Robot target point range navigation method based on grid map

Abstract

The invention relates to the technical field of robot navigation, in particular to a method for robot target point range navigation based on a grid map. Comprising the following steps: constructing a grid map, and marking according to whether a barrier exists in a grid; finding a shortest path from a starting point to an end point on the grid map through a path planning algorithm; potential field expansion calculation is carried out from the starting point, the potential field range is expanded on the grid map, grids which can be reached by the robot are determined, and each grid has a potential field value which represents the distance or cost from the grid to the starting point; when the target point is not reachable, searching a new reachable point near the target point as a new target point; after all candidate points are searched, sorting the candidate points according to an application scene; taking out a first candidate point from the sorted candidate point list as a current candidate point; and acquiring a path from the starting point to the current candidate point by using a path planning algorithm. According to the technical scheme, the reasonability of the target point in the robot navigation process can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of robot navigation, and in particular to a method for robot target point range navigation based on a grid map. Background Art

[0002] In the field of robot navigation, target point selection and path planning are two crucial links. Traditional robot navigation systems often rely on preset maps and target points, but in practical applications, due to the complexity and uncertainty of the environment, this method of relying on preset information often has many limitations.

[0003] Reference Figure 1 In the prior art, when a robot needs to search for a new target point, its selection often has a certain degree of randomness. This randomness may result in that an effective path may not be planned from the starting point to the new target point. This is because the new target point may be located behind an obstacle or in an inaccessible area, making it impossible for the robot to reach it.

[0004] Reference Figure 2 , even if a path from the starting point to the new target point can be planned, the new target point searched by the existing technology may not be the most reasonable. Reasonableness involves multiple dimensions, such as path length, energy consumption, time, etc. If the selection of the new target point is too random or does not consider these dimensions, the navigation efficiency and effect of the robot will be greatly reduced. Summary of the invention

[0005] The purpose of the present invention is to propose a method for robot target point range navigation based on a grid map, and the technical solution can improve the rationality of the target point during the robot navigation process.

[0006] To achieve the above objectives, in a first aspect, an embodiment of the present disclosure provides a method for robot target point range navigation based on a grid map, comprising: Construct a grid map and mark the grid based on whether there are obstacles. Through the path planning algorithm, find the shortest path from the starting point to the end point on the grid map; Start from the starting point to perform potential field expansion calculation, expand the potential field range on the grid map, and determine the grids that the robot can reach. Each grid has a potential field value, which represents the distance or cost from the grid to the starting point. When the target point is unreachable, search for a new reachable point near the target point as the new target point; After searching all candidate points, sort the candidate points according to the application scenario; Take the first candidate point from the sorted candidate point list as the current candidate point; Use the path planning algorithm to obtain the path from the starting point to the current candidate point.

[0007] Beneficial effects of the basic scheme: By constructing a grid map and marking obstacles on the grid, this method can flexibly adapt to various complex indoor or outdoor environments. The resolution of the grid map can be adjusted according to actual needs to better reflect the details of the environment.

[0008] The path planning algorithm is used to find the shortest path from the starting point to the end point on the grid map, ensuring the efficiency and accuracy of navigation. The potential field expansion calculation is performed from the starting point to determine the grid range that the robot can reach, and a potential field value is assigned to each grid. Not only the distance factor is considered, but also other cost factors (such as energy consumption, time, etc.) are introduced according to actual needs, thereby improving the flexibility and adaptability of navigation, while ensuring the rationality of the target point.

[0009] When the target point is unreachable due to obstacles or other reasons, this method can search for a new reachable point near the target point as the new target point, effectively avoiding the navigation failure problem caused by the unreachable target point and improving the robustness of navigation.

[0010] After searching for all candidate points, the candidate points are sorted according to the application scenario, and can be selected according to actual needs (such as safety, efficiency, etc.), thereby further optimizing the selection of navigation paths. When the target point or environment changes, the path planning can be quickly updated and the path from the starting point to the current candidate point can be recalculated, ensuring the real-time and accuracy of navigation.

[0011] This technical solution is based on the grid map and is easy to maintain. At the same time, the update and expansion of the grid map is also relatively easy, which is convenient for functional expansion and optimization according to actual needs.

[0012] As an implementable preferred solution, a grid map is constructed and marked according to whether there are obstacles in the grid, including the following: Environmental information is obtained through sensors, which include laser radar and cameras; the size and resolution of the grid map are set, and a two-dimensional array is created to store the information of the grid map; the three-dimensional point cloud data generated by the laser radar is projected onto a two-dimensional plane to obtain two-dimensional point cloud data; the two-dimensional point cloud data is traversed to map each point to the corresponding grid of the grid map; edge detection and feature extraction are performed on the two-dimensional image data generated by the camera to obtain the outline of obstacles in the environment; the obstacle outline is mapped to the corresponding grid of the grid map, and the grid containing the obstacle outline is marked, and the data of the laser radar and the camera are fused.

[0013] As an implementable preferred solution, a path planning algorithm is used to find the shortest path from the starting point to the end point on the grid map, including the following: Create a priority queue to store the grid nodes to be processed; create a two-dimensional array to store the distance values ​​and parent node information of the grid nodes; add the starting grid node to the priority queue and set its distance value to 0.

[0014] As an implementable preferred solution, a path planning algorithm is used to find a shortest path from the starting point to the end point on the grid map, which also includes the following: Take the grid node with the smallest distance value from the priority queue as the current node; traverse the neighboring grid nodes of the current node; for each neighboring grid node, if its distance value is greater than the distance value of the current node plus the cost from the current node to the neighboring grid node, update the distance value of the neighboring grid node to the distance value of the current node plus the cost, and add it to the priority queue, and record the parent node information of the neighboring grid node as the current node; after the loop ends, the shortest path and distance value from the starting point to all reachable grid nodes are obtained.

[0015] As an implementable preferred solution, the potential field expansion calculation is performed from the starting point, and the potential field range is expanded on the grid map, including the following contents: Initialize the potential field map and create a two-dimensional array to store the potential field values ​​of the grid map; set the potential field value of the starting point to 0; create an empty open list to store the grid to be expanded; add the starting grid node to the open list.

[0016] As an implementable preferred solution, the potential field expansion calculation is performed from the starting point, and the potential field range is expanded on the grid map, which also includes the following contents: Take a grid node from the open list as the current node; traverse the neighboring grid nodes of the current node; For each neighbor grid node, if its potential value is greater than the potential value of the current grid node plus the cost from the current grid to the neighbor grid node, then update the potential value of the neighbor grid node to the potential value of the current grid node plus the cost, and add the neighbor grid node to the open list; After the loop is completed, an expanded potential field graph is obtained, in which each grid has a potential field value, which represents the distance or cost from the grid to the starting point.

[0017] As an implementable preferred solution, when the target point is unreachable, a new reachable point is searched near the target point as the new target point, including the following contents: Determine the search range, which can be circular, rectangular, or annular; traverse the grids within the search range and determine whether the grids meet the following conditions: has been expanded by the potential field; is within a given range; the grid cost value is less than the cost value threshold; For grids that meet the conditions, they are recorded as candidate points, and their grid cost value, potential field value and distance to the end point are recorded.

[0018] As an implementable preferred solution, the cost value threshold calculation formula is as follows: ref_cost = 253 * std::exp(-1.0 * cost_scaling_factor_ * obstacle_distance) Among them, ref_cost represents the threshold; obstacle_distance is the distance that needs to be maintained from the obstacle; cost_scaling_factor_ is the expansion coefficient of the expansion layer.

[0019] As an implementable preferred solution, the first candidate point is taken from the sorted candidate point list as the current candidate point, including the following contents: Use the path planning algorithm to try to obtain the path from the starting point to the current candidate point; If the path is successfully obtained, the path planning attempt process ends and the current candidate point is used as the new target point; if the path is failed, the next candidate point is taken from the candidate point list as the current candidate point, and the path planning attempt process is repeated until the path is successfully obtained or the candidate point list is empty.

[0020] As an implementable preferred solution, a path planning algorithm is used to obtain a path from the starting point to the current candidate point, including the following: During the navigation process, the robot needs to perceive environmental information in real time and adjust the path planning algorithm and parameters based on the environmental information. When encountering sudden obstacles, the robot re-plans the path and recalculates the potential field to find a new feasible path. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the defects of the prior art.

[0022] Figure 2 This is a schematic diagram of the second defect of the prior art.

[0023] Figure 3 A schematic diagram of a method for robot target point range navigation based on a grid map.

[0024] Figure 4 This is a diagram of the search range shape.

[0025] Figure 5 Schematic diagram of candidate points after the existing technology potential field is expanded.

[0026] Figure 6 and Figure 7Schematic diagram of candidate points after potential field expansion in this embodiment.

[0027] Figure 8 Schematic diagram of the local robot navigating to the preset waiting point.

[0028] Fig. 9 FIG. 4 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the technical solution and advantages of the present application clearer, the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings. It will be understood that the specific embodiments described herein are only partial embodiments of the present invention, which are only used to explain the present application, rather than to limit the present application. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated, and they can be combined with each other to achieve better technical effects. The same reference numerals appearing in the drawings of the following embodiments represent the same features or components, which can be applied to different embodiments.

[0030] In addition, unless otherwise defined, the technical terms or scientific terms used in the description of the present invention should have the common meanings understood by those skilled in the art in the art to which the present invention belongs.

[0031] The present invention is further described in detail below in conjunction with the accompanying drawings: Reference numerals: electronic device 500 , processor 501 , communication interface 502 , memory 503 , bus 504 .

[0032] Reference Figure 3 , a method for robot target point range navigation based on grid map, includes the following steps.

[0033] Step S100, constructing a grid map, in which each grid has a unique identifier and is marked according to whether there is an obstacle in the grid, including: Step S101, constructing a grid map of the robot's working environment. The grid map can be constructed by obtaining environmental information through sensors such as laser radar and camera. In this embodiment, a laser radar with high precision and high scanning frequency, such as Velodyne VLP-16, is selected to provide three-dimensional point cloud data of the environment; a camera with high resolution and wide-angle field of view, such as Intel RealSense D435, is selected to provide two-dimensional image data of the environment.

[0034] Step S102, using image processing, data fusion and other technologies to convert environmental information into a grid map, includes: Step S102-1, set the size and resolution of the grid map, create a two-dimensional array, and store the information of the grid map. Each element of the array corresponds to a grid, and the initial value is set to "unknown".

[0035] Step S102-2, project the three-dimensional point cloud data generated by the laser radar onto a two-dimensional plane to obtain two-dimensional point cloud data. Traverse the two-dimensional point cloud data and map each point to the corresponding grid of the grid map. If a grid contains point cloud data, it is marked as an "obstacle".

[0036] Step S102-3, edge detection and feature extraction are performed on the two-dimensional image data generated by the camera to obtain the outline of obstacles in the environment. The obstacle outline is mapped to the corresponding grid of the grid map, and if a grid contains the obstacle outline, it is marked as an "obstacle".

[0037] Step S102-4, the data of the laser radar and the camera are integrated to obtain a more complete grid map. If a grid is marked as an "obstacle" in both sensors, its "obstacle" mark is maintained; if a grid is marked as a "non-obstacle" in both sensors, it is marked as "passable"; if the marks of a grid in the two sensors are inconsistent, it is marked according to the priority.

[0038] Step S102-5: Smoothing the grid map to remove isolated points and burrs caused by sensor noise and error. Dilation and erosion are performed on the grid map to more accurately represent the shape and size of the obstacle.

[0039] Step S200, after the grid map is constructed, a suitable path planning algorithm is selected, and the Dijkstra algorithm or the A* algorithm is selected as the path planning algorithm. The above algorithms are all path planning algorithms based on graph search, and a shortest path from the starting point to the end point is found on the grid map.

[0040] In this embodiment, the Dijkstra algorithm is selected as the path planning algorithm, and the algorithm execution steps include the following: Create a priority queue to store the grid nodes to be processed. The priority queue is sorted according to the distance value of the grid nodes. The smaller the distance value, the higher the priority.

[0041] Create a two-dimensional array to store the distance value and parent node information of the grid node. Each element of the array corresponds to a grid node, and the initial value is set to infinity (indicating unreachable).

[0042] Add the starting grid node to the priority queue and set its distance value to 0 (indicating that the starting point is reachable).

[0043] Loop through the following steps until the priority queue is empty: Take the grid node with the smallest distance value from the priority queue as the current node; traverse the neighboring grid nodes of the current node (i.e., the grid nodes adjacent to the current grid node); for each neighboring grid node, if its distance value is greater than the distance value of the current node plus the cost from the current node to the neighboring grid node (usually a constant, representing the cost of moving one step), then update the distance value of the neighboring grid node to the distance value of the current node plus the cost, and add it to the priority queue (if it is not in the priority queue). At the same time, record the parent node information of the neighboring grid node as the current node.

[0044] After the loop ends, the shortest path and distance values ​​from the starting point to all reachable grid nodes are obtained.

[0045] Step S300, before searching for a new target point, a potential field expansion calculation is performed starting from the starting point. Potential field expansion calculation is a preprocessing process based on the path planning algorithm, which determines the grids that the robot can reach by expanding a potential field range on the grid map. The result of the potential field expansion calculation is a potential field map, in which each grid has a potential field value, which represents the distance or cost from the grid to the starting point.

[0046] The specific steps of potential field expansion calculation are as follows: Step S301, initialize the potential field map, create a two-dimensional array, and store the potential field values ​​of the grid map. Each element of the array corresponds to a grid, and the initial value is set to infinity (indicating unreachable).

[0047] Step S302, setting the potential field value of the starting point to 0 (indicating that the starting point is reachable).

[0048] Step S303: create an empty open list for storing the grids to be expanded.

[0049] Step S304, adding the starting grid node to the open list.

[0050] Step S305, the potential field is expanded in a loop until the open list is empty, including: Step S305-1, taking a grid node from the open list as the current node.

[0051] Step S305 - 2 , traversing neighboring grid nodes of the current node (ie, grid nodes adjacent to the current grid node).

[0052] Step S305-3, for each neighbor grid node, if its potential field value is greater than the potential field value of the current grid node plus the cost from the current grid to the neighbor grid node (usually a constant, representing the cost of moving one step), then the potential field value of the neighbor grid node is updated to the potential field value of the current grid node plus the cost, and the neighbor grid node is added to the open list (if it is not in the open list).

[0053] Step S305-4, after the loop is completed, an expanded potential field graph is obtained, in which each grid has a potential field value, which represents the distance or cost from the grid to the starting point.

[0054] Step S400: When the target point is unreachable, it is necessary to search for a new reachable point near the target point as the new target point. This includes: Step S401, determine the search range, refer to Figure 4 The search range of the new target point can be a circle, rectangle or ring, etc. The parameters limiting the range include: Circle: radius, distance to be maintained from obstacles; Rectangle: The distances before, after, left, and right of the end point as the reference point, and the distances to be maintained from obstacles; Ring shape: inner circle radius, outer circle radius, and the distance to be maintained from obstacles.

[0055] The specific shape can be selected according to the actual application scenario, and the search range can be determined according to the position and shape parameters of the target point (such as radius, front, back, left, and right distances, etc.).

[0056] Step S402, traverse the grids within the search range, and for each grid within the search range, determine whether it meets the following conditions: has been expanded by the potential field (i.e., its potential field value is not infinite); is within the given range (i.e. its position is within the search range); The grid cost value is less than ref_cost (ref_cost is a cost value threshold calculated based on the obstacle distance and expansion coefficient, used to limit the location of candidate points).

[0057] The calculation method of ref_cost is as follows: ref_cost = 253 * std::exp(-1.0 * cost_scaling_factor_ * obstacle_distance); Among them, obstacle_distance is the distance that needs to be maintained from the obstacle; cost_scaling_factor_ is the expansion coefficient of the expansion layer, which is adjusted according to the actual situation.

[0058] Step S403: For the grids that meet the conditions, record them as candidate points, and record their grid cost value, potential field value and distance from the end point.

[0059] Step S500, sorting candidate points, includes: Step S501: After searching all candidate points, the candidate points need to be sorted according to different application scenarios. The sorting order will determine the order of trying to obtain paths from the potential field.

[0060] Step S502, select a suitable sorting method according to the application scenario. The sorting method may be based on the grid cost value from small to large, from large to small, based on the distance from the end point from far to near, from near to far, or based on the potential field value from small to large, from large to small, etc.

[0061] Step S503: sorting the candidate points according to the selected sorting method to obtain a sorted candidate point list.

[0062] Step S600, performing path planning, includes: Step S601: Take the first candidate point from the sorted candidate point list as the current candidate point, and use a path planning algorithm (such as Dijkstra algorithm or A* algorithm) to try to obtain a path from the starting point to the current candidate point.

[0063] Step S602: If the path is successfully obtained, the path planning attempt process ends and the current candidate point is used as the new target point.

[0064] Step S603: If the path acquisition fails, the next candidate point is taken from the candidate point list as the current candidate point, and the path planning attempt process is repeated until the path acquisition succeeds or the candidate point list is empty.

[0065] Step S700, perform navigation. After obtaining the new target point, the robot will navigate according to the new target point. During the navigation process, the robot needs to perceive the environmental information in real time and adjust the path planning algorithm and parameters according to the environmental information to ensure that the robot can reach the new target point safely and accurately. When encountering sudden obstacles, the robot needs to re-plan the path and recalculate the potential field to find a new feasible path.

[0066] Reference Figure 5 ,The blue area is the area that the existing technology expands to. The existing technology may search for a new target point in the red circle. Because the red circle is not expanded to, the path planning from the starting point to the target point finally planned fails.

[0067] Reference Figure 6 and Figure 7, this technical solution can set the new target point to the red circle, as shown in the figure below, the red box contains all the candidate points.

[0068] Reference Figure 8 , where the red area is the potential field range that has been expanded by this technical solution, the red arrow is the target point, and the green line is the point that only the expanded area can reach by the robot.

[0069] The disclosed embodiment also provides a system for robot target point range navigation based on a grid map, and the system utilizes the above-mentioned method for robot target point range navigation based on a grid map.

[0070] The embodiment of the present disclosure further provides a storage medium, in which a computer program is stored. When the computer program is executed by a processor, all steps of the above-mentioned method for robot target point range navigation based on a grid map can be implemented.

[0071] A person of ordinary skill in the art can understand that all or part of the process of implementing a method for robot target point range navigation based on a grid map can be completed by instructing related hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the process of each embodiment of a method for robot target point range navigation based on a grid map. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0072] Reference Fig. 9, the electronic device 500 includes: at least one processor 501, at least one communication interface 502, at least one memory 503 and at least one bus 504. The bus 504 is used to realize the connection and communication between these components, the communication interface 502 is used to communicate signaling or data with other node devices, and the memory 503 stores machine-readable instructions executable by the processor 501. When the electronic device 500 is running, the processor 501 communicates with the memory 503 through the bus 504, and when the machine-readable instructions are called by the processor 501, the steps of the robot avoidance method based on the grid map are executed.

[0073] The above contents are only embodiments of the present invention. The common sense such as the known specific structures and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for the ordinary technicians in the relevant field to implement this application. It should be pointed out that for the technicians in this field, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to explain the content of the claims.

Claims

1. A method for robot target point range navigation based on a grid map, characterized in that: include: Construct a grid map and mark the grid based on whether there are obstacles. Through the path planning algorithm, find the shortest path from the starting point to the end point on the grid map; Start from the starting point to perform potential field expansion calculation, expand the potential field range on the grid map, and determine the grids that the robot can reach. Each grid has a potential field value, which represents the distance or cost from the grid to the starting point. When the target point is unreachable, search for a new reachable point near the target point as the new target point; After searching all candidate points, sort the candidate points according to the application scenario; Take the first candidate point from the sorted candidate point list as the current candidate point; Use the path planning algorithm to obtain the path from the starting point to the current candidate point.

2. The method for robot target point range navigation based on a grid map according to claim 1, characterized in that: Build a grid map and mark the grid based on whether there are obstacles, including the following: Environmental information is obtained through sensors, which include laser radar and cameras; the size and resolution of the grid map are set, and a two-dimensional array is created to store the information of the grid map; the three-dimensional point cloud data generated by the laser radar is projected onto a two-dimensional plane to obtain two-dimensional point cloud data; the two-dimensional point cloud data is traversed to map each point to the corresponding grid of the grid map; edge detection and feature extraction are performed on the two-dimensional image data generated by the camera to obtain the outline of obstacles in the environment; the obstacle outline is mapped to the corresponding grid of the grid map, and the grid containing the obstacle outline is marked, and the data of the laser radar and the camera are fused.

3. The method for robot target point range navigation based on grid map according to claim 1, characterized in that: Through the path planning algorithm, a shortest path from the starting point to the end point is found on the grid map, including the following: Create a priority queue to store the grid nodes to be processed; Create a two-dimensional array to store the distance values ​​and parent node information of the grid nodes; add the starting grid node to the priority queue and set its distance value to 0.

4. The method for robot target point range navigation based on grid map according to claim 3, characterized in that: Through the path planning algorithm, a shortest path from the starting point to the end point is found on the grid map, which also includes the following: Take the grid node with the smallest distance value from the priority queue as the current node; traverse the neighboring grid nodes of the current node; for each neighboring grid node, if its distance value is greater than the distance value of the current node plus the cost from the current node to the neighboring grid node, update the distance value of the neighboring grid node to the distance value of the current node plus the cost, and add it to the priority queue, and record the parent node information of the neighboring grid node as the current node; after the loop ends, the shortest path and distance value from the starting point to all reachable grid nodes are obtained.

5. The method for robot target point range navigation based on grid map according to claim 4, characterized in that: The potential field expansion calculation is performed from the starting point, and the potential field range is expanded on the grid map, including the following: Initialize the potential field map and create a two-dimensional array to store the potential field values ​​of the grid map; set the potential field value of the starting point to 0; create an empty open list to store the grid to be expanded; add the starting grid node to the open list.

6. The method for robot target point range navigation based on grid map according to claim 5, characterized in that: The potential field expansion calculation starts from the starting point, and the potential field range is expanded on the grid map, including the following: Take a grid node from the open list as the current node; traverse the neighboring grid nodes of the current node; For each neighbor grid node, if its potential value is greater than the potential value of the current grid node plus the cost from the current grid to the neighbor grid node, then update the potential value of the neighbor grid node to the potential value of the current grid node plus the cost, and add the neighbor grid node to the open list; After the loop is completed, an expanded potential field graph is obtained, in which each grid has a potential field value, which represents the distance or cost from the grid to the starting point.

7. A method for robot target point range navigation based on a grid map according to claim 6, characterized in that: When the target point is unreachable, search for a new reachable point near the target point as the new target point, including the following: Determine the search range, which can be circular, rectangular, or annular; traverse the grids within the search range and determine whether the grids meet the following conditions: has been expanded by the potential field; is within a given range; the grid cost value is less than the cost value threshold; For grids that meet the conditions, they are recorded as candidate points, and their grid cost value, potential field value and distance to the end point are recorded.

8. The method for robot target point range navigation based on grid map according to claim 1, characterized in that: The calculation formula of the cost value threshold is as follows: ref_cost = 253 * std::exp(-1.0 * cost_scaling_factor_ * obstacle_distance) Among them, ref_cost represents the cost value threshold; obstacle_distance is the distance that needs to be maintained from the obstacle; cost_scaling_factor_ is the expansion coefficient of the expansion layer.

9. The method for robot target point range navigation based on grid map according to claim 1, characterized in that: Take the first candidate point from the sorted candidate point list as the current candidate point, including the following: Use the path planning algorithm to try to obtain the path from the starting point to the current candidate point; If the path is successfully obtained, the path planning attempt process ends and the current candidate point is used as the new target point; If the path acquisition fails, the next candidate point is taken from the candidate point list as the current candidate point, and the path planning attempt process is repeated until the path acquisition succeeds or the candidate point list is empty.

10. The method for robot target point range navigation based on grid map according to claim 1, characterized in that: Use the path planning algorithm to obtain the path from the starting point to the current candidate point, including the following: During the navigation process, the robot needs to perceive environmental information in real time and adjust the path planning algorithm and parameters based on the environmental information. When encountering sudden obstacles, the robot re-plans the path and recalculates the potential field to find a new feasible path.

Images