Path replanning method, device, equipment and vehicle

Abstract

The present application discloses a path replanning method, device, equipment and vehicle, and relates to the field of path planning technology. The path replanning method includes: obtaining an initial parking path, vehicle status information and vehicle surrounding perception information; based on the vehicle status information and vehicle surrounding perception information, performing collision detection on the initial parking path to obtain a collision detection result; if it is detected that there is a risk of collision when the vehicle travels along the initial parking path, then based on the collision detection result and a dynamic replanning algorithm, performing path replanning on the initial parking path to obtain a replanned path. Through the above scheme, the present application can realize automatic replanning of the parking path without stopping when the vehicle encounters an unexpected obstacle during parking, while improving the efficiency of vehicle parking.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a path replanning method, device, equipment and vehicle. Background Art

[0002] In existing parking solutions, since the parking decision and path planning modules are often coupled, the operation of the path planning module will block the parking algorithm process and affect the parking decision module's collision judgment of obstacles. Therefore, when it is detected that the vehicle has a collision risk along the planned parking path, the vehicle is often required to stop first and then re-plan the trajectory. However, the vehicle's stopping for obstacles will lead to discontinuity in the parking action, which in turn affects the smoothness and efficiency of the vehicle parking process.

[0003] Therefore, existing path replanning methods cannot guarantee real-time path replanning without stopping obstacles when a collision risk is detected.

[0004] Based on the above content, how to improve the efficiency of vehicle parking is a problem that needs to be solved urgently.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a path replanning method, device, equipment and vehicle, aiming to solve the technical problem of how to improve the efficiency of vehicle parking.

[0007] To achieve the above objectives, the present application proposes a path replanning method, which is applied to a vehicle and includes:

[0008] Obtain the initial parking path, vehicle status information, and vehicle surrounding perception information;

[0009] Based on the vehicle state information and the vehicle surrounding perception information, performing collision detection on the initial parking path to obtain a collision detection result;

[0010] If it is detected that there is a risk of collision when the vehicle travels along the initial parking path, the initial parking path is replanned based on the collision detection result and the dynamic replanning algorithm to obtain a replanned path.

[0011] In one embodiment, the step of performing collision detection on the initial parking path based on the vehicle state information and the vehicle surrounding perception information to obtain the collision detection result includes:

[0012] Based on the preset cycle, the collision detection thread is used regularly to confirm obstacle information based on the vehicle's surrounding perception information;

[0013] Predicting a driving area of ​​the vehicle on the initial parking path according to the vehicle state information using a collision detection thread;

[0014] According to the driving area and obstacle information, it is detected whether there is a risk of collision between the vehicle and the obstacle, and a collision detection result is obtained.

[0015] In one embodiment, the collision detection result includes a collision stop flag and collision information. If it is detected that there is a collision risk when the vehicle travels along the initial parking path, the initial parking path is replanned based on the collision detection result and a dynamic replanning algorithm to obtain a replanned path, the step includes:

[0016] When the collision stop flag is a preset value, it is confirmed that there is a collision risk when the vehicle travels according to the initial parking path;

[0017] Using the path planning thread, according to the collision information and the dynamic replanning algorithm, the advance planning point is calculated;

[0018] When the number of path replanning times is not greater than the preset first number, the initial parking path is replanned based on the dynamic replanning algorithm according to the advance planning points, vehicle status information and obstacle information, until the vehicle travels along the parking path after path replanning without collision risk, thereby obtaining a replanned path.

[0019] In one embodiment, the dynamic replanning algorithm includes a preset optimization algorithm and a preset heuristic path search algorithm, the advance planning point includes a first planning point and a second planning point, and the step of using the path planning thread to calculate the advance planning point according to the collision information and the dynamic replanning algorithm includes:

[0020] When the dynamic replanning algorithm is a preset optimization algorithm, a path planning thread is used to calculate a first planning point according to the vehicle state information in the collision information;

[0021] When the dynamic replanning algorithm is a preset heuristic path search algorithm, a path planning thread is used to establish an object polygon map model according to the vehicle state information and obstacle information in the collision information;

[0022] Using the object polygon map model, a safe obstacle stopping point is determined according to the overlapping area between the vehicle polygon and the obstacle polygon;

[0023] A second planning point is determined based on the safety obstacle stopping point and the vehicle status information.

[0024] In one embodiment, the number of path replanning includes the number of path optimization and the number of path search. When the number of path replanning is not greater than the preset first number, the initial parking path is replanned based on the advance planning point, the vehicle state information and the obstacle information based on the dynamic replanning algorithm until the vehicle travels along the parking path after the path replanning without collision risk, and the step of obtaining the replanned path includes:

[0025] When the number of path optimizations is less than the preset second number, the preset optimization algorithm is used to optimize the initial parking path according to the first planning point, the vehicle state information and the obstacle information to obtain a first planning path;

[0026] Using a collision detection thread to perform collision detection on the first planned path;

[0027] When the vehicle is at risk of collision when traveling along the first planned path, the process returns to the execution step: when the number of path optimizations is less than the preset second number, the initial parking path is optimized using a preset optimization algorithm according to the first planned point, the vehicle state information, and the obstacle information, until the number of path optimizations is equal to the preset second number or the vehicle is at risk of collision when traveling along the first planned path;

[0028] When the number of path optimizations is equal to the preset second number and the number of path searches is not greater than the preset third number, using a preset heuristic path search algorithm, the initial parking path is replanned according to the second planning point, the vehicle state information and the obstacle information to obtain a second planned path;

[0029] Using a collision detection thread to perform collision detection on the second planned path;

[0030] When there is a risk of collision when the vehicle travels along the second planned path, the process returns to the execution step: when the number of path optimizations is equal to the preset second number, and the number of path searches is not greater than the preset third number, the initial parking path is replanned using a preset heuristic path search algorithm according to the second planned points, the vehicle state information, and the obstacle information, until the number of path searches is greater than the preset third number or there is no risk of collision when the vehicle travels along the second planned path;

[0031] When there is no collision risk when the vehicle travels along the first planned path, using the first planned path as the re-planned path; or

[0032] When there is no collision risk when the vehicle travels along the second planned path, the second planned path is used as the re-planned path.

[0033] In one embodiment, the initial parking path includes a target parking point, and the step of replanning the initial parking path according to the second planned point, the vehicle state information, and the obstacle information using a preset heuristic path search algorithm to obtain a second planned path includes:

[0034] Using a preset heuristic path search algorithm, according to the vehicle state information and obstacle information, a path search is performed between the second planning point and the target parking point to obtain a searched path;

[0035] According to the second planning point, the searched path is spliced ​​with the initial parking path to obtain a spliced ​​parking path;

[0036] The spliced ​​parking path is subjected to trajectory smoothing processing to obtain a second planned path.

[0037] In one embodiment, the method further comprises:

[0038] When the number of path replanning times is greater than the preset first number, a collision detection thread is used to send a stop signal to the vehicle to control the vehicle to stop at the safety stop point; or

[0039] In the process of replanning the initial parking path by the path planning thread, detecting the collision distance between the vehicle and the obstacle by using the collision detection thread;

[0040] When the collision distance is less than the minimum safety distance, a collision detection thread is used to send a stop signal to the vehicle to control the vehicle to stop at the safety stop point.

[0041] In addition, to achieve the above purpose, the present application also proposes a path re-planning device, the path re-planning device comprising:

[0042] An acquisition module, used to acquire an initial parking path, vehicle status information, and vehicle surrounding perception information;

[0043] A collision detection module, configured to perform collision detection on the initial parking path based on vehicle state information and vehicle surrounding perception information to obtain a collision detection result;

[0044] The path replanning module is used to replan the initial parking path based on the collision detection result and the dynamic replanning algorithm to obtain a replanned path if it is detected that there is a collision risk when the vehicle travels along the initial parking path.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a path replanning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path replanning method as described above.

[0046] In addition, to achieve the above objectives, the present application also proposes a vehicle, which includes the path replanning device as described above.

[0047] One or more technical solutions proposed in this application have at least the following technical effects:

[0048] The path replanning method, device, equipment and vehicle proposed in the embodiments of the present application specifically obtain an initial parking path, vehicle status information and vehicle surrounding perception information; based on the vehicle status information and the vehicle surrounding perception information, perform collision detection on the initial parking path to obtain a collision detection result; if it is detected that there is a collision risk when the vehicle travels along the initial parking path, then based on the collision detection result and a dynamic replanning algorithm, perform path replanning on the initial parking path to obtain a replanned path.

[0049] The present application performs collision detection on the initial parking path through vehicle status information and vehicle surrounding perception information to confirm whether the vehicle has a collision risk according to the initial parking path; if it is detected that the vehicle has a collision risk according to the initial parking path, the parking path is replanned based on the collision detection result and the dynamic replanning algorithm, with reference to the initial parking path. When the vehicle encounters an unexpected obstacle during parking, the parking path is automatically replanned without stopping, thereby improving the efficiency of vehicle parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0052] Figure 1 A flowchart of the first embodiment of the path replanning method of the present application is provided;

[0053] Figure 2 A flow chart of the second embodiment of the path replanning method of the present application;

[0054] Figure 3A flowchart of the third embodiment of the path replanning method of the present application is provided;

[0055] Figure 4 A flowchart of the fourth embodiment of the path replanning method of the present application is provided;

[0056] Figure 5 This is a schematic diagram of the module structure of the path re-planning device according to an embodiment of the present application;

[0057] Figure 6 A schematic diagram of the device structure of the hardware operating environment involved in the path replanning method in the embodiment of the present application;

[0058] Figure 7 A schematic diagram of a vehicle parking scenario involved in the path re-planning method in an embodiment of the present application.

[0059] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0061] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0062] The main solution of the embodiment of the present application is: obtaining an initial parking path, vehicle status information and vehicle surrounding perception information; performing collision detection on the initial parking path based on the vehicle status information and the vehicle surrounding perception information to obtain a collision detection result; if it is detected that there is a risk of collision when the vehicle travels along the initial parking path, then based on the collision detection result and a dynamic replanning algorithm, the initial parking path is replanned to obtain a replanned path.

[0063] In the automatic parking scenario, given the parking space information, the vehicle can generate a reasonable parking path through path planning and speed planning based on the vehicle's posture, and implement path tracking based on the control module to complete parking. However, during driving, due to the limitation of the perception range or the uncertainty of the environment, unexpected obstacles may be encountered. If these obstacles are located on the parking path, there is a risk of collision if the vehicle continues to drive along the original parking path. Therefore, the trajectory must be replanned in real time based on the vehicle's posture and obstacle information to ensure parking safety.

[0064] The current automatic parking solutions generally adopt the strategy of parking first and then re-planning. The reason is that the parking decision and path planning modules are often coupled. The operation of the path planning module will block the parking algorithm process, which will not only affect the parking decision module's judgment of obstacles, but also fail to transmit the collision signal to the control module in time. If planning is not carried out without stopping, there is a risk of collision during the planning period. However, parking to avoid obstacles will cause discontinuous parking actions, affecting the smoothness and overall efficiency of parking.

[0065] Therefore, existing path replanning methods cannot guarantee real-time path replanning without stopping obstacles when a collision risk is detected.

[0066] From the above analysis, it can be seen that how to improve the efficiency of vehicle parking is a problem that needs to be solved urgently.

[0067] The present application provides a solution, which performs collision detection on an initial parking path through vehicle status information and vehicle surrounding perception information to confirm whether the vehicle has a collision risk according to the initial parking path; if it is detected that the vehicle has a collision risk according to the initial parking path, the parking path is replanned based on the collision detection result and a dynamic replanning algorithm, with reference to the initial parking path, so that when the vehicle encounters an unexpected obstacle during parking, the parking path can be automatically replanned without stopping, thereby improving the efficiency of vehicle parking.

[0068] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a path replanning device capable of realizing the above functions, etc. The following takes the path replanning device as an example to illustrate this embodiment and the following embodiments.

[0069] Based on this, the embodiment of the present application provides a path replanning method, which is applied to a vehicle, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the path re-planning method of the present application.

[0070] In this embodiment, the method is applied to a vehicle, and the path replanning method includes steps S110 to S130:

[0071] Step S110, obtaining an initial parking path, vehicle status information, and vehicle surrounding perception information;

[0072] Specifically, the path replanning device first needs to obtain the initial parking path pre-generated by the vehicle according to the parking space information in the current automatic parking scenario, the current vehicle status information and the vehicle's surrounding perception information, so as to facilitate the subsequent vehicles to perform collision detection on the initial parking path and confirm whether there is a collision risk when the vehicle travels along the initial parking path. Among them, the initial parking path refers to a pre-generated path between the current vehicle position and the target parking space in the automatic parking scenario. The path can usually be calculated by a preset parking path planning algorithm based on the parking space information (such as the location, size, direction, etc. of the space) and the current posture information (i.e., position and posture) of the vehicle. The preset parking path planning algorithm is a path planning algorithm set by relevant personnel based on the actual needs of automatic parking, which can be a Dijkstra algorithm, a genetic algorithm, a particle swarm optimization algorithm, a fast search random tree, a Dubins path planning algorithm, etc., or a path planning method based on a deep learning algorithm.

[0073] Vehicle status information refers to the vehicle's position information, speed information, posture information, and control information.

[0074] The vehicle location information includes the vehicle's current geographic location (such as longitude and latitude information, etc.) and its position relative to the parking space. The vehicle control information includes the status of the vehicle's control system, including but not limited to the vehicle's driving mode, acceleration and deceleration control information, vehicle lane change control information, and the current vehicle braking system control information.

[0075] Vehicle peripheral perception information refers to the vehicle's surrounding environment information perceived by the vehicle through various sensors such as lidar, infrared, and on-board cameras, including obstacle information around the vehicle, weather information, lane information of the vehicle, and related information of surrounding dynamic objects.

[0076] Step S120, performing collision detection on the initial parking path based on the vehicle state information and the vehicle surrounding perception information to obtain a collision detection result;

[0077] Specifically, according to the vehicle state information and the vehicle surrounding perception information obtained above, it is determined whether the vehicle will collide with the currently perceived obstacle when driving to the parking space according to the current initial parking path in the global or self-vehicle coordinate system, thereby realizing collision detection on the initial parking path and obtaining a collision detection result. Among them, the collision detection result at least includes identification information indicating whether there is a collision risk, obstacle information with a collision risk, vehicle state information and vehicle surrounding perception information, and collision distance information at the current moment.

[0078] In a feasible implementation manner, the step S120 may include steps A01 to A03:

[0079] Step A01, based on a preset period, regularly using a collision detection thread to confirm obstacle information based on vehicle surrounding perception information;

[0080] Step A02, predicting the driving area of ​​the vehicle on the initial parking path according to the vehicle state information using a collision detection thread;

[0081] Step A03: Detect whether there is a risk of collision between the vehicle and the obstacle based on the driving area and obstacle information, and obtain a collision detection result.

[0082] As can be seen from the foregoing, since the parking decision and path planning modules in the automatic parking scenario are often coupled serial structures, the operation of the path planning module will affect the parking decision module's collision judgment of obstacles. Therefore, in this embodiment, another independent thread (i.e., collision detection thread) is opened up to detect collisions on the parking path, thereby realizing real-time collision detection of the vehicle parking path without affecting the re-planning of the parking path.

[0083] It should be understood that in order to ensure the normal and efficient operation of the path planning module, a multi-threaded approach may be adopted in the present embodiment, where a single information thread is used to obtain the vehicle's surrounding perception information and vehicle status information through the vehicle's control system, and then sends it to the collision detection thread; the path planning thread is solely responsible for planning the vehicle's parking path, and sends the initial parking path and the re-planned parking path to the collision detection thread.

[0084] Specifically, the path replanning device needs to use the collision detection thread to perform collision detection on the parking path according to a preset period. First, the path replanning device confirms the potential obstacle information around the initial parking path based on the vehicle's surrounding perception information, such as lidar data and infrared detection data, including the location information, posture information, size information, motion state information, etc. of the obstacle.

[0085] Then, the collision detection thread further uses the vehicle state information to construct the vehicle's kinematic model, as well as the initial parking path received from the path planning thread, and evaluates the vehicle's driving area along the initial parking path through methods such as trajectory prediction. Then, combined with the obstacle information, it is confirmed whether the vehicle will overlap with any obstacles in the driving area along the initial parking path, thereby confirming whether the vehicle has a risk of collision with the obstacle. It can be understood that when there are moving obstacles among the obstacles, the overlap confirmation can be performed second by second based on the movement time, thereby confirming whether the vehicle has a risk of collision with the obstacle.

[0086] If a collision risk is detected, the collision detection thread will generate a "collision risk" result; otherwise, it will generate a "no collision risk" result. The collision detection result will be sent to the path planning thread so that the path planning thread can take appropriate measures, such as replanning the path, slowing down or stopping, to ensure the safety and reliability of the automatic parking process.

[0087] This implementation is based on a multi-threaded method and uses a single thread to implement collision detection on the parking path. While the path planning module is performing path replanning, the collision situation of the parking path is detected at a fixed period to ensure safety during real-time path replanning.

[0088] Step S130: If it is detected that there is a collision risk when the vehicle travels along the initial parking path, the initial parking path is replanned based on the collision detection result and a dynamic replanning algorithm to obtain a replanned path.

[0089] Specifically, the path replanning device detects that the vehicle will collide with one or more obstacles while traveling along the initial parking path according to the collision detection thread. Then, according to the obstacle information with collision risk in the collision detection result, the vehicle status information and the vehicle surrounding perception information, the collision distance information at the current moment, combined with the dynamic replanning algorithm, the original initial parking path is referred to, and a parking path avoiding obstacles is planned to obtain a replanned path. Among them, the dynamic replanning algorithm is a path replanning algorithm pre-set by relevant personnel based on the obstacle avoidance requirements of vehicle parking and the smoothness of the parking path, etc., which can be a heuristic search algorithm A* algorithm, a fast search random tree, a path planning algorithm based on speed space (such as a dynamic window method), and a path planning algorithm based on deep learning.

[0090] In a feasible implementation manner, the collision detection result includes a collision stop flag and collision information, and the step S130 may include steps B01 to B03:

[0091] Step B01, when the collision stop flag is a preset value, confirming that there is a collision risk when the vehicle travels along the initial parking path;

[0092] Step B02, using the path planning thread, according to the collision information and the dynamic replanning algorithm, calculate and obtain the advance planning point;

[0093] First, the path planning thread receives the collision detection result sent by the collision detection thread, and when it is confirmed that the collision stop flag in the collision detection result is a preset value, it is further confirmed that the vehicle has a collision risk when traveling according to the initial parking path. Among them, the collision stop flag is a Boolean value used to characterize whether the vehicle has a collision risk when traveling according to the initial parking path, and usually includes two values. The preset value of the collision stop flag in this embodiment refers to the value set by the relevant personnel based on experience.

[0094] The collision information includes at least obstacle information with collision risk, vehicle status information, vehicle surrounding perception information, and collision distance information at the current moment.

[0095] Then, after confirming that there is a risk of collision, the path replanning device uses the path planning thread to calculate the advance planning point where the vehicle should turn or adjust the driving direction in advance based on the current vehicle movement information, the location of the collision point, the size and movement state of the obstacle, etc. contained in the collision information, combined with the dynamic replanning algorithm. Among them, the advance planning point refers to a reference point selected on the initial parking path to guide the vehicle to avoid the collision point. The advance planning point must ensure that the vehicle can avoid collisions while transitioning to the replanned parking path as smoothly as possible.

[0096] Step B03, when the number of path replanning times is not greater than the preset first number, the initial parking path is replanned based on the dynamic replanning algorithm according to the advance planning points, vehicle status information and obstacle information, until the vehicle travels along the parking path after path replanning without collision risk, and a replanned path is obtained.

[0097] Finally, for the driving safety of the vehicle, this implementation method needs to limit the number of path replanning to ensure that the vehicle will not collide with obstacles. It should be noted that the preset first number is the maximum planning number of the dynamic replanning algorithm set by relevant personnel based on the actual needs or experience of vehicle parking.

[0098] Specifically, when the number of path replanning times is not greater than the preset first number, based on the dynamic replanning algorithm, according to the advance planning point, vehicle status information and obstacle information, as well as parking space information, an obstacle avoidance path from the advance planning point to the parking space is first planned, and then the obstacle avoidance path can be connected to the initial parking path, thereby realizing path replanning of the initial parking path, until there is no collision risk when the vehicle travels along the parking path after path replanning, thereby obtaining a replanned path.

[0099] It should be understood that each time a path replanning is completed, the number of path replanning times needs to be counted and increased. A replanned path is only a valid replanned path if it is confirmed by the collision detection thread that there is no collision risk.

[0100] The present embodiment provides a path replanning method, which obtains an initial parking path, vehicle status information, and vehicle surrounding perception information; based on the vehicle status information and the vehicle surrounding perception information, performs collision detection on the initial parking path to obtain a collision detection result; if it is detected that there is a collision risk when the vehicle travels along the initial parking path, then based on the collision detection result and a dynamic replanning algorithm, the initial parking path is replanned to obtain a replanned path.

[0101] The present application performs collision detection on the initial parking path through vehicle status information and vehicle surrounding perception information to confirm whether the vehicle has a collision risk according to the initial parking path; if it is detected that the vehicle has a collision risk according to the initial parking path, the parking path is replanned based on the collision detection result and the dynamic replanning algorithm, with reference to the initial parking path. When the vehicle encounters an unexpected obstacle during parking, the parking path is automatically replanned without stopping, thereby improving the efficiency of vehicle parking.

[0102] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and no further description will be given later. On this basis, the dynamic replanning algorithm includes a preset optimization algorithm and a preset heuristic path search algorithm, and the advance planning point includes a first planning point and a second planning point, please refer to Figure 2 , the step B02 includes steps S210 to S240:

[0103] Step S210, when the dynamic replanning algorithm is a preset optimization algorithm, using a path planning thread, calculate a first planning point according to the vehicle state information in the collision information;

[0104] It should be noted that the preset optimization algorithm is a path optimization algorithm pre-set by relevant personnel based on the obstacle avoidance requirements of vehicle parking and the smoothness of the parking path. It can be the optimal control method, gradient descent method and its variants, linear optimization and nonlinear optimization, particle swarm optimization algorithm, genetic algorithm, etc.

[0105] The preset heuristic path search algorithm is a heuristic path search algorithm pre-set by relevant personnel based on the obstacle avoidance requirements of vehicle parking and the smoothness of the parking path, etc. It can be an A* search algorithm, Dijkstra algorithm, greedy search algorithm, ant colony algorithm, simulated annealing method, etc.

[0106] Specifically, when the dynamic replanning algorithm is a preset optimization algorithm, the path planning thread is used to use the position information and speed information in the current vehicle state information to obtain the vehicle position coordinate information obtained when the vehicle travels along the initial parking path at the current speed in a fixed coordinate system for the predetermined first time as the first planning point. The fixed coordinate system may be a world coordinate system or a self-vehicle coordinate system with the coordinates of the vehicle where the risk of collision is first discovered as the origin. The predetermined first time refers to the maximum optimization time set by relevant personnel based on experience or actual vehicle parking needs, which is calculated by the time taken for a single use of the preset optimization algorithm and the maximum number of path optimizations.

[0107] Step S220, when the dynamic replanning algorithm is a preset heuristic path search algorithm, using a path planning thread to establish an object polygon map model according to the vehicle state information and obstacle information in the collision information;

[0108] Step S230, using the object polygon map model, determining a safe obstacle stopping point according to an overlapping area between the vehicle polygon and the obstacle polygon;

[0109] Specifically, when the dynamic replanning algorithm is a preset heuristic path search algorithm, the path replanning device uses the path planning thread to construct a vehicle polygon (for example, a vehicle quadrilateral is constructed with the size of a four-wheel vehicle) and an obstacle polygon in a fixed coordinate system according to the position information, posture information, and vehicle size information in the current vehicle state information, and the obstacle position information, posture information, and size information in the obstacle information, thereby establishing an object polygon map model.

[0110] Then, according to the speed information in the current vehicle state information and the obstacle speed information in the obstacle information, the vehicle in the object polygon map model is driven at the current speed along the initial parking path so that it collides with an obstacle for the first time at a certain moment, and the area where the vehicle collides with the obstacle for the first time is analyzed.

[0111] Reference Figure 7 A schematic diagram of a vehicle parking scenario is shown. Based on whether there is an overlapping area between the vehicle polygon and the obstacle polygon, the overlapping critical point of the vehicle polygon and the obstacle polygon is confirmed, thereby determining the critical point where the vehicle collides with the obstacle for the first time. That is to say, the vehicle will not collide with the obstacle when it stops at this point. When the vehicle continues to travel along the initial parking path from this point, the vehicle will collide with the obstacle, so that the critical point is used as a safe obstacle parking point.

[0112] Step S240: determining a second planning point according to the safety obstacle stopping point and the vehicle status information.

[0113] Since the vehicle may reverse or turn when using the heuristic search algorithm, it is necessary to stop the vehicle first and then drive according to the re-planned path.

[0114] The calculation method of the second planning point needs to first use the path planning thread, according to the position information and speed information in the current vehicle status information, to take the vehicle position coordinate information obtained when the vehicle travels along the initial parking path at the current speed in a fixed coordinate system for a predetermined second time as the initial second planning point. Then, the vehicle parking point position coordinate information obtained by decelerating and braking the vehicle at the current speed at the predetermined maximum deceleration from the initial second planning point is taken as the second planning point. Among them, the predetermined second time refers to the maximum path search time set by relevant personnel based on experience or actual vehicle parking needs, which is calculated by the time used for a single use of the preset heuristic path search algorithm and the maximum number of path searches. The predetermined maximum deceleration refers to the maximum deceleration set by relevant personnel based on the vehicle's own deceleration limit or experience.

[0115] In order to ensure the validity of the second planned point, it is necessary to compare the coordinate information of the second planned point with the coordinate information of the safe obstacle stopping point to ensure that the path searched by the preset heuristic path search algorithm can be used for the vehicle to avoid obstacles before a collision occurs.

[0116] When following the direction of travel of the initial parking path, only the second planning point before the safety obstacle stop point is a valid second planning point, and the valid second planning point is used as the second planning point of the preset heuristic path search algorithm. When following the direction of travel of the initial parking path, the second planning point after the safety obstacle stop point is an invalid second planning point, and it is deemed that there is no second planning point in the preset heuristic path search algorithm, and the path cannot be replanned by the preset heuristic path search algorithm.

[0117] This embodiment provides a path replanning method, which calculates the first planning point and the second planning point so that a preset optimization algorithm and a preset heuristic path search algorithm can be used to replan the parking path. When a vehicle encounters an unexpected obstacle during parking, the parking path can be automatically replanned without stopping, thereby improving the efficiency of vehicle parking.

[0118] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment and / or the second embodiment can refer to the above description, and no further description will be given later. On this basis, the number of path replanning includes the number of path optimization and the number of path search. Please refer to Figure 3 , the step B03 includes steps S310 to S380:

[0119] Step S310, when the number of path optimizations is less than the preset second number, using a preset optimization algorithm, the initial parking path is optimized according to the first planning point, the vehicle state information and the obstacle information to obtain a first planned path;

[0120] Specifically, in this embodiment, it is necessary to combine the preset optimization algorithm and the preset heuristic path search algorithm to replan the path of the initial parking path. Therefore, the number of path replanning includes the number of path optimization and the number of path searches. The preset first number is composed of the sum of the preset second number and the preset third number. Among them, the preset second number is the maximum optimization number of the preset optimization algorithm set by relevant personnel based on the actual needs or experience of vehicle parking. The preset third number is the maximum search number of the preset heuristic path search algorithm set by relevant personnel based on the actual needs or experience of vehicle parking.

[0121] Specifically, when the number of path optimizations is less than the preset second number, the preset optimization algorithm is first used to construct a vehicle kinematic model and obstacle constraints under fixed coordinates according to the vehicle state information and obstacle information, and then a parking constraint is established according to the first planning point and the parking garage site, and then the path between the first planning point and the parking garage site on the initial parking path is optimized with the parking constraint, obstacle constraint and the smoothness or efficiency of the optimized path as the optimization target, and the initial parking path and the path between the optimized first planning point and the parking garage site are spliced ​​at the first planning point to obtain the first planning path. The parking garage site is the end point of the initial parking path.

[0122] It should be understood that each time after the first planned path is obtained, it is necessary to detect whether the first planned path is valid, that is, to detect whether the vehicle can travel along the first planned path and whether the vehicle can reach the parking space by traveling along the first planned path.

[0123] Step S320, performing collision detection on the first planned path using a collision detection thread;

[0124] Step S330, when there is a collision risk when the vehicle travels along the first planned path, return to the execution step: when the number of path optimizations is less than the preset second number, the initial parking path is optimized using a preset optimization algorithm according to the first planned point, the vehicle state information and the obstacle information, until the number of path optimizations is equal to the preset second number or there is no collision risk when the vehicle travels along the first planned path;

[0125] Specifically, after obtaining the first planned path, the path re-planning device needs to use the collision detection thread to perform collision detection on the first planned path again to ensure that the first planned path allows the vehicle to park without obstacles.

[0126] When the path replanning device detects that there is a risk of collision when the vehicle travels along the first planned path, it returns to step S310 and re-optimizes the initial parking path using the preset optimization algorithm until the number of path optimizations is equal to the preset second number, or there is no risk of collision when the vehicle travels along the first planned path.

[0127] Step S340, when the number of path optimizations is equal to the preset second number and the number of path searches is not greater than the preset third number, using a preset heuristic path search algorithm, the initial parking path is replanned according to the second planning point, the vehicle state information and the obstacle information to obtain a second planned path;

[0128] Specifically, when the number of path optimizations is equal to the preset second number, and the number of path searches is not greater than the preset third number, the preset heuristic path search algorithm is first used, with the second planned point as the search starting point of the algorithm and the parking garage site as the search end point of the algorithm, to search for an obstacle avoidance path from the second planned point to the parking garage site, and then the obstacle avoidance path from the second planned point to the parking garage site and the initial parking path are spliced ​​to generate a second planned path.

[0129] In a feasible implementation manner, the initial parking path includes a target parking point, and the step of: using a preset heuristic path search algorithm to replan the initial parking path according to the second planned point, vehicle state information, and obstacle information to obtain a second planned path may include steps C01 to C03:

[0130] Step C01, using a preset heuristic path search algorithm, based on vehicle state information and obstacle information, performing a path search between the second planned point and the target parking point to obtain a searched path;

[0131] Step C02, according to the second planning point, splicing the searched path with the initial parking path to obtain a spliced ​​parking path;

[0132] Step C03, performing trajectory smoothing processing on the spliced ​​parking path to obtain a second planned path.

[0133] Specifically, when the number of path optimizations is equal to the preset second number, and the number of path searches is not greater than the preset third number, the preset heuristic path search algorithm is first used, the second planning point is used as the algorithm's search starting point, and the target parking point (i.e., the parking garage site) is used as the algorithm's search end point, and then the coordinate area in the polygonal map model where the vehicle will not collide with the obstacle is constructed based on the vehicle state information and the obstacle information, thereby constructing the algorithm search space, and then the heuristic function is established based on the vehicle's kinematic model to evaluate the quality of the node (i.e., the coordinate point in the algorithm search space), and the nodes with the largest heuristic value are continuously searched in the algorithm search space, and these nodes are connected to generate a path from the second planning point to the parking garage site, thereby obtaining the searched path. Then, at the second planning point, the searched path is spliced ​​with the initial parking path to obtain the spliced ​​parking path.

[0134] It should be understood that each time the searched path is obtained, it is necessary to detect whether the searched path is successful, that is, to detect whether the vehicle can travel along the searched path and whether the vehicle can avoid obstacles while traveling along the searched path.

[0135] In order to ensure the smoothness of the splicing, curve fitting, polynomial fitting, Bezier curve, spline curve and other methods are used within the limit of vehicle curvature to smooth the spliced ​​parking path. For example, the curvature and directional gradient of the path are optimized to make the path smoother and reduce sharp turns or sudden acceleration / deceleration, thereby obtaining the second planned path.

[0136] Step S350, performing collision detection on the second planned path using a collision detection thread;

[0137] Step S360, when there is a collision risk when the vehicle travels along the second planned path, return to the execution step: when the number of path optimizations is equal to the preset second number, and the number of path searches is not greater than the preset third number, the initial parking path is replanned using a preset heuristic path search algorithm according to the second planned point, the vehicle state information, and the obstacle information, until the number of path searches is greater than the preset third number or there is no collision risk when the vehicle travels along the second planned path;

[0138] Specifically, after obtaining the second planned path, the path re-planning device needs to use the collision detection thread to perform collision detection on the second planned path again to ensure that the second planned path allows the vehicle to park without obstacles.

[0139] When the path replanning device detects that there is a risk of collision when the vehicle travels along the second planned path, it returns to step S340 and re-searches the initial parking path using the preset heuristic path search algorithm until the number of path searches is greater than the preset third number, or there is no risk of collision when the vehicle travels along the second planned path.

[0140] Step S370: when there is no collision risk when the vehicle travels along the first planned path, the first planned path is used as a re-planned path; or

[0141] Step S380: When there is no collision risk when the vehicle travels along the second planned path, the second planned path is used as a re-planned path.

[0142] Finally, when there is no collision risk when the vehicle travels along the first planned path, the optimized first planned path is used as the re-planned path for the vehicle to park and avoid obstacles.

[0143] When there is no collision risk when the vehicle travels along the second planned path, the searched second planned path is used as a re-planned path for the vehicle to park and avoid obstacles.

[0144] It should be understood that when a valid replanned path is detected, that is, there is no risk of collision when the vehicle travels along the replanned path, the number of path replanning times needs to be counted and reset so that the vehicle can be replanned again when the vehicle encounters an obstacle later.

[0145] Through the above scheme, this embodiment combines the preset optimization algorithm with the preset heuristic path search algorithm to re-plan the parking path, so that when the vehicle encounters an unexpected obstacle during parking, the parking path can be automatically re-planned without stopping, while improving the efficiency of vehicle parking.

[0146] Based on the third embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the third embodiment can be referred to the above description, and will not be described in detail later. Figure 4 , the method further comprises steps S410 to S430:

[0147] Step S410, when the number of path replanning times is greater than the preset first number, using the collision detection thread to send an obstacle stop signal to the vehicle to control the vehicle to stop at the safety obstacle stop point; or

[0148] Specifically, when the number of path replanning times is greater than the preset first number, it means that the vehicle path replanning has failed, and no effective replanning path can be obtained for obstacle-free parking. The vehicle will subsequently travel along the initial parking path, and there is still a risk of collision. At this time, in order to ensure driving safety, the path replanning device will use the collision detection thread to send an obstacle stop signal to the vehicle, so that the vehicle control system or control module controls the vehicle to stop at a safe obstacle stop point according to the obstacle stop signal.

[0149] Step S420, in the process of the path planning thread replanning the initial parking path, the collision detection thread is used to detect the collision distance between the vehicle and the obstacle;

[0150] Step S430: When the collision distance is less than the minimum safety distance, a collision detection thread is used to send a stop signal to the vehicle to control the vehicle to stop at the safety stop point.

[0151] In addition, when the path planning thread is replanning the initial parking path, the path replanning device will use the collision detection thread to regularly detect the collision distance between the vehicle and the obstacle that may collide, that is, the distance between the vehicle's current position along the initial parking path and the safe obstacle stopping point.

[0152] When the collision distance is less than the minimum safety distance, the path replanning device will use the collision detection thread to send a stop signal to the vehicle, so that the vehicle control system or control module controls the vehicle to stop at a safe stop point according to the stop signal.

[0153] The minimum safety distance is the distance required for the relevant personnel to decelerate at a predetermined maximum deceleration based on the current speed.

[0154] Through the above scheme, this embodiment sends a stop signal to the vehicle through the collision detection thread, so as to ensure the driving safety of the vehicle when the vehicle encounters an unexpected obstacle during parking and the parking path replanning fails.

[0155] This application also provides a path re-planning device, please refer to Figure 5 , the path re-planning device comprises:

[0156] An acquisition module 10 is used to acquire an initial parking path, vehicle status information, and vehicle surrounding perception information;

[0157] A collision detection module 20, configured to perform collision detection on the initial parking path based on vehicle state information and vehicle surrounding perception information to obtain a collision detection result;

[0158] The path replanning module 30 is used to replan the initial parking path based on the collision detection result and the dynamic replanning algorithm to obtain a replanned path if it is detected that there is a collision risk when the vehicle travels along the initial parking path.

[0159] The path replanning device provided by the present application adopts the path replanning method in the above embodiment, which can solve the technical problem of how to improve the efficiency of vehicle parking. Compared with the prior art, the beneficial effects of the path replanning device provided by the present application are the same as the beneficial effects of the path replanning method provided by the above embodiment, and the other technical features in the path replanning device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0160] The present application provides a path replanning device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the path replanning method in the above-mentioned implementation example.

[0161] Reference below Figure 6 , which shows a schematic diagram of the structure of a path replanning device suitable for implementing the embodiment of the present application. The path replanning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The path replanning device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0162] like Figure 6As shown, the path replanning device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the path replanning device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the path re-planning device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a path re-planning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0163] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0164] The path replanning device provided by the present application adopts the path replanning method in the above embodiment, which can solve the technical problem of how to improve the efficiency of vehicle parking. Compared with the prior art, the beneficial effects of the path replanning device provided by the present application are the same as the beneficial effects of the path replanning method provided by the above embodiment, and the other technical features in the path replanning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0165] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0166] 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.

[0167] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the path replanning method in the above-mentioned embodiment.

[0168] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0169] The computer-readable storage medium may be included in the path replanning device; or may exist independently without being assembled into the path replanning device.

[0170] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the path replanning device, the path replanning device: obtains an initial parking path, vehicle status information, and vehicle surrounding perception information; performs collision detection on the initial parking path based on the vehicle status information and the vehicle surrounding perception information to obtain a collision detection result; if it is detected that there is a collision risk when the vehicle travels along the initial parking path, then based on the collision detection result and a dynamic replanning algorithm, the initial parking path is replanned to obtain a replanned path.

[0171] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0172] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0174] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned path replanning method, and can solve the technical problem of how to improve the efficiency of vehicle parking. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the path replanning method provided in the above-mentioned embodiment, and will not be repeated here.

[0175] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the path replanning method as described above when executed by a processor.

[0176] The computer program product provided in this application can solve the technical problem of how to improve the efficiency of vehicle parking. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the path replanning method provided in the above embodiment, which will not be repeated here.

[0177] An embodiment of the present application provides a vehicle, comprising a path replanning device as provided in the above embodiment.

[0178] The vehicle provided in this application can solve the technical problem of how to improve the efficiency of vehicle parking. Compared with the prior art, the beneficial effects of the vehicle provided in the embodiment of this application are the same as the beneficial effects of the path replanning method provided in the above embodiment, which will not be repeated here.

[0179] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A path replanning method, characterized in that: The method is applied to a vehicle, and comprises: Obtain the initial parking path, vehicle status information, and vehicle surrounding perception information; Based on the vehicle state information and the vehicle surrounding perception information, a collision detection is performed on the initial parking path to obtain a collision detection result, wherein the collision detection result includes a collision stop flag and collision information; If it is detected that there is a collision risk when the vehicle travels along the initial parking path, the initial parking path is replanned based on the collision detection result and the dynamic replanning algorithm to obtain a replanned path, which specifically includes the following steps: When the collision stop flag is a preset value, it is confirmed that there is a collision risk when the vehicle travels according to the initial parking path; Using a path planning thread, according to the collision information and a dynamic replanning algorithm, an advance planning point is calculated, wherein the advance planning point refers to a reference point on the initial parking path, which is used to guide the vehicle to avoid the collision point and smoothly transition to the replanning path; When the number of path replanning times is not greater than the preset first number, the initial parking path is replanned based on the dynamic replanning algorithm according to the advance planning points, vehicle status information and obstacle information, until the vehicle travels along the parking path after path replanning without collision risk, thereby obtaining a replanned path.

2. The method according to claim 1, characterized in that The step of performing collision detection on the initial parking path based on the vehicle state information and the vehicle surrounding perception information to obtain a collision detection result includes: Based on the preset cycle, the collision detection thread is used regularly to confirm obstacle information based on the vehicle's surrounding perception information; Predicting a driving area of ​​the vehicle on the initial parking path according to the vehicle state information using a collision detection thread; According to the driving area and obstacle information, it is detected whether there is a risk of collision between the vehicle and the obstacle, and a collision detection result is obtained.

3. The path replanning method according to claim 2, characterized in that: The dynamic replanning algorithm includes a preset optimization algorithm and a preset heuristic path search algorithm, the advance planning point includes a first planning point and a second planning point, and the step of using the path planning thread to calculate the advance planning point according to the collision information and the dynamic replanning algorithm includes: When the dynamic replanning algorithm is a preset optimization algorithm, a path planning thread is used to calculate a first planning point according to the vehicle state information in the collision information; When the dynamic replanning algorithm is a preset heuristic path search algorithm, a path planning thread is used to establish an object polygon map model according to the vehicle state information and obstacle information in the collision information; Using the object polygon map model, a safe obstacle stopping point is determined according to the overlapping area between the vehicle polygon and the obstacle polygon; A second planning point is determined based on the safety obstacle stopping point and the vehicle status information.

4. The path replanning method according to claim 3, characterized in that: The number of path replanning times includes the number of path optimization times and the number of path search times. When the number of path replanning times is not greater than the preset first number, the initial parking path is replanned based on the advance planning points, vehicle state information and obstacle information based on a dynamic replanning algorithm until the vehicle travels along the parking path after the path replanning without collision risk, and the step of obtaining the replanned path includes: When the number of path optimizations is less than the preset second number, the preset optimization algorithm is used to optimize the initial parking path according to the first planning point, the vehicle state information and the obstacle information to obtain a first planning path; Using a collision detection thread to perform collision detection on the first planned path; When the vehicle is at risk of collision when traveling along the first planned path, the process returns to the execution step: when the number of path optimizations is less than the preset second number, the initial parking path is optimized using a preset optimization algorithm according to the first planned point, the vehicle state information, and the obstacle information, until the number of path optimizations is equal to the preset second number or the vehicle is at risk of collision when traveling along the first planned path; When the number of path optimizations is equal to the preset second number and the number of path searches is not greater than the preset third number, using a preset heuristic path search algorithm, the initial parking path is replanned according to the second planning point, the vehicle state information and the obstacle information to obtain a second planned path; Using a collision detection thread to perform collision detection on the second planned path; When there is a risk of collision when the vehicle travels along the second planned path, the process returns to the execution step: when the number of path optimizations is equal to the preset second number, and the number of path searches is not greater than the preset third number, the initial parking path is replanned using a preset heuristic path search algorithm according to the second planned points, the vehicle state information, and the obstacle information, until the number of path searches is greater than the preset third number or there is no risk of collision when the vehicle travels along the second planned path; When there is no collision risk when the vehicle travels along the first planned path, using the first planned path as the re-planned path; or When there is no collision risk when the vehicle travels along the second planned path, the second planned path is used as the re-planned path.

5. The method according to claim 4, characterized in that The initial parking path includes a target parking point, and the step of using a preset heuristic path search algorithm to replan the initial parking path according to the second planned point, vehicle state information, and obstacle information to obtain a second planned path includes: Using a preset heuristic path search algorithm, according to the vehicle state information and obstacle information, a path search is performed between the second planning point and the target parking point to obtain a searched path; According to the second planning point, the searched path is spliced ​​with the initial parking path to obtain a spliced ​​parking path; The spliced ​​parking path is subjected to trajectory smoothing processing to obtain a second planned path.

6. The method according to any one of claims 3 to 5, characterized in that The method further comprises: When the number of path replanning times is greater than the preset first number, a collision detection thread is used to send a stop signal to the vehicle to control the vehicle to stop at the safety stop point; or In the process of replanning the initial parking path by the path planning thread, detecting the collision distance between the vehicle and the obstacle by using the collision detection thread; When the collision distance is less than the minimum safety distance, a collision detection thread is used to send a stop signal to the vehicle to control the vehicle to stop at the safety stop point.

7. A path replanning device, characterized in that: The path re-planning device comprises: An acquisition module, used to acquire an initial parking path, vehicle status information, and vehicle surrounding perception information; A collision detection module, configured to perform collision detection on the initial parking path based on vehicle state information and vehicle surrounding perception information to obtain a collision detection result, wherein the collision detection result includes a collision stop flag and collision information; A path replanning module, for replanning the initial parking path based on the collision detection result and the dynamic replanning algorithm to obtain a replanned path if it is detected that there is a collision risk when the vehicle travels along the initial parking path; The path replanning module is further configured to confirm that there is a risk of collision when the vehicle travels along the initial parking path when the collision stop flag is a preset value; Using a path planning thread, according to the collision information and a dynamic replanning algorithm, an advance planning point is calculated, wherein the advance planning point refers to a reference point on the initial parking path, which is used to guide the vehicle to avoid the collision point and smoothly transition to the replanning path; When the number of path replanning times is not greater than the preset first number, the initial parking path is replanned based on the dynamic replanning algorithm according to the advance planning points, vehicle status information and obstacle information, until the vehicle travels along the parking path after path replanning without collision risk, thereby obtaining a replanned path.

8. A path replanning device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the path replanning method according to any one of claims 1 to 6.

9. A vehicle, characterized in that: The vehicle comprises the path replanning device of claim 8.

Images