Underground path planning method, device and equipment and storage medium

Abstract

The invention discloses an underground path planning method, device and equipment and a storage medium, and the method comprises the steps: combining a vehicle driving region given by a perception sensor with a field angle of the sensor, so as to generate a vehicle driving region boundary; performing conversion processing on the boundary of the vehicle driving area to generate a grid map; and determining a starting point and a target point of the vehicle based on the grid map, generating path control points by adopting a path search algorithm, and fitting the path control points to plan a driving path. According to the method, the problem that blind areas are limited during underground operation can be effectively solved, the path generation time can be shortened, and the path planning speed is increased.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an underground path planning method, device, equipment and storage medium. Background Art

[0002] The industry's autonomous driving path planning is mainly used in structured road scenarios such as highways and cities. The planning technology solutions adopted are not fully applicable to unstructured roads underground, and do not take into account the characteristics of narrow underground space, uneven mine walls, and irregular road edges.

[0003] In the existing technology, the road boundary can be obtained based on map, perception, positioning and other information to plan a drivable path. However, the limited perception blind spot is not taken into account. When generating a path, random sampling is performed from the vehicle starting point, and the sampling points are connected to generate a path. This method requires sufficient sampling points. As the number of sampling points increases, the time consumption increases, resulting in a decrease in the path planning rate.

[0004] Therefore, how to plan paths and improve the path planning speed is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and storage medium for underground path planning, which can effectively solve the problem of blind area limitation during underground operations, and can also reduce the time of path generation and improve the path planning rate.

[0006] In a first aspect, the present application provides a method for downhole path planning, wherein the method comprises the steps of:

[0007] The vehicle driving area given by the perception sensor is combined with the sensor field of view to generate the boundary of the vehicle driving area;

[0008] Converting the boundary of the vehicle driving area to generate a grid map;

[0009] Based on the grid map, the vehicle starting point and target point are determined, and a path search algorithm is used to generate path control points, and the path control points are fitted to plan the driving path.

[0010] In combination with the first aspect above, as an optional implementation method, the point cloud information collected by the perception sensor is decoded to generate boundary point cloud information;

[0011] The boundary point cloud information is combined with the field of view of the sensor to fill the vehicle driving blind spot and generate a single layer of point cloud data;

[0012] The single-layer point cloud data is screened and processed to obtain the boundary of the vehicle driving area.

[0013] In combination with the first aspect above, as an optional implementation method, a grid map is generated using a breadth-first search algorithm according to the boundary of the vehicle driving area.

[0014] In combination with the first aspect above, as an optional implementation method, the starting point and the target point of the vehicle are determined in the grid map;

[0015] The initial radius is determined according to the vehicle width and calibration parameters, and a circle is determined with the starting point and the target point as the center of the circle respectively;

[0016] Control the rings to move towards each other and determine whether they collide with the wall.

[0017] If not, store the center point of the circle that does not hit the wall and use it as the path control point.

[0018] If so, calculate the collision value and blind area value of the current center in multiple directions, and iterate the ring towards the maximum gradient in multiple directions, move the center or reduce the radius until the ring does not collide with the wall, and store the center of the ring that does not hit the wall as the control point.

[0019] In combination with the first aspect above, as an optional implementation method, it is determined whether the circles in the directions of the starting point and the target point meet each other while moving toward each other;

[0020] If they meet, the search ends; if they do not meet, the center of the circle is moved and they move toward each other until they meet.

[0021] In combination with the first aspect above, as an optional implementation method, a quintic polynomial fitting algorithm is used to fit the control points to generate a planned path.

[0022] In a second aspect, the present application provides a downhole path planning device, the device comprising:

[0023] A processing module, which is used to combine the vehicle driving area given by the perception sensor with the sensor field of view to generate a boundary of the vehicle driving area;

[0024] A generation module, which is used to convert the boundary of the vehicle driving area to generate a grid map;

[0025] The planning module is used to determine the vehicle starting point and target point based on the grid map, and adopt a path search algorithm to generate path control points, and fit the path control points to plan the driving path.

[0026] In a third aspect, the present application further provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method described in any one of the first aspects is implemented.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium storing computer program instructions, which, when executed by a computer, enables the computer to execute any of the methods described in the first aspect.

[0028] The present application provides a method, device, equipment and storage medium for underground path planning, wherein the method includes the steps of: combining the vehicle driving area given by the perception sensor with the sensor field of view to generate the boundary of the vehicle driving area; converting the boundary of the vehicle driving area to generate a grid map; based on the grid map, determining the vehicle starting point and target point, and using a path search algorithm to generate path control points, and fitting the path control points to plan the driving path. The present application can effectively solve the problem of blind spot limitation during underground operations, and can also reduce the time of path generation and improve the path planning rate.

[0029] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0031] Figure 1 A flow chart of a downhole path planning method provided in an embodiment of the present application;

[0032] Figure 2 A schematic diagram of a downhole path planning device provided in an embodiment of the present application;

[0033] Figure 3 A schematic diagram of a path search provided in an embodiment of the present application;

[0034] Figure 4 A schematic diagram of a ring search provided in an embodiment of the present application;

[0035] Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present application;

[0036] Figure 6 A schematic diagram of a computer-readable program medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0038] Furthermore, the drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. Some of the blocks shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities.

[0039] The embodiments of the present application provide a method, device, equipment and storage medium for underground path planning, which can effectively solve the problem of blind spot limitation during underground operations, and can also reduce the time of path generation and improve the path planning rate.

[0040] In order to achieve the above technical effects, the general idea of ​​this application is as follows:

[0041] A method for underground path planning, the method comprising the steps of:

[0042] S101: combining the vehicle driving area provided by the perception sensor with the sensor field of view to generate a boundary of the vehicle driving area.

[0043] S102: converting the boundary of the vehicle driving area to generate a grid map.

[0044] S103: Based on the grid map, determine the vehicle starting point and target point, use a path search algorithm to generate path control points, and fit the path control points to plan the driving path.

[0045] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0046] Reference Figure 1 , Figure 1 FIG. 1 is a flow chart of a downhole path planning method provided by the present invention, as shown in FIG. Figure 1 As shown, the method comprises the steps of:

[0047] Step S101: Combine the vehicle driving area given by the perception sensor with the sensor field of view to generate the boundary of the vehicle driving area.

[0048] Specifically, the point cloud information collected by the perception sensor is decoded to generate boundary point cloud information; the boundary point cloud information is combined with the field of view of the sensor to fill the vehicle driving blind spot and generate a single layer of point cloud data; the single layer of point cloud data is screened and processed to obtain the boundary of the vehicle driving area.

[0049] For easy understanding, an example is given. The point cloud information collected by the sensor is decoded to generate the boundary information available for planning; and based on the boundary information (boundary points of the drivable area, i.e., the boundary of the underground mine wall) and the field of view of the sensor (front radar field of view: 180 degrees; rear radar field of view: 120 degrees), the blind area is filled (i.e., the intersection with the boundary is searched counterclockwise from the right front of the vehicle according to the angle recognized by the sensor), a single-layer point cloud data is generated, and finally the boundary points of the drivable area are obtained. The single-layer point cloud of the front and rear radar field of view angles is filtered to determine the boundary of the drivable area. It should be noted that the boundary is three-dimensional, and it can be filtered into two dimensions through the intersection with the vehicle, leaving a single-layer point cloud information.

[0050] Step S102: converting the boundary of the vehicle driving area to generate a grid map.

[0051] Specifically, a raster map is generated using a breadth-first search algorithm based on the boundary of the vehicle driving area. It should be explained that Breadth-First Search (BFS) is an algorithm for traversing or searching a tree or graph. It starts from the root node (or any node) and gradually expands outward until the target node is found or the entire graph is traversed. BFS maintains a queue data structure during the search process, queues all adjacent nodes, and processes them one by one. This search method is particularly suitable for situations where the distance between nodes is close. It should be explained that the raster map is a raster data file obtained by computer processing of existing paper topographic maps. After scanning and digitizing, each topographic map undergoes geometric correction, color correction and data compression processing, and finally forms a raster data set that is consistent with the national basic scale topographic map in content, geometric accuracy and color.

[0052] Step S103: Based on the grid map, determine the vehicle starting point and target point, use a path search algorithm to generate path control points, and fit the path control points to plan the driving path.

[0053] Specifically, the vehicle's starting point and target point are determined in the grid map;

[0054] The initial radius is determined according to the vehicle width and calibration parameters, and a circle is determined with the starting point and the target point as the center of the circle respectively;

[0055] Control the rings to move towards each other and determine whether they collide with the wall.

[0056] If not, store the center point of the circle that does not hit the wall and use it as the path control point.

[0057] If so, calculate the collision value and blind area value of the current center in multiple directions, and iterate the ring towards the maximum gradient in multiple directions, move the center or reduce the radius until the ring does not collide with the wall, and store the center of the ring that does not hit the wall as the control point.

[0058] For easy understanding, an example is given to determine the starting point and the target point (end point): starting from the location of the vehicle, marking the target point (end point) in the drivable area. For example, two points AB are set in the grid map. When the vehicle is going to travel in the direction of AB, A and B are the visible range of the sensor, and the midpoint of AB is the target point (end point). It should be explained that point B is not used as the end point because A and B are the intersection points of the perceived places and the mine wall. If point B is used as the end point, the car will use the point on the wall as the target and will hit the wall. Therefore, the midpoint of AB is set as the target point, and the vehicle will not hit the wall.

[0059] Generate a search circle and search at the start and end points simultaneously: take the start and end points as the circle points, the initial radius is: vehicle width + a (a can be calibrated), determine the circle, move the circle points in the opposite direction at the same time to search, store the center points of the circle points that do not hit the wall, and use the center points of the circle points that do not hit the wall as the path control point. When the search circle will collide with the wall, calculate the collision value of the current circle center in 8 directions (the center point of the circle when it touches the wall during the search process) and the blind area value (the center point of the circle when the circle coincides with the blind area), iterate the circle in 8 directions (the directions of the four sides and four corners of the grid) at the maximum gradient, move the center point or reduce the radius until the circle does not collide with the wall, and then store the center point that does not hit the wall as the control point. The control points are fitted using a quintic polynomial fitting algorithm to generate a planned path.

[0060] It should be explained that the bidirectional circle search algorithm is a strategy for optimizing the search process by searching from two directions simultaneously: one from the starting point and the other from the target point. A breadth-first search is performed from both the starting point and the target point. If the fronts of the two searches meet, then a feasible solution is considered to have been found. The steps of this method include adding the starting node and the target node to the queue, marking them, and then alternately expanding the nodes in both directions until the meeting point is found.

[0061] In one embodiment, it is determined whether the circles in the direction of the starting point and the target point meet while moving toward each other; if they do, the search is terminated; if they do not, the centers of the circles are moved and they move toward each other until they meet.

[0062] It can be understood that the information obtained by the sensor (the point cloud information of the boundary of the drivable area) is combined with the sensor field of view to obtain the boundary information available for planning (the boundary of the underground mine wall), and convert the boundary information into a grid map. Based on the grid map, a two-way circle search algorithm is used to plan a collision-free path that meets the vehicle dynamics constraints, solving the planning problems faced by special scenarios in the mine.

[0063] Combined with the complex situation under the mine, blind spots are considered at the turns, and a grid map is generated based on sensor information. The starting point and target point are confirmed based on the grid map and vehicle information. The control point is quickly confirmed and smoothed through a two-way search algorithm to generate the target trajectory, which takes less time.

[0064] In summary, the present application provides a method, device, equipment and storage medium for underground path planning, wherein the method includes the steps of: combining the vehicle driving area given by the perception sensor with the sensor field of view to generate the boundary of the vehicle driving area; converting the boundary of the vehicle driving area to generate a grid map; based on the grid map, determining the vehicle starting point and target point, and using a path search algorithm to generate path control points, and fitting the path control points to plan the driving path. The present application can effectively solve the problem of blind spot limitation during underground operations, and can also reduce the time of path generation and improve the path planning rate.

[0065] Reference Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a downhole path planning device provided by the present invention, Figure 2 As shown, the device comprises:

[0066] Processing module 201: It is used to combine the vehicle driving area given by the perception sensor with the sensor field of view to generate the boundary of the vehicle driving area.

[0067] The generation module 202 is used to convert the boundary of the vehicle driving area to generate a grid map.

[0068] Planning module 203: It is used to determine the vehicle starting point and target point based on the grid map, and use a path search algorithm to generate path control points, and fit the path control points to plan the driving path.

[0069] Furthermore, in a possible implementation manner, the processing module is further used to decode the point cloud information collected by the perception sensor to generate boundary point cloud information;

[0070] The boundary point cloud information is combined with the field of view of the sensor to fill the vehicle driving blind spot and generate a single layer of point cloud data;

[0071] The single-layer point cloud data is screened and processed to obtain the boundary of the vehicle driving area.

[0072] Furthermore, in a possible implementation manner, the generating module is further configured to generate a grid map using a breadth-first search algorithm according to the boundary of the vehicle driving area.

[0073] Furthermore, in a possible implementation manner, the planning module is also used to determine a starting point and a target point of the vehicle in the grid map;

[0074] The initial radius is determined according to the vehicle width and calibration parameters, and a circle is determined with the starting point and the target point as the center of the circle respectively;

[0075] Control the rings to move towards each other and determine whether they collide with the wall.

[0076] If not, store the center point of the circle that does not hit the wall and use it as the path control point.

[0077] If so, calculate the collision value and blind area value of the current center in multiple directions, and iterate the ring towards the maximum gradient in multiple directions, move the center or reduce the radius until the ring does not collide with the wall, and store the center of the ring that does not hit the wall as the control point.

[0078] Furthermore, in a possible implementation manner, the processing module is further used to determine whether the circles in the directions of the starting point and the target point meet each other while moving toward each other;

[0079] If they meet, the search ends; if they do not meet, the center of the circle is moved and they move toward each other until they meet.

[0080] Furthermore, in a possible implementation manner, the planning module is further configured to fit the control points using a quintic polynomial fitting algorithm to generate a planned path.

[0081] Reference Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a path search provided by the present invention. Figure 3 As shown:

[0082] Determine the starting point and target point on the grid map, with the starting point and the end point as the circle point, and the initial radius is: vehicle width + a (a can be calibrated parameter). Determine the circle, and the circle moves towards each other to search at the same time to determine whether the circle hits the wall. If not, store the center point of the circle that does not hit the wall, and use the center of the circle that does not hit the wall as the path control point. If so, that is, when the search circle will collide with the wall, calculate the collision value and blind area value of the current center in 8 directions, iterate towards the maximum gradient in the 8 directions, move the center or reduce the radius, and continue to return to the judgment of hitting the wall until it does not collide with the wall, and then store the center of the circle that does not hit the wall as the control point.

[0083] After storing the center of the circle that does not hit the wall as the control point, determine whether the two circles meet. If so, end. If not, move the centers of each circle towards each other, that is, the center of the starting point moves towards the end point, and the center of the end point moves towards the starting point.

[0084] For unstructured roads and irregular mine wall scenes under the mine, the drivable area given by perception is combined with the sensor field of view to generate the boundary of the drivable area to solve the problem of blind spots on curves; a bidirectional circle iterative search algorithm is used to improve the accuracy and efficiency of path generation.

[0085] Reference Figure 4 , Figure 4 FIG. 1 is a schematic diagram of a path search provided by the present invention. Figure 4 As shown: Take the vehicle location as the starting point, mark the target point in the drivable area, take the starting point and the end point as the circle point, the initial radius is: vehicle width + a (a can be calibrated parameter), determine the circle, and the circle moves towards each other at the same time to search, such as Figure 4 Storage does not hit the wall (as shown above Figure 4 , the gray part is the wall part, and the white part is the drivable area) is used as the center point of the circle, and the center of the circle that does not hit the wall is used as the path control point. When the search circle collides with the wall, the collision value and blind area value of the current center of the circle in 8 directions are calculated, and the circle iterates toward the maximum gradient in the 8 directions, moves the center of the circle or reduces the radius until it does not collide with the wall, and then stores the center of the circle that does not hit the wall as the controller point. The circles in the starting and ending directions move towards each other until they meet.

[0086] Refer to the following Figure 5 The electronic device 500 according to this embodiment of the present invention is described. Figure 5 The electronic device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0087] like Figure 5 As shown, the electronic device 500 is in the form of a general computing device. The components of the electronic device 500 may include but are not limited to: at least one processing unit 510, at least one storage unit 520, and a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510).

[0088] The storage unit stores program codes, which can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0089] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 521 and / or a cache memory unit 522 , and may further include a read-only memory unit (ROM) 523 .

[0090] The storage unit 520 may also include a program / utility 524 having a set (at least one) of program modules 525, such program modules 525 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0091] Bus 530 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0092] The electronic device 500 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or may communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 550. Furthermore, the electronic device 500 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 560. As shown, the network adapter 560 communicates with other modules of the electronic device 500 via a bus 530. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0093] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0094] According to the solution of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present invention described in the above "Exemplary Method" section of the present specification.

[0095] refer to Figure 6 As shown, a program product 600 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0096] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0097] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0098] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0099] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0100] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0101] In summary, the present application provides a method, device, equipment and storage medium for underground path planning, wherein the method includes the steps of: combining the vehicle driving area given by the perception sensor with the sensor field of view to generate the boundary of the vehicle driving area; converting the boundary of the vehicle driving area to generate a grid map; based on the grid map, determining the vehicle starting point and target point, and using a path search algorithm to generate path control points, and fitting the path control points to plan the driving path. The present application can effectively solve the problem of blind spot limitation during underground operations, and can also reduce the time of path generation and improve the path planning rate.

[0102] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

Claims

1. A method for underground path planning, characterized in that: include: The vehicle driving area given by the perception sensor is combined with the sensor field of view to generate the boundary of the vehicle driving area; Converting the boundary of the vehicle driving area to generate a grid map; Based on the grid map, the vehicle starting point and target point are determined, and a path search algorithm is used to generate path control points, and the path control points are fitted to plan the driving path.

2. The method according to claim 1, characterized in that The step of combining the vehicle driving area provided by the perception sensor with the sensor field of view to generate a boundary of the vehicle driving area includes: Decode the point cloud information collected by the perception sensor to generate boundary point cloud information; The boundary point cloud information is combined with the field of view of the sensor to fill the vehicle driving blind spot and generate a single layer of point cloud data; The single-layer point cloud data is screened and processed to obtain the boundary of the vehicle driving area.

3. The method according to claim 1, characterized in that The converting process of the boundary of the vehicle driving area to generate a grid map includes: A grid map is generated according to the boundary of the vehicle driving area using a breadth-first search algorithm.

4. The method according to claim 1, characterized in that: The method of determining the vehicle starting point and target point based on the grid map and using a path search algorithm to generate path control points includes: Determine the starting point and target point of the vehicle in the grid map; The initial radius is determined according to the vehicle width and calibration parameters, and a circle is determined with the starting point and the target point as the center of the circle respectively; Control the rings to move towards each other and determine whether they collide with the wall. If not, store the center point of the circle that does not hit the wall and use it as the path control point. If so, calculate the collision value and blind area value of the current center in multiple directions, and iterate the ring towards the maximum gradient in multiple directions, move the center or reduce the radius until the ring does not collide with the wall, and store the center of the ring that does not hit the wall as the control point.

5. The method according to claim 4, characterized in that include: Determine whether the circles in the direction of the starting point and the target point meet each other while moving towards each other; If they meet, the search ends; If they do not meet, move the center of the circle and move toward each other until they meet.

6. The method according to claim 1, characterized in that The fitting of the path control points to plan the driving path includes: The control points are fitted using a quintic polynomial fitting algorithm to generate a planned path.

7. A downhole path planning device, characterized in that: include: A processing module, which is used to combine the vehicle driving area given by the perception sensor with the sensor field of view to generate a boundary of the vehicle driving area; A generation module, which is used to convert the boundary of the vehicle driving area to generate a grid map; The planning module is used to determine the vehicle starting point and target point based on the grid map, and adopt a path search algorithm to generate path control points, and fit the path control points to plan the driving path.

8. The device according to claim 7, characterized in that: The processing module is also used to decode the point cloud information collected by the perception sensor to generate boundary point cloud information; The boundary point cloud information is combined with the field of view of the sensor to fill the vehicle driving blind spot and generate a single layer of point cloud data; The single-layer point cloud data is screened and processed to obtain the boundary of the vehicle driving area.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer program instructions are stored therein, and when the computer program instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

Images