Robot path planning method and device, storage medium and electronic equipment
By segmenting the map into sub-contours and planning point-to-point and narrow passage paths, combined with LiDAR detection, the robot can safely pass through fire doors, solving the path planning difficulties of traditional navigation methods and enabling the robot to successfully pass through fire doors.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-30
- Publication Date
- 2026-03-31
AI Technical Summary
When a robot passes through a fire door, traditional point-to-point navigation methods are difficult to use because the distance between the two sides of the fire door is smaller than the grid size, making path planning difficult.
The map is divided into several sub-outlines, and point-to-point navigation paths and narrow passage paths are planned. The depth camera is turned off when driving on narrow passage paths. LiDAR is used to detect obstacles. When passing through fire doors, dynamic obstacles are detected and waited for to disappear or point-to-point navigation mode is used.
The robot can safely and effectively pass through fire doors, avoiding the problem of depth cameras misidentifying the inside of fire doors as blank areas or obstacles, thus improving the success rate and efficiency of path planning.
Smart Images

Figure CN121764058A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of path planning, and specifically relates to a robot path planning method, apparatus, storage medium, and electronic device. Background Technology
[0002] For safety reasons, residential buildings install fire doors in the common areas of each floor. These doors divide the common areas into several zones to protect residents' lives in the event of a fire. Typically, only one fire door can be opened at a time. This poses a significant challenge to robots cleaning the entire common area of a floor, as the distance between the robot and the sides of the fire door is less than the size of a grid, making it difficult for the robot to pass through using traditional point-to-point navigation methods. When planning point-to-point navigation paths, the map is typically divided into several grids, and then a search algorithm is used to find the order in which the robot moves from its starting grid to its target grid. A grid size is typically 3cm x 3cm, 4cm x 4cm, or 5cm x 5cm. Summary of the Invention
[0003] In view of the above-mentioned shortcomings or defects in the prior art, the present invention provides a robot path planning method that can smoothly pass through fire doors.
[0004] The robot path planning method provided by the present invention includes: acquiring a map of the location of the task and fire doors on the map; and dividing the map into several sub-contours according to the fire doors.
[0005] Obtain the robot's starting point and target point, and determine whether the robot's starting point and target point are within the same sub-contour; if the robot's starting point and target point are not within the same sub-contour, plan the robot's operation path, the operation path including a point-to-point navigation path and a narrow passage path, the narrow passage path including the path from the fire door entry point to the fire door exit point, the point-to-point navigation path including at least the path from the robot's starting point to the fire door entry point and the path from the fire door exit point to the target point; while walking along the narrow passage path, turn off the robot's depth camera.
[0006] The path planning scheme provided by this invention plans the robot's path into two types when it needs to pass through a fire door: a point-to-point navigation path and a narrow passage path. When the robot travels along the narrow passage path, the robot's depth camera is turned off because the point cloud data detected by the depth camera is not stable enough. This can prevent the point cloud data detected by the depth camera from identifying the blank area inside the fire door as an obstacle, thus preventing the robot from passing through the fire door.
[0007] Optionally, the robot path planning method provided by the present invention further includes the following steps: detecting whether there is an obstacle at the fire door entrance; when an obstacle is detected at the fire door entrance, waiting for a preset time at a preset distance from the obstacle; when the obstacle disappears within the preset time, moving to the fire door entrance and passing through the fire door along the narrow passage path; when the obstacle does not disappear within the preset time, passing through the fire door through a point-to-point navigation mode.
[0008] Optionally, the robot path planning method provided by the present invention further includes the following steps: detecting whether there is an obstacle at the exit point of the fire door; when an obstacle is detected at the exit point of the fire door, waiting for a preset time at a preset distance from the obstacle; when the obstacle disappears within the preset time, moving to the exit point of the fire door; when the obstacle does not disappear within the preset time, first checking whether there is enough space to pass through, and if not, exiting along a narrow passage path to the entrance point of the fire door.
[0009] Optionally, the robot path planning method provided by the present invention further includes the following steps: determining whether the exit point of the fire door has been reached; if the exit point of the fire door has not been reached, obtaining the passage time of the robot from entering the fire door entry point to the current moment; determining whether the passage time is greater than a preset passage time; if the passage time is greater than the preset passage time, returning to the fire door entry point and retrying to pass through the fire door along the narrow passage path.
[0010] Optionally, the robot path planning method provided by the present invention further includes the following steps: detecting whether the target point is occupied by an obstacle; if the target point is occupied by an obstacle, obtaining the pixel values of the grids around the target point; selecting the grids around the target point whose pixel values are less than or equal to a preset pixel value as new target points.
[0011] Optionally, the robot path planning method provided by the present invention further includes the following steps: when the robot walks along the point-to-point navigation path, turning on the lidar and the depth camera; when the robot walks along the narrow passage path, turning on the lidar and turning off the depth camera.
[0012] Optionally, the robot path planning method provided by the present invention further includes the following steps: when it is determined that three or more sub-contours need to be traversed between the starting point and the target point, an algorithm is first used to plan the path from the starting point to the target point to determine the order of passing through the fire doors; based on the distance between the starting point and the two entry and exit points of the first fire door, the entry point and exit point of the first fire door are determined, and the first segment point-to-point navigation path and the first segment narrow passage path are determined; based on the distance between the exit point of the previous fire door and the entry and exit points of the next fire door, the entry point and exit point of the next fire door are determined, and the intermediate segment point-to-point navigation path and the intermediate segment narrow passage path are determined; based on the distance between the target point and the two entry and exit points of the last fire door, the entry point and exit point of the last fire door are determined, and the final segment point-to-point navigation path and the final segment narrow passage path are determined.
[0013] The robot path planning device provided by the present invention includes: an acquisition module for acquiring a map of the task location and fire doors on the map; a segmentation module for segmenting the map into several sub-contours based on the fire doors; a judgment module for acquiring the robot's starting point and target point, and judging whether the robot's starting point and target point are within the same sub-contour; and a planning module for planning the robot's operation path when the robot's starting point and target point are not within the same sub-contour. The operation path includes a point-to-point navigation path and a narrow passage path. The narrow passage path includes a path from the fire door entry point to the fire door exit point. The point-to-point navigation path includes at least a path from the robot's starting point to the fire door entry point and a path from the fire door exit point to the target point. When walking along the narrow passage path, the robot's depth camera is turned off.
[0014] Optionally, the robot path planning device provided by the present invention further includes: a determination module, which, when it is determined that three or more sub-contours need to be traversed, first uses a preset search algorithm to plan the path between the starting point and the target point to determine the order of passing through the fire doors; a first-segment path planning module, which determines the entry point and exit point of the first fire door based on the distance between the starting point and the two entry and exit points of the first fire door, and determines the first-segment point-to-point navigation path and the first-segment narrow passage path; and a middle-segment path planning module, which determines the entry point and exit point of the next fire door based on the distance between the exit point of the previous fire door and the entry and exit points of the next fire door, and determines the middle-segment point-to-point navigation path and the middle-segment narrow passage path;
[0015] The final path planning module determines the entry and exit points of the last fire door based on the distance between the target point and the two entry and exit points of the last fire door, and also determines the final point-to-point navigation path and the path through the narrowest passage in the final section.
[0016] The storage medium provided by the present invention stores a computer program, which, when executed, implements the above-described robot path planning method.
[0017] The electronic device provided by the present invention includes a processor and a memory, wherein the memory stores instructions, which are loaded and executed by the processor to implement the above-described robot path planning method. Attached Figure Description
[0018] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without any inventive effort. In the drawings:
[0019] Figure 1 A flowchart for robot path planning;
[0020] Figure 2 This is a map outline;
[0021] Figure 3 This is a path planning diagram. Detailed Implementation
[0022] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention. The present invention will now be described in detail with reference to the accompanying drawings and embodiments. Figure 2 The map outline is typical, consisting of a long corridor and cleaning areas on either side of the corridor, with fire doors between the corridor and the cleaning areas, as well as on the corridor itself.
[0023] The robot path planning method provided in this embodiment includes the following steps:
[0024] S1 obtains the map where the task is located and the fire doors on the map;
[0025] S2 divides the map into several sub-outlines according to the fire door;
[0026] S3 obtains the robot's starting point and target point, and determines whether the robot's starting point and target position are within the same sub-contour;
[0027] S4 If the robot's starting point and target point are not within the same sub-contour, plan the robot's operation path. The operation path includes a point-to-point navigation path and a narrow passage path. The narrow passage path includes the path from the fire door entry point to the fire door exit point. The point-to-point navigation path includes at least the path from the robot's starting point to the fire door entry point and the path from the fire door exit point to the target location point. When walking along the narrow passage path, turn off the robot's depth camera.
[0028] The fire door entry point is located outside the fire door entrance and at a first preset distance from the entrance, while the fire door exit point is located outside the fire door exit and at a second preset distance from the exit. Both the entry and exit points are located at the center of the fire door's width, specifically the center of a single fire door. The height of the fire door is the same as the height of the wall, the depth is the direction of entry and exit, and the width extends along the length of the wall.
[0029] When the robot needs to traverse more than two sub-contours between its starting point and target point, in addition to the path from the current location to the fire door entry point and the path from the fire door exit point to the target point, the point-to-point navigation path also includes the path from the previous fire door exit point to the next fire door entry point.
[0030] The entry and exit points of fire doors are pre-planned based on previous detection results, and updated according to new detection results when the robot approaches the fire door. For example, if there are two fire doors in the passage, and the fire doors usually open on the left, the exit and entry points of the fire doors are planned on the center line of the width direction of the left fire door. However, if the robot finds that the fire door on the right is open when it approaches, the exit and entry points of the fire doors are planned on the center line of the width direction of the right fire door. The center line is the direction in which users enter and exit the fire doors.
[0031] There are three key points in time for path planning. The first is when the robot is executing the previous sub-task and preparing to execute the next one. In this case, the starting point is the end point of the previous sub-task, and the target point is the start point of the next sub-task. The second is when the robot is idle at the workstation and receives a non-floor-crossing task. In this case, the starting point is the workstation location, and the target point is the task's starting point. The third is when the robot is idle at the workstation and receives a cross-floor task. In this case, two path planning steps are required: one for the path from the workstation location to the elevator waiting point, and another for the path from the elevator exit point to the target point. During the first path planning, the starting point is the workstation location, and the target point is the elevator waiting point. During the second path planning, the starting point is the elevator exit point, and the target point is the task's starting point.
[0032] The first and second preset distances are set based on the premise that the robot can complete the turning action when it reaches the entry point and exit point. In this embodiment, the first and second preset distances are 20 cm to 40 cm, and are specifically set according to the parameters of different machines. The first preset distance is the distance from the entry point to the wall where the fire door entrance is located, and the second preset distance is the distance from the exit point to the wall where the fire door exit is located.
[0033] The robot's sensors include a lidar on top, line lasers on the lower left and right sides of the robot's front face, a line laser on the upper right side of the robot's front face, a depth camera in the middle of the upper front face, and an ultrasonic sensor in the middle of the lower front face. In the path planning scheme provided in this embodiment, the robot simultaneously activates all sensors to obtain more obstacle data when traveling along a point-to-point navigation path; the depth camera is deactivated when traveling along narrow passages. Because the point cloud data detected by lidar is more stable than that detected by the depth camera, it can accurately detect obstacles on both sides of the fire door and will not identify the blank areas inside the fire door as obstacles, allowing the robot to safely pass through the fire door. In this embodiment, the robot passes through the fire door by using lidar to detect the contours of both sides of the fire door, finding the center line of the contours, and then traveling along the center line. The robot's depth cameras include a top-view depth camera and a bottom-view depth camera. Even the bottom-view depth camera has a sufficient field of view to detect obstacles inside fire doors at the point of entry, which reduces the impact of not being able to detect obstacles inside fire doors in time when the depth camera is turned off in narrow passages.
[0034] When preparing to cross a narrow passage, the robot needs to first check whether there are obstacles at the fire door entrance. Specifically, this includes the following steps: detecting whether there are obstacles at the fire door entrance; if an obstacle is detected, waiting at a preset distance from the obstacle for a preset time; if the obstacle disappears within the preset time, moving to the fire door entrance and passing through the fire door along the narrow passage path; if the obstacle does not disappear within the preset time, moving through the fire door using point-to-point navigation mode.
[0035] Generally, fire door entrances are not usually blocked by static obstacles. If an obstacle is detected, it is initially assumed to be a dynamic obstacle. Therefore, wait at the fire door for a period of time until the dynamic obstacle disappears before attempting to pass through. If the dynamic obstacle does not disappear, assume that both fire doors are open, i.e., assume there is sufficient distance between the fire doors, and attempt to pass through using point-to-point navigation.
[0036] When the robot is about to exit the fire door, it needs to check whether there are any obstacles at the exit point of the fire door. The specific steps include: checking whether there are any obstacles at the exit point of the fire door; if an obstacle is detected at the exit point of the fire door, waiting for a preset time at a preset distance from the obstacle; if the obstacle disappears within the preset time, moving to the exit point of the fire door; if the obstacle does not disappear within the preset time, first checking whether there is enough space to pass through. If not, it exits along the narrow passage path to the entrance point of the fire door.
[0037] When the robot is about to reach the target point, it also needs to confirm whether the target point is occupied by obstacles. Specifically, this includes the following steps: detecting whether the target point is occupied by obstacles; if the target point is occupied by obstacles, acquiring the pixel values of the grid cells surrounding the target point; selecting the grid cells around the target point whose pixel values are less than or equal to a preset pixel value as new target points. The pixel value of the grid cell in the obstacle area is higher than the pixel value of the grid cell in the vicinity of the obstacle, and higher than the pixel value of the grid cell in the obstacle-free area. Detecting whether the target point is occupied by obstacles is also determined by judging whether the pixel value of the grid cell where the target point is located meets the preset requirements.
[0038] This embodiment also considers the time it takes for the robot to pass through a fire door. If the robot tilts to one side while passing through the fire door and continues to tilt in that direction due to a misadjustment, it will result in an excessively long time for the robot to pass through the narrow passage. In this case, this embodiment will allow the robot to first return to the fire door entrance point and try to enter again. Specifically, this includes the following steps: determining whether the exit point of the fire door has been reached; if the exit point of the fire door has not been reached, obtaining the passage time from the time the robot entered the fire door entrance point to the current moment; determining whether the passage time is greater than a preset passage time; if the passage time is greater than the preset passage time, returning to the fire door entrance point and re-attempting to pass through the fire door along the narrow passage path. The preset passage time can be, for example, 40 seconds.
[0039] The robot path planning method provided in this embodiment, when traversing three or more sub-contours between the starting point and the target point (the three or more sub-contours include the sub-contour where the starting point is located and the sub-contour where the target point is located), specifically includes the following steps: First, a preset search algorithm is used to plan the path from the starting point to the target point to determine the order of passing through fire doors. Second, based on the distance between the starting point and the two entrance / exit points of the first fire door, the entrance and exit points of the first fire door are determined, and the first segment of point-to-point navigation path and the first segment of narrow passage path are determined. Third, based on the distance between the exit point of the previous fire door and the entrance / exit point of the next fire door, the entrance and exit points of the next fire door are determined, and the intermediate segment of point-to-point navigation path and the intermediate segment of narrow passage path are determined. Fourth, based on the distance between the target point and the two entrance / exit points of the last fire door, the entrance and exit points of the last fire door are determined, and the final segment of point-to-point navigation path and the final segment of narrow passage path are determined. The preset search algorithm is, for example, Dijkstra's algorithm.
[0040] The entry and exit points of a fire door are collectively referred to as the fire door entry and exit points. These points vary depending on the direction of entry and exit. For the first fire door, the entry point is the one closer to the starting point, and the exit point is the one farther away. The path from the starting point to the first fire door entry point is the initial point-to-point navigation path, and the path from the first fire door entry point to the exit point is the initial narrow passage path. Similarly, for the next fire door, the entry point is the one closer to the previous fire door exit point, and the exit point is the one farther away. The path from the previous fire door exit point to the next fire door entry point is the intermediate point-to-point navigation path, and the path from the next fire door entry point to the next fire door exit point is the intermediate narrow passage path. Similarly, for the next fire door, the point closer to the target point is the exit point, and the point farther from the target point is the entry point. The path from the exit point of the last fire door to the target point is the final point-to-point navigation path, and the path from the entry point of the last fire door to the exit point is the final narrow passage path. For example... Figure 3 As shown, s is the starting point, e is the target point, a is the entry point of the first fire door, b is the exit point of the first fire door, c is the entry point of the second fire door, and d is the exit point of the second fire door.
[0041] This embodiment also provides a robot path planning device, including: an acquisition module for acquiring a map of the task location and fire doors on the map; a segmentation module for segmenting the map into several sub-contours based on the fire doors; a judgment module for acquiring the robot's starting point and target point, and judging whether the robot's starting point and target point are within the same sub-contour; and a planning module for planning the robot's operation path when the robot's starting point and target point are not within the same sub-contour. The operation path includes a point-to-point navigation path and a narrow passage path. The narrow passage path includes a path from the fire door entry point to the fire door exit point. The point-to-point navigation path includes at least a path from the robot's starting point to the fire door entry point and a path from the fire door exit point to the target point. The fire door entry point is located outside the fire door entrance and at a first preset distance from the fire door entrance, and the fire door exit point is located outside the fire door exit and at a second preset distance from the fire door exit.
[0042] This embodiment also provides an electronic device, including a processor and a memory. The memory stores instructions, which are loaded and executed by the processor to implement the aforementioned robot path planning method. The electronic device also includes a communication interface for communicating with external devices and exchanging data. If the memory, processor, and communication interface are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be categorized as an address bus, data bus, control bus, etc. If the memory, processor, and communication interface are integrated on a single chip, they can communicate with each other through an internal interface.
[0043] This embodiment provides a computer-readable storage medium storing a computer program, which, when executed, implements the robot path planning method described above.
[0044] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. It is worth noting that the processor can be a processor supporting the Advanced Reduced Instruction Set Computing (RISC) machine (ARM) architecture.
[0045] The memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).
[0046] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention. Furthermore, the information disclosed in the various embodiments in the specific implementation details can be used for mutual reference.
[0047] Furthermore, various different implementations of this application can be combined in any way, as long as they do not violate the spirit of this application, they should also be regarded as the content disclosed in this application.
Claims
1. A robot path planning method, characterized by, The method comprises the following steps: acquiring a map where a work task is located and a fire door on the map; segmenting the map into several sub-contours according to the fire door; acquiring a starting point and a target point of the robot, and judging whether the starting point and the target point of the robot are in the same sub-contour; when the starting point and the target point of the robot are not in the same sub-contour, planning a work path of the robot, wherein the work path comprises a point-to-point navigation path and a narrow passage path, the narrow passage path comprises a path between an entering point and an exiting point of the fire door, the point-to-point navigation path at least comprises a path between the starting point and the entering point of the fire door and a path between the exiting point of the fire door and the target point, and a depth camera of the robot is closed when the robot walks along the narrow passage path.
2. The robot path planning method of claim 1, wherein, The method comprises the following steps: detecting whether there is an obstacle at the entering point of the fire door; when it is detected that there is an obstacle at the entering point of the fire door, waiting for a preset time at a preset distance from the obstacle; when the obstacle disappears within the preset time, moving to the entering point of the fire door and passing through the fire door along the narrow passage path; when the obstacle does not disappear within the preset time, attempting to pass through the fire door in a point-to-point navigation mode.
3. The robot path planning method of claim 1, wherein, The method comprises the following steps: detecting whether there is an obstacle at the exiting point of the fire door; when it is detected that there is an obstacle at the exiting point of the fire door, waiting for a preset time at a preset distance from the obstacle; when the obstacle disappears within the preset time, moving to the exiting point of the fire door; when the obstacle does not disappear within the preset time, first detecting whether there is enough passing space, and if there is, switching to the point-to-point navigation mode to pass through, and if not, exiting to the entering point of the fire door along the narrow passage path.
4. The robot path planning method of claim 1, wherein, The method comprises the following steps: judging whether the exiting point of the fire door is reached; if the exiting point of the fire door is not reached, acquiring a passing time of the robot from the entering point of the fire door to the current time; judging whether the passing time is greater than a preset passing time; if the passing time is greater than the preset passing time, returning to the entering point of the fire door and reattempting to pass through the fire door along the narrow passage path.
5. The robotic path planning method of claim 1, wherein, The method comprises the following steps: detecting whether the target point is occupied by an obstacle; if the target point is occupied by an obstacle, acquiring pixel values of grids around the target point; selecting grids with pixel values less than or equal to a preset pixel value as new target points.
6. The robotic path planning method of claim 1, wherein, The method comprises the following steps: when it is determined that three or more sub-contours need to be crossed, first planning a path between the starting point and the target point by using a preset search algorithm to determine the order of passing through the fire doors; according to distances between the starting point and two entering and exiting points of a first fire door, determining the entering point and the exiting point of the first fire door and determining a first section of point-to-point navigation path and a first section of narrow passage path; according to distances between an exiting point of a last fire door and two entering and exiting points of a next fire door, determining the entering point and the exiting point of the next fire door and determining a middle section of point-to-point navigation path and a middle section of narrow passage path; according to distances between the target point and two entering and exiting points of a last fire door, determining the entering point and the exiting point of the last fire door and determining a last section of point-to-point navigation path and a last section of narrow passage path.
7. A robot path planning apparatus characterized by comprising: The method comprises the following steps: An acquisition module acquires a map where a task is located and a fire door on the map; A segmentation module segments the map into a plurality of sub-contours according to the fire doors; A determination module acquires a starting point and a target point of a robot, and determines whether the starting point and the target point are in a same sub-contour; A planning module plans a task path of the robot when the starting point and the target point are not in the same sub-contour, the task path including a point-to-point navigation path and a narrow passage path, the narrow passage path including a path between an entering point and an exiting point of the fire door, and the point-to-point navigation path including at least a path between the starting point and the entering point of the fire door, and a path between the exiting point of the fire door and the target point, and the robot closes a depth camera when walking along the narrow passage path.
8. The robotic path planning device of claim 7, wherein, Further comprising: A determination module determines a path between the starting point and the target point by using a preset search algorithm to determine a passing order of the fire doors when it is determined that three or more sub-contours need to be crossed; A first path planning module determines an entering point and an exiting point of a first fire door according to a distance between the starting point and two entering and exiting points of the first fire door, and determines a first point-to-point navigation path and a first narrow passage path; A middle path planning module determines an entering point and an exiting point of a next fire door according to a distance between an exiting point of a previous fire door and two entering and exiting points of the next fire door, and determines a middle point-to-point navigation path and a middle narrow passage path; A last path planning module determines an entering point and an exiting point of a last fire door according to a distance between the target point and two entering and exiting points of the last fire door, and determines a last point-to-point navigation path and a last narrow passage path.
9. A storage medium, characterized by The computer readable storage medium stores a computer program, and the computer program is executed to implement the robot path planning method according to any one of claims 1 to 6.
10. An electronic device, comprising: The processor and the memory are included, and the memory stores instructions, the instructions are loaded and executed by the processor to implement the robot path planning method according to any one of claims 1 to 6.