vehicle, the dynamic obstacles whose boundaries need to be processed are screened, and the dynamic obstacles are processed to obtain the boundaries of the dynamic obstacles; S3: Solve the dynamic obstacle boundary obtained in step S2 to obtain the path planning trajectory of the vehicle; S4: The vehicle receives the trajectory planning solved in step S3, and drives to avoid dynamic obstacles based on the trajectory planning.

2. A boundary analysis method for processing nearby obstacles according to claim 1, characterized in that: In step S1, the information upstream of the ego vehicle includes: the location of the ego vehicle; the status of the ego vehicle; whether the ego vehicle lane and the left and right lane reference lines exist; whether the obstacle is dynamic and there is a predicted trajectory line for the ego vehicle within a preset time in the future; and whether the ego vehicle task management module has issued the driving task normally.

3. A boundary analysis method for processing nearby obstacles according to claim 2, characterized in that: In step S2, screening dynamic obstacles includes the following steps: S201: According to the position of the ego vehicle, the lane in which the ego vehicle is traveling is obtained, and according to the reference line information, the reference line closest to the ego vehicle is selected, and based on the reference line closest to the ego vehicle, the reference lines of the left and right lanes are queried to obtain the position information of all dynamic obstacles on the reference lines of the left and right lanes; S202: judging the positional relationship between the dynamic obstacle and the vehicle according to the position of the dynamic obstacle; If the dynamic obstacle is not on the left side of the left reference line or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the left side of the vehicle; If the dynamic obstacle is not on the right side of the right reference line, or is not a dynamic obstacle crossing the road, then the dynamic obstacle is on the right side of the vehicle; S203: Segment the predicted trajectory of the dynamic obstacle into time segments, and obtain the position of the dynamic obstacle in each time segment, including the position of the dynamic obstacle at the start time and the end time; S204: Compare the positions of the ego vehicle and the dynamic obstacle in a set time period to determine whether the ego vehicle and the dynamic obstacle have an overlapping relationship in the same time period; S205: When the ego vehicle and the dynamic obstacles overlap, the number of all dynamic obstacles is increased by one. When the number of the dynamic obstacles is zero, there is no dynamic obstacle near the ego vehicle and no processing is required.

4. A boundary analysis method for processing nearby obstacles according to claim 3, characterized in that: The comparison method of the ego vehicle and the dynamic obstacle in step S204 is that within a preset time period, the longitudinal projection of the dynamic obstacle from the front end to the rear end on the reference line of the ego vehicle lane intersects with the longitudinal projection of the ego vehicle from the rear end to the front end on the reference line, that is, the dynamic obstacle and the ego vehicle partially overlap in the longitudinal direction of the reference line of the ego vehicle lane, and the ego vehicle and the dynamic obstacle overlap within the time period.

5. A boundary analysis method for processing nearby obstacles according to claim 4, characterized in that: In step S2, processing the dynamic obstacle to obtain the boundary of the dynamic obstacle includes the following steps: S211: Based on steps S201-S202, the position information of all dynamic obstacles on the left and right lane reference lines is obtained; S212: For each left and right dynamic obstacle, the longitudinal projection distance of the rear end of the obstacle on the reference line at the start time of the time period is used as the longitudinal starting point for processing the dynamic obstacle boundary, and the longitudinal projection distance of the front end of the obstacle on the reference line at the end time of the time period is used as the longitudinal end point for processing the dynamic obstacle boundary, and the left longitudinal starting point, the right longitudinal starting point, the left longitudinal end point, and the right longitudinal end point are obtained respectively; S213: For the left dynamic obstacle, the lateral projection distance of its right side on the reference line is used as the lateral value for processing the dynamic obstacle. For the right dynamic obstacle, the lateral projection distance of its left side on the reference line is used as the lateral value for processing the dynamic obstacle, thereby obtaining a left lateral value and a right lateral value. S214: generating a left boundary based on the dynamic obstacle according to the determined left longitudinal starting point, left longitudinal end point and left lateral value, and generating a right boundary based on the dynamic obstacle according to the determined right longitudinal starting point, right longitudinal end point and right lateral value; Among them, if any point on the reference line is selected as the origin, the left boundary is positive and the right boundary is negative. The value of the left boundary becomes larger as it moves away from the reference line to the left, and the value of the right boundary becomes smaller as it moves away from the reference line to the right. S215: Compare the left boundary and right boundary generated in step S214 with the default left boundary and right boundary of the dynamic obstacle: if the left boundary generated in step S214 is larger than the default left boundary, the default left boundary is selected as the final left boundary; otherwise, the generated left boundary is selected as the final left boundary; if the right boundary generated in step S214 is larger than the default right boundary, the generated right boundary is selected as the final right boundary; otherwise, the default right boundary is selected as the final right boundary.

6. A boundary analysis method for processing nearby obstacles according to claim 5, characterized in that: In step S3, the final left boundary and the final right boundary are both used as inputs and solved by a solver to obtain a planned path of the vehicle in the current environment.

7. A boundary resolution system for processing nearby obstacles according to any one of claims 1 to 6, characterized in that: include: The upstream module is used to obtain perception, reference lines, vehicle status and task management status; The observation module is used to observe the road conditions of the vehicle lane and the left and right lanes based on the information obtained by the upstream module, and determine whether dynamic obstacles need to be handled; The boundary analysis module is used to process the dynamic obstacles on the left and right sides of the vehicle lane, screen the dynamic obstacles that need to be processed, and process them to obtain the boundaries of the dynamic obstacles; The planning and solving module is used to plan the trajectory of the vehicle path according to the boundary obtained by the boundary analysis module; The control module is used for the vehicle to perform avoidance driving according to the path planning of the planning and solving module.

8. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein: The processor, the communication interface and the memory communicate with each other via the communication bus, wherein the memory is used to store a computer program; The processor is configured to execute the method according to any one of claims 1 to 6 by running the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program implements the method described in any one of claims 1 to 6 when executed by a processor.

Images