A path planning method for mobile battery swapping robots

Abstract

The present invention relates to the field of image path planning technology, and more specifically, the present invention relates to a path planning method for a mobile battery-swapping robot, including: constructing a coordinate system based on an operation site map to obtain the positions and areas of various obstacles in the operation site; determining the path generation step length; constructing the starting point and end point of the path of the mobile battery-swapping robot and the common circumscribed rectangle of all obstacles between them; determining the degree of offset of the obstacles in the path; using the path generation step length as the step length of the RRT* algorithm, randomly sampling through the RRT* algorithm, and determining the final parent node of the new node; and randomly reconnecting through the RRT* algorithm to complete the path planning for the mobile battery-swapping robot. The parent node in the pre-selected path with the minimum moving cost is selected as the final parent node of the new node. The path generated on this basis fully considers the mobility of the mobile battery-swapping robot and reduces the impact on the vehicle energy replenishment efficiency caused by unreasonable paths.

Description

Technical Field

[0001] The present invention relates to the field of image path planning technology, and more specifically, to a path planning method for a mobile battery-swapping robot. Background Art

[0002] In the existing energy replenishment process of battery-swap new energy vehicles, when a new energy vehicle enters the operation site, the mobile battery-swap robot compares and identifies the vehicle information with the cruise robot to obtain the vehicle information package. Based on the obtained vehicle information, the mobile battery-swap robot is driven to carry the battery pack disassembly platform of the corresponding vehicle model to the vehicle location to disassemble the battery pack. At the same time, another mobile battery-swap robot is driven to carry the energy replenishment battery of the corresponding vehicle to follow the mobile battery-swap robot equipped with the disassembly platform to the location of the battery-swap vehicle. When the original energy battery is disassembled, the replacement battery is sent to the bottom of the vehicle for energy replenishment. In this process, reasonable path planning is required for the mobile battery-swap robot to achieve efficient energy replenishment.

[0003] The patent document with announcement number CN116859909B discloses a path planning method for an intelligent robot, which relates to the field of path planning technology. An electronic map of an activity area is obtained, and several immovable objects are selected as landmarks in the activity area to plan a preselected path from a starting point to a destination. Then, the indicating landmarks located around the preselected path are determined as node landmarks. The position of the robot is located. If the positioning coordinates show that the robot has deviated from the preselected path, the robot is guided to move to the preselected path. After identifying the road conditions of the path to be selected, a movement coefficient Yxs is generated, and each path to be selected is sorted. The obtained simulation analysis results generate a cost coefficient Cxs, and the path to be selected is screened, and the path is planned again until the robot reaches the destination.

[0004] The above patent document adopts the RRT (Rapidly-exploring Random Trees) sampling-based motion planning algorithm. Compared with the RRT algorithm, the RRT* algorithm has stronger path optimization capabilities. By introducing random reconnection and local optimization steps, the path quality is gradually improved, and a shorter and smoother path can be found, and gradually converge to the optimal solution during the planning process. However, when there are obstacles in the moving path of the mobile battery swap robot, it will be difficult to move, so that the robot needs more moving time to move along the path with a shorter generation time, which affects the energy supply efficiency. Summary of the invention

[0005] In order to solve the problem that when there are obstacles in the moving path of the mobile battery-swapping robot, it will be difficult to move, so that the robot needs more moving time to move along a path with a shorter generation time, which affects the energy replenishment efficiency, the present invention proposes a path planning method for the mobile battery-swapping robot, which includes:

[0006] Construct a coordinate system based on the operation site map to obtain the position and area of ​​each obstacle in the operation site; determine the path generation step length, which is positively correlated with the basic step length of the mobile battery swap robot, and negatively correlated with the aspect ratio of the mobile battery swap robot, the proportion of the area occupied by the obstacle, and the relative size of the standard deviation of the obstacle position; construct the starting point and end point of the path of the mobile battery swap robot and the common circumscribed rectangle of all obstacles between them, determine the offset degree of the obstacles on the path, the relative size of the offset degree and the area of ​​the common circumscribed rectangle, the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and end point of the path of the mobile battery swap robot, and the common circumscribed rectangle. The ratio of the areas of the connected rectangles is positively correlated; the path generation step length is taken as the step length of the RRT* algorithm, and random sampling is performed through the RRT* algorithm to continuously obtain new nodes of the RRT tree of the RRT* algorithm, and each neighboring node of the new node is used as the parent node. The parent node on the pre-selected path with the smallest moving cost from the starting point to the new node is used as the final parent node of the new node. The moving cost is positively correlated with the relative average length of each sub-path in the pre-selected path, the standard deviation of the similarity between each sub-path and the starting point to the end point, and the degree of offset, and is negatively correlated with the relative length of the pre-selected path; random reconnection is performed through the RRT* algorithm to complete the path planning for the mobile battery exchange robot.

[0007] The beneficial effects are as follows: by building a coordinate system based on the operation site map and accurately obtaining the position and area of ​​obstacles, the robot can effectively avoid collisions with fixed or moving obstacles; by reasonably setting the path generation step size, the path planning is neither too conservative, resulting in inefficiency, nor too aggressive, resulting in increased collision risk; by calculating the offset degree of obstacles, the path planning is ensured to take into account the actual distribution of obstacles and ensure the navigation safety of the robot in complex environments; by using the RRT* algorithm for random sampling and reconnection, the path planning is highly flexible and robust; by minimizing the movement cost from the starting point to the new node, the economy and effectiveness of the path are guaranteed, and the energy replenishment efficiency is improved.

[0008] Further, constructing a coordinate system according to the operation site map includes: taking any corner of the operation site map as the coordinate origin of the coordinate system, and extending along the boundary of the operation site map as the horizontal and vertical coordinates of the coordinate system, respectively, and the horizontal and vertical coordinates increase successively.

[0009] Furthermore, the path generation step size satisfies the following relationship:

[0010] ; In the formula, Generate step lengths for the path, is the basic step length of the mobile battery swapping robot, and are the length and width of the mobile battery-swapping robot, is the ratio of the area occupied by obstacles in the operation site, is the average area occupied by each obstacle in the operation site, and are the length and width of the operation site, is the relative size of the standard deviation of the obstacle locations within the operation site, is the standard deviation of the ordinate of the center point of each obstacle in the operation site, is the standard deviation of the horizontal coordinates of the center points of each obstacle in the operation site, is a natural exponential function.

[0011] The beneficial effect is that by comprehensively considering the proportion of obstacles and the standard deviation of their positions in the operating site to adjust the step size of the path generation of the mobile battery swapping robot, the accuracy of path planning and the overall efficiency of the energy replenishment process are improved, which helps the mobile battery swapping robot to better adapt to environmental changes in actual applications and improve the quality of completion of energy replenishment tasks.

[0012] Furthermore, the offset degree satisfies the following relationship:

[0013] ; In the formula, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is the relative size of the common circumscribed rectangle, is the area of ​​the common circumscribed rectangle, and are the length and width of the operation site, is the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and the end point of the path of the mobile battery swapping robot. is a natural exponential function.

[0014] The beneficial effects are: calculating the impact of obstacles through relative area can more accurately reflect the actual impact of obstacles on the path; taking into account the overall circumscribed rectangular area of ​​the obstacle, the path planning within the operation site can better avoid obstacles and improve space utilization efficiency; by comprehensively considering the relative size and time factors of the obstacle, it can better help plan the path and avoid possible collisions and interference, so that the mobile battery exchange robot can complete the energy supply task more smoothly.

[0015] Furthermore, the movement cost satisfies the following relationship:

[0016] ; In the formula, For the The movement cost of the pre-selected paths, is the relative average length of each sub-path in the pre-selected path, is the average length of each sub-path in the pre-selected path, Generate step lengths for the path, is the relative length of the preselected path, is the Euclidean distance between the starting point and the new node of the path of the mobile battery swapping robot, is the length of the preselected path, is the standard deviation of the similarity between the starting point and the end point of each sub-path in the pre-selected path and the path of the mobile battery swapping robot, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is a natural exponential function.

[0017] The beneficial effects are: by comprehensively considering the length, relative position, similarity standard deviation and obstacle impact of each sub-path, the actual cost of the path can be evaluated more comprehensively, which helps to select the best path under various conditions; by quantifying and integrating multiple factors such as the length, similarity and obstacle impact of the path, the uncertainty in path planning can be reduced and the accuracy of path selection can be improved.

[0018] Furthermore, the method for obtaining the similarity is: construct a unit vector from the starting point of the path of the mobile battery exchange robot toward the end point, take the unit vector as the target vector, construct a unit vector from the parent node to the child node in each sub-path in the pre-selected path, and obtain the cosine similarity between the unit vector and the target vector as the similarity.

[0019] The beneficial effect is that by constructing the target vector and calculating the cosine similarity, it not only simplifies the path selection process, but also provides an efficient and intelligent path planning solution, thereby improving the operating efficiency and overall performance of the mobile battery swap robot.

[0020] Furthermore, the random reconnection by the RRT* algorithm includes: comparing the path cost from the new node to the nearby node with the original path cost, and if the new path cost is lower, taking the new node as the parent node of the nearby node.

[0021] Furthermore, in order to complete the path planning for the mobile battery-swapping robot, the method includes: in response to the distance between the new node and the end point of the path of the mobile battery-swapping robot being less than the path generation step length, using the preselected path of the node at this time as the final moving path of the mobile battery-swapping robot to complete the path planning for the mobile battery-swapping robot.

[0022] The present invention has the following beneficial effects:

[0023] The path generation step length is calculated according to the existing operation site map and the inherent properties of the mobile battery-swap robot, so as to obtain a step length that is more suitable for the operation site scene and the characteristics of the robot; the obstacle offset degree of the path is calculated according to the obstacle distribution at the starting point and the end point of the path and the path generation step length, so as to reduce the judgment of the movement cost of the pre-selected path by obstacles; at the same time, the parent node in the pre-selected path with the smallest movement cost is selected as the final parent node of the new node. The path generated by the present invention on this basis fully considers the mobility of the mobile battery-swap robot, reduces the impact on the vehicle energy supply efficiency caused by the unreasonable movement path, and improves the energy supply efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 It is a step flow chart of a path planning method for a mobile battery-swapping robot according to an embodiment of the present invention.

[0026] Figure 2 It is a first schematic diagram of the common circumscribed rectangle of the starting point and end point of the path of a mobile battery-swapping robot and all obstacles therebetween in a path planning method for a mobile battery-swapping robot according to an embodiment of the present invention.

[0027] Figure 3 This is a second schematic diagram of the common circumscribed rectangle of the starting point and end point of the path of a mobile battery-swapping robot and all obstacles therebetween in a path planning method for a mobile battery-swapping robot in an embodiment of the present invention.

[0028] Figure 4 It is a schematic diagram of the directions of the target vector and the sub-path unit vectors of a path planning method for a mobile battery-swapping robot according to an embodiment of the present invention.

[0029] Figure 2 , 3 , 4 in, is the starting point of the path of the mobile battery swapping robot. It is the end point of the path of the mobile battery swapping robot. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0032] See also Figure 1 , which shows a flow chart of a path planning method for a mobile battery-swapping robot provided by an embodiment of the present invention, the method comprising the following steps:

[0033] S1: Construct a coordinate system based on the operation site map to obtain the location and area of ​​each obstacle in the operation site.

[0034] Specifically, the step of constructing a coordinate system according to the operation site map includes:

[0035] Any corner of the operation site map is used as the origin of the coordinate system, and the horizontal and vertical coordinates of the coordinate system are extended along the boundary of the operation site map, and the horizontal and vertical coordinates increase successively.

[0036] S2: Determine the path generation step size.

[0037] It should be noted that since the RRT* algorithm continuously generates a moving path based on the starting node with a specified step size, the step size has a certain impact on the path planning of a specific mobile robot in different scenarios. For scenes with a large moving range, using a small step size will produce a more delicate moving path, but it will increase the path generation time to a certain extent. For scenes with a small moving range, if a large step size is used, an overly rough moving path will be generated, affecting the efficiency of battery swapping. Therefore, the path generation step size is obtained based on the existing operating site map and the inherent properties of the mobile battery swapping robot.

[0038] Specifically, the path generation step size satisfies the following relationship:

[0039] ;

[0040] In the formula, Generate step lengths for the path, is the basic step length of the mobile battery swapping robot, and are the length and width of the mobile battery-swapping robot, is the ratio of the area occupied by obstacles in the operation site, is the average area occupied by each obstacle in the operation site, and are the length and width of the operation site, is the relative size of the standard deviation of the obstacle locations within the operation site, is the standard deviation of the ordinate of the center point of each obstacle in the operation site, is the standard deviation of the horizontal coordinates of the center points of each obstacle in the operation site, is a natural exponential function.

[0041] in, The ratio of the area occupied by obstacles in the operation site. The larger the value, the larger the area occupied by obstacles in the exchange station, and the narrower the passable space in the exchange station may be. A smaller step size should be used to explore the passable space in the operation site more carefully. The smaller the value, the smaller the area occupied by obstacles in the exchange station, and the wider the passable space in the exchange station may be. Since there is no need to explore too carefully in the open space, a larger step size should be used to improve the efficiency of path generation. The aspect ratio of the mobile battery swapping robot. The larger the value, the more restricted the robot is when turning and passing through narrow areas. Using a smaller step size can improve the precision of the path, helping the robot to adjust its direction more flexibly in complex environments and avoid collisions. The smaller the value, the more flexible the robot is in space, making it easier to turn and avoid obstacles. Using a larger step size can improve the efficiency of the algorithm. is the relative size of the standard deviation of the obstacle position in the operation site. The larger the value, the sparser the distribution of obstacles in the operation site. A larger step size should be used to reduce the number of node expansions to accelerate path generation. The smaller the value, the denser the distribution of obstacles in the operation site. A step size that is too large should not be used to avoid collisions. In summary, through For basic step length Adjust the path generation step size, and use As the basic step length, implementers can determine the basic step length based on actual conditions.

[0042] S3: Construct the common circumscribed rectangle of the starting point and end point of the path of the mobile battery swapping robot and all obstacles in between.

[0043] See also Figure 2 and Figure 3 , which are respectively the first schematic diagram and the second schematic diagram of the starting point and the end point of the path of the mobile battery-swapping robot and the common circumscribed rectangle of all obstacles therebetween.

[0044] S4: Determine the degree of deviation of obstacles in the path.

[0045] It should be noted that since there may be obstacles between the starting point and the end point of the path, which has a certain impact on whether the generated path is suitable for the movement of the mobile robot, the obstacle offset degree of the path is calculated according to the obstacle distribution between the starting point and the end point of the path and the path generation step size.

[0046] Specifically, the offset degree satisfies the following relationship:

[0047] ;

[0048] In the formula, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is the relative size of the common circumscribed rectangle, is the area of ​​the common circumscribed rectangle, and are the length and width of the operation site, is the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and the end point of the path of the mobile battery swapping robot. is a natural exponential function.

[0049] in, is the relative size of the common circumscribed rectangle. The larger the value, the larger the offset required when generating the path, so as to bypass the obstacles between the starting point and the end point of the path, thereby generating a path from the starting point to the end point of the path. Therefore, the larger the value, the greater the degree of obstacle offset of the path. The smaller the value, the smaller the offset required when generating the path, and there is no need to generate a route with a large detour. Therefore, the smaller the value, the smaller the degree of obstacle offset of the path. It is the ratio of the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and the end point of the path of the mobile battery-swapping robot and the area of ​​the common circumscribed rectangle. The larger the value, the closer the obstacles between the starting point and the end point of the path are to the distance between the starting point and the end point of the path. The path needs to be offset to a greater extent to avoid these obstacles. The greater the degree of obstacle offset of the path. The smaller the value, the farther the obstacles between the starting point and the end point of the path are from the starting point to the end point of the path. When generating the path, there is no need to offset the path significantly. The smaller the degree of obstacle offset of the path is. right Make corrections, The bigger it is, The smaller, right The greater the expansion, the greater the degree of deviation of the path obstacles. The more hours, The bigger, The closer it is to 1, the smaller the obstacle deviation of the path is.

[0050] S5: The path generation step length is the step length of the RRT* algorithm, and the final parent node of the new node is determined by random sampling through the RRT* algorithm.

[0051] It should be noted that the existing technology of the RRT* algorithm determines the parent node of the new node based on the path length between the path start point and the new node when the node near the new node is the parent node of the new node, and lacks consideration of the mobility of the mobile battery swapping robot in the generated path, which may produce a path that is not suitable for movement. Therefore, the movement cost of the pre-selected path is calculated based on the difference between the length of the path segment in the pre-selected path and the step length of the path generation, the degree of obstacle offset of the path, and the similarity between the start point and the end point of each sub-path and the path, and the parent node of the new node is selected based on the movement cost.

[0052] The path generation step length is used as the step length of the RRT* algorithm. Through random sampling of the RRT* algorithm, new nodes of the RRT tree of the RRT* algorithm are continuously obtained. Each neighboring node of the new node is used as the parent node, and the parent node on the pre-selected path with the minimum moving cost from the starting point to the new node is used as the final parent node of the new node.

[0053] The implementer can select the range of neighboring nodes according to the actual implementation situation. For example, All nodes within the radius are neighboring nodes.

[0054] Specifically, the movement cost satisfies the following relationship:

[0055] ;

[0056] In the formula, For the The movement cost of the pre-selected paths, is the relative average length of each sub-path in the pre-selected path, is the average length of each sub-path in the pre-selected path, Generate step lengths for the path, is the relative length of the preselected path, is the Euclidean distance between the starting point and the new node of the path of the mobile battery swapping robot, is the length of the preselected path, is the standard deviation of the similarity between the starting point and the end point of each sub-path in the pre-selected path and the path of the mobile battery swapping robot, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is a natural exponential function.

[0057] in, The relative average length of each sub-path in the pre-selected path. The smaller the value, the closer the length of most sub-paths in the pre-selected path is to the path generation step length. , the fewer turning points in the path, the smoother the pre-selected path may be overall, the more suitable the pre-selected path is for the mobile robot to move, and the smaller the moving cost of the pre-selected path. The larger the value, the more likely that most of the sub-paths in the pre-selected path are of the same length as the path generation step length. If the difference is large, there may be more turning points in the path, which means that the pre-selected path is less smooth overall, the pre-selected path is less suitable for the mobile robot to move, and the movement cost of the pre-selected path is greater; is the relative length of the preselected path, The larger the value, the smaller the value, indicating that the length of the pre-selected path is greater than the straight-line distance between the starting point of the path and the new node. , the higher the possibility of a turning point in the path, the less suitable the pre-selected path may be for the mobile battery swap robot to move, and the greater the movement cost of the pre-selected path, The smaller the value, the larger it is, indicating that the length of the pre-selected path is closer to the straight-line distance between the starting point of the path and the new node. , the lower the possibility of a turning point in the path, the more suitable the pre-selected path may be for the movement of the mobile battery swap robot, and the smaller the movement cost of the pre-selected path.

[0058] It should be noted that in order to more accurately determine whether the pre-selected path is suitable for the mobile battery swap robot to move, the standard deviation of the similarity between each sub-path on the pre-selected path and the starting point to the end point is used to compare the Make corrections.

[0059] Specifically, the method for obtaining the similarity is:

[0060] See also Figure 4 , construct a unit vector from the starting point of the path of the mobile battery swapping robot toward the end point, use the unit vector as the target vector, construct a unit vector from the parent node to the child node in each sub-path in the pre-selected path, and obtain the cosine similarity between the unit vector and the target vector as the similarity.

[0061] in, The larger the value is, the more frequent the direction changes of the sub-paths in the pre-selected path are or the greater the difference in the directions of adjacent sub-paths is, the more likely it is that the pre-selected path is not suitable for the movement of the mobile battery-swapping robot, and the greater the movement cost of the pre-selected path. The smaller it is, the less the direction change of the sub-path in the pre-selected path is or the smaller the direction difference of adjacent sub-paths is, the more likely the pre-selected path is to be suitable for the movement of the mobile battery swap robot, and the smaller the movement cost of the pre-selected path is; sometimes there will be obstacles between the end point and the starting point of the path, making It is inevitably a larger value, so z is corrected by the degree of obstacle deviation of the path. When the degree of obstacle deviation of the path is larger, it means The more likely the value of is caused by obstacles rather than the unevenness of the path, the more likely the path is suitable for the movement of the mobile battery swap robot. right Corrected downwards, The larger the The greater the downward correction ability of the path, the smaller the degree of obstacle deviation. The more likely the value of is caused by the non-smoothness of the path, the path may not be suitable for the movement of the mobile robot, so The smaller the The smaller the downward correction ability is, the greater the moving cost of the path is.

[0062] The prior art of the RRT* algorithm selects the parent node of the new node based on the path length of each preselected path, while the present invention refers to the direction of the path segment in each preselected path when selecting the parent node of the new node. This method can plan a path that is more suitable for the mobility of the mobile battery exchange robot.

[0063] S6: Randomly reconnect through the RRT* algorithm to complete the path planning for the mobile battery swapping robot.

[0064] Specifically, the random reconnection by the RRT* algorithm includes:

[0065] Compare the path cost from the new node to the nearby nodes with the original path cost. If the new path cost is lower, the new node is used as the parent node of the nearby nodes.

[0066] Specifically, the path planning for the mobile battery swapping robot includes:

[0067] In response to the distance between the new node and the end point of the path of the mobile battery swap robot being less than the path generation step, the pre-selected path of the node at this time is used as the final moving path of the mobile battery swap robot to complete the path planning for the mobile battery swap robot.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A path planning method for a mobile battery swapping robot, characterized in that: include: Construct a coordinate system based on the operation site map to obtain the location and area of ​​each obstacle in the operation site; Determine the path generation step length, which is positively correlated with the basic step length of the mobile battery-swapping robot, and negatively correlated with the aspect ratio of the mobile battery-swapping robot, the proportion of the area occupied by obstacles, and the relative size of the standard deviation of the obstacle position; construct the starting point and end point of the path of the mobile battery-swapping robot and the common circumscribed rectangle of all obstacles between them, determine the offset degree of the obstacles on the path, the relative size of the offset degree and the area of ​​the common circumscribed rectangle, the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and end point of the path of the mobile battery-swapping robot, and the common circumscribed rectangle. The ratio of the areas of the rectangles is positively correlated; the path generation step length is used as the step length of the RRT* algorithm, and new nodes of the RRT tree of the RRT* algorithm are continuously obtained through random sampling of the RRT* algorithm. The neighboring nodes of the new node are respectively used as parent nodes, and the parent node on the pre-selected path with the minimum movement cost from the starting point to the new node is used as the final parent node of the new node. The movement cost is positively correlated with the relative average length of each sub-path in the pre-selected path, the standard deviation of the similarity between each sub-path and the starting point to the end point, and the degree of deviation, and is negatively correlated with the relative length of the pre-selected path; The movement cost satisfies the following relationship: ； In the formula, For the The movement cost of the pre-selected paths, is the relative average length of each sub-path in the pre-selected path, is the average length of each sub-path in the pre-selected path, Generate step lengths for the path, is the relative length of the preselected path, is the Euclidean distance between the starting point and the new node of the path of the mobile battery swapping robot, is the length of the preselected path, is the standard deviation of the similarity between the starting point and the end point of each sub-path in the pre-selected path and the path of the mobile battery swapping robot, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is the natural exponential function; Random reconnection is performed through the RRT* algorithm to complete path planning for the mobile battery swapping robot.

2. A path planning method for a mobile battery-swapping robot according to claim 1, characterized in that: The step of constructing a coordinate system according to the operation site map includes: Any corner of the operation site map is used as the origin of the coordinate system, and the horizontal and vertical coordinates of the coordinate system are extended along the boundary of the operation site map, and the horizontal and vertical coordinates increase successively.

3. A path planning method for a mobile battery-swapping robot according to claim 1, characterized in that: The path generation step size satisfies the following relationship: ； In the formula, Generate step lengths for the path, is the basic step length of the mobile battery swapping robot, and are the length and width of the mobile battery-swapping robot, is the ratio of the area occupied by obstacles in the operation site, is the average area occupied by each obstacle in the operation site, and are the length and width of the operation site, is the relative size of the standard deviation of the obstacle locations within the operation site, is the standard deviation of the ordinate of the center point of each obstacle in the operation site, is the standard deviation of the horizontal coordinates of the center points of each obstacle in the operation site, is a natural exponential function.

4. A path planning method for a mobile battery-swapping robot according to claim 1, characterized in that: The degree of deviation satisfies the following relationship: ； In the formula, is the degree of deviation of obstacles in the path of the mobile battery swapping robot, is the relative size of the common circumscribed rectangle, is the area of ​​the common circumscribed rectangle, and are the length and width of the operation site, is the sum of the areas of the circumscribed rectangles of all obstacles between the starting point and the end point of the path of the mobile battery swapping robot. is a natural exponential function.

5. A path planning method for a mobile battery-swapping robot according to claim 1, characterized in that: The method for obtaining the similarity is: Construct a unit vector from the starting point of the path of the mobile battery-swapping robot toward the end point, use the unit vector as the target vector, construct a unit vector from the parent node to the child node in each sub-path in the pre-selected path, and obtain the cosine similarity between the unit vector and the target vector as the similarity.

6. A path planning method for a mobile battery-swapping robot according to claim 1, characterized in that: The random reconnection by RRT* algorithm includes: Compare the path cost from the new node to the nearby nodes with the original path cost. If the new path cost is lower, the new node is used as the parent node of the nearby nodes.

7. A path planning method for a mobile battery-swapping robot according to claim 6, characterized in that: The path planning for the mobile battery swapping robot is completed, including: In response to the distance between the new node and the end point of the path of the mobile battery swap robot being less than the path generation step, the pre-selected path of the node at this time is used as the final moving path of the mobile battery swap robot to complete the path planning for the mobile battery swap robot.

Images