Map boundary-based detour path planning method, chip, and robot

Abstract

The present invention discloses a detour path planning method, chip and robot based on map boundaries. The detour path planning method includes: step 1, constructing a first circular domain with each map boundary grid point as the center and a preset multiple of the robot body diameter as the radius, and then performing a gradual corrosion operation on each first circular domain to obtain a path obstacle degree evaluation value of each grid point in the first circular domain; step 2, traversing a map boundary grid point at a preset interval, and constructing a second circular domain with the currently traversed map boundary grid point as the center and a preset multiple of the robot body diameter as the radius, and then searching for grid points that meet critical conditions based on the path obstacle degree evaluation value obtained in step 1; wherein all grid points in the second circular domain have been assigned the path obstacle degree evaluation value in step 1; step 3, sequentially connecting the grid points that meet the critical conditions searched in step 2 to form a detour path.

Description

Technical Field

[0001] The present invention relates to the technical field of map graphic morphology processing, and relates to a detour path planning method based on map boundaries, a chip, and a robot. Background Art

[0002] Mobile robots can create visual real-time maps with the help of sensors (including lidar, monocular vision sensors, and binocular vision sensors). However, the two-dimensional grid maps generated by these sensors are affected by the environment. For example, uneven lighting and object occlusion can cause shadows around obstacles, and there may be some noise or uneven map edges, which affect the extraction of obstacle outlines in the grid map and subsequent measurement work. How to simply and efficiently extract the route around the boundary of the map (which can be a closed edge route inside the grid map) is of great significance to the autonomous navigation and obstacle avoidance of mobile robots. Summary of the Invention

[0003] To solve the above technical problems, the present invention discloses a detour path planning method, chip, and robot based on map boundaries, which are used to perform a progressive erosion process on the map boundaries within a grid map. Then, based on the results of the progressive erosion process, a detour path is expanded from the map boundary grid points and planned within the map boundary. The specific technical solution is as follows:

[0004] A detour path planning method based on map boundaries includes: step 1, constructing a first circular domain with each map boundary grid point as the circle center and a preset multiple of the robot body diameter as the radius, then performing a gradual erosion operation on each first circular domain to obtain a path obstacle degree evaluation value for the grid points within each first circular domain; wherein the map boundary grid points exist on the boundary of a grid map pre-constructed by the robot; wherein the preset multiple is related to the positioning accuracy of the grid map; step 2, traversing a map boundary grid point at a preset interval, and constructing a second circular domain with the currently traversed map boundary grid point as the circle center and a preset multiple of the robot body diameter as the radius, then searching for grid points that meet a critical condition based on the path obstacle degree evaluation value obtained in step 1; wherein all grid points within the second circular domain have been assigned the path obstacle degree evaluation value in step 1; step 3, sequentially connecting the grid points that meet the critical condition searched in step 2 to form a detour path.

[0005] This technical solution performs a gradual erosion operation on each first circular domain in step 1 to obtain a path obstacle degree evaluation value of any grid point in the first circular domain that is different from the conventional erosion operation. The path obstacle degree evaluation value obtained in step 1 is then combined with the grid points that meet the critical conditions in the second circular domain constructed in step 2 to connect the detour path to obtain a boundary line obtained by subtracting the gradual erosion operation from the grid map. The detour path thus planned to adapt to the boundary of the grid map is not affected by the environment, effectively achieves the denoising and smoothing effects of the detour path, improves the planning effect of the robot's detour path, and especially improves the smoothness of the robot's path along the edge of the obstacle.

[0006] Furthermore, the gradual erosion operation in step 1 includes: calculating the straight-line distance between the currently eroded grid point and the center of the first circular domain to which it belongs, recorded as the boundary search distance; wherein the currently eroded grid point is a grid point covered by the traversal unit starting from the center of the first circular domain; the traversal unit is equivalent to the structural element of the erosion operation; setting the preset multiple of the robot body diameter as the erosion radius; then, setting the path obstacle degree evaluation value of the currently eroded grid point to be negatively correlated with the boundary search distance in the first circular domain; judging the path obstacle degree evaluation value of the currently set currently eroded grid point. Whether the estimated value is greater than the path obstacle degree evaluation value of the same grid point set previously, if so, the path obstacle degree evaluation value of the currently corroded grid point currently set is maintained unchanged, and then the path obstacle degree evaluation value of the currently corroded grid point currently set is set as the latest path obstacle degree evaluation value of the currently corroded grid point; otherwise, the path obstacle degree evaluation value of the currently corroded grid point set previously is updated to the path obstacle degree evaluation value of the currently corroded grid point currently set, and then the path obstacle degree evaluation value of the currently corroded grid point currently set is set as the latest path obstacle degree evaluation value of the currently corroded grid point.

[0007] This technical solution is an improvement on the conventional erosion operation. In the process of traversing each map boundary grid point, each first circular domain performs a gradual erosion operation from the corresponding map boundary grid point to the surrounding areas, and the path obstacle degree evaluation value of the currently eroded grid point is set to decrease within the first circular domain as the boundary search distance increases, so that within the first circular domain, the path obstacle degree evaluation values ​​of the grid points distributed from the outside to the inside increase successively; this technical solution is also based on the characteristic that the same grid point is covered by multiple first circular domains, and the path obstacle degree evaluation value of the currently set currently eroded grid point is compared with the path obstacle degree evaluation value of the same grid point set previously, and the maximum path obstacle degree evaluation value obtained by the comparison is set as the latest path obstacle degree evaluation value of the currently eroded grid point, as the latest path obstacle degree evaluation value of the currently eroded grid point obtained under the gradual erosion operation (which can be understood as filling the grid point with the maximum value), thereby obtaining the currently eroded grid point closest to the corresponding map boundary grid point.

[0008] Furthermore, when the boundary search distance is greater than the erosion radius, the path obstruction level assessment value of the currently eroded grid point is set to a preset minimum path obstruction level assessment value; wherein the path obstruction level assessment value of the map boundary grid point is set to a preset maximum path obstruction level assessment value. This sets all grid points outside the first circular region currently being eroded (performing a progressive erosion operation) to the preset minimum path obstruction level assessment value, and further constrains the path obstruction level assessment value of any grid point within the first circular region to be greater than the preset minimum path obstruction level assessment value and less than or equal to the preset maximum path obstruction level assessment value.

[0009] Furthermore, before performing the gradual erosion operation in step 1, the initial values ​​of the path obstruction degree assessment values ​​for the map boundary grid points are set to a preset maximum path obstruction degree assessment value. At the same time, the initial values ​​of the path obstruction degree assessment values ​​for unknown grid points within the grid map are set to a preset maximum path obstruction degree assessment value. Furthermore, the initial values ​​of the path obstruction degree assessment values ​​for the remaining types of grid points in the grid map are set to a preset minimum path obstruction degree assessment value. Thus, by setting the path obstruction degree assessment values, the map boundary grid points are pre-extracted, and different types of grid points, particularly unknown grid points, are distinguished and marked.

[0010] Furthermore, the method of setting the path obstruction degree assessment value of the currently corroded grid point to be negatively correlated with the boundary search distance within the first circular region includes: the path obstruction degree assessment value of the currently corroded grid point is the product of the ratio of the difference between the corrosion radius and the boundary search distance to the corrosion radius and a preset maximum path obstruction degree assessment value, so that the path obstruction degree assessment value of the currently corroded grid point decreases as the boundary search distance increases; wherein the difference between the corrosion radius and the boundary search distance is the difference obtained by subtracting the boundary search distance from the corrosion radius. In this way, a linear negative correlation is established between the path obstruction degree assessment value of the currently corroded grid point and the boundary search distance, thereby meeting map reading accuracy.

[0011] Furthermore, the step 2 specifically includes: setting a preset multiple of the robot body diameter as the preset interval, traversing the map boundary grid points along the boundary of the robot pre-constructed grid map and according to the preset interval; constructing a second circular domain with the currently traversed map boundary grid point as the center and the preset multiple of the robot body diameter as the radius, and then expanding the neighborhood within the second circular domain with the currently traversed map boundary grid point as the search center; the latest path obstacle degree evaluation value of the grid point currently expanded to in the second circular domain is greater than the preset minimum path obstacle degree evaluation value, and the currently expanded grid point is greater than the preset minimum path obstacle degree evaluation value. When there is at least one grid point in the eight neighborhoods of the grid point expanded to have the latest path obstacle degree assessment value that is the preset minimum path obstacle degree assessment value, the grid point with the smallest path obstacle degree assessment value among the grid points currently expanded to is set as the searched grid point that meets the critical condition, so as to realize the search for the critical position of the grid point whose latest path obstacle degree assessment value is the preset minimum path obstacle degree assessment value and the grid point whose latest path obstacle degree assessment value is not the preset minimum path obstacle degree assessment value, which is used as the target position for connecting the detour path.

[0012] Furthermore, in step 3, a grid point that meets the critical condition and is searched out in the second circular area corresponding to each map boundary grid point traversed at the preset interval in step 2 is sequentially connected to form the detour path, so that the detour path is parallel to the boundary of the grid map; wherein, on one side of the detour path, there is a grid point whose latest path obstacle degree assessment value is the preset minimum path obstacle degree assessment value, and on the other side of the detour path, there is a grid point whose latest path obstacle degree assessment value is not the preset minimum path obstacle degree assessment value; wherein, each grid point that meets the critical condition corresponds to a map boundary grid point traversed at a specific time, so that the order of obtaining the grid points that meet the critical condition is the same as the order of traversing the map boundary grid points, so that the order of obtaining the grid points that meet the critical condition is the same as the order of traversing the map boundary grid points, so that a corrosion area is enclosed between the detour path and the boundary of the grid map. This allows the detour path to have the meaning of the robot walking around obstacles, and the feature of being parallel to the boundary of the grid map improves the coverage of the detour path and reduces the number of discontinuous and non-smooth path segments planned.

[0013] Furthermore, the preset interval is set so that the grid points satisfying the critical condition found within the second circular region corresponding to different map boundary grid points are different grid points. The setting of the preset interval and the preset multiple achieves a balance between the degree of similarity between the detour path and the grid map boundary and the repeatability of the search for grid points satisfying the critical condition.

[0014] A chip stores program code, which, when executed by the chip, implements the aforementioned method for planning a detour path based on a map boundary, thereby ensuring the quality of the detour path planned within the map and parallel to the boundary.

[0015] A robot is provided with the chip and is configured to execute the map boundary-based detour path planning method, thereby providing a navigation path for the robot to avoid obstacles and improving the smoothness of the robot's obstacle avoidance behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of a method for planning a detour path based on map boundaries, disclosed in one embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following is a further description of the specific embodiments of the present invention with reference to the accompanying drawings. It should be noted that the following detailed description is illustrative and is intended to further illustrate the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as commonly understood by those of ordinary skill in the art to which this application belongs.

[0018] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0019] As an example, Figure 1 As shown, a method for planning a detour path based on map boundaries is disclosed. Before executing the detour path planning method, the robot pre-constructs a grid map. The grid map contains map boundaries, which are represented by grid points, referred to as map boundary grid points. The detour path planning method includes the following steps:

[0020] Step P1: Construct a first circular region with each map boundary grid point as the center and a preset multiple of the robot body diameter as the radius. Then, perform a gradual erosion operation on each first circular region to obtain a path obstruction level assessment value for each grid point within the first circular region. Specifically, the path obstruction level assessment value obtained by performing the gradual erosion operation on the first circular region of the current map boundary grid point is updated by the path obstruction level assessment value obtained by the corresponding gradual erosion operation on the adjacent previous map boundary grid point. This ensures that the path obstruction level assessment value obtained by performing the gradual erosion operation on the first circular region of the current map boundary grid point is the most recent path obstruction level assessment value, ensuring that the path obstruction level assessment value of the current map boundary grid point is filled with the optimal value. The map boundary grid points are located on the boundary of the grid map pre-constructed by the robot. The preset multiple is related to the positioning accuracy of the grid map and is set based on a thorough reading of the grid map. At the beginning of the detour path planning method, the preset multiple is set to 1 by default. Then, the process proceeds to Step P2.

[0021] Step P2: Traverse a map boundary grid point at a preset interval, and construct a second circular area with the currently traversed map boundary grid point as the center and a preset multiple of the robot body diameter as the radius. Combined with the path obstacle assessment value obtained in Step 1, a grid point that meets the critical condition is searched for. This allows grid points filled with appropriate path obstacle assessment values ​​to be obtained during the traversal along the map boundary. The process then proceeds to Step P3, where all grid points within the second circular area have already been assigned the path obstacle assessment value in Step 1. Executing Step P2 involves traversing a corresponding map boundary grid point along the map boundary at the preset interval, but not all map boundary grid points, thus conserving computing resources.

[0022] Step P3: Connect the grid points that meet the critical conditions found in step P2 to form a detour route. Each grid point that meets the critical conditions corresponds to a traversed map boundary grid point, and the order of their extraction is consistent, at least in time, but independent of the path obstacle assessment value of the specific grid point. Preferably, the route formed by connecting the grid points that meet the critical conditions found in step P2 is parallel to the grid map boundary.

[0023] Compared with the morphological operations of map graphics associated with the prior art, this embodiment performs a gradual erosion operation on each first circular domain through step P1 to obtain a path obstacle degree evaluation value of any grid point in the first circular domain that is different from the conventional erosion operation. The path obstacle degree evaluation value obtained in step P1 is then combined with the grid points that meet the critical conditions in the second circular domain constructed in step P2 to connect a detour path to obtain an inner boundary obtained by subtracting the gradual erosion operation from the grid map. The detour path thus planned, which is equivalent to the inner boundary of the grid map, is not affected by the environment, effectively achieves the denoising and smoothing effects of the detour path, and improves the planning effect of the robot's detour path, especially improves the smoothness of the robot's path around obstacles along the edge.

[0024] As an embodiment, the gradual etching operation in step P1 includes:

[0025] Step P11, calculate the straight-line distance between the currently corroded grid point and the center of the first circular domain to which it belongs, and record it as the boundary search distance; wherein, the currently corroded grid point is a grid point covered by the traversal unit starting from the center of the first circular domain; the traversal unit is equivalent to the structural element of the erosion operation; then enter step P12. It should be noted that when the structural element scans the grid points of the grid map, part of the neighborhood of the structural element will be outside the boundary of the grid map. For example, when the structural element scans the first row of pixel values ​​above the boundary of the grid map, the structural element and its neighborhood form a 3×3 sliding window by default, which is used to obtain the outline of the area to be scanned in the grid map; part of the structural element will be outside the grid map. At this time, in order to effectively process the grid points covered by the boundary of the grid map, this embodiment uses a morphological operation method different from the conventional one to assign values ​​to the structural element and its neighborhood, that is, to assign the aforementioned path obstacle degree assessment value. It is known to those skilled in the art that the window used to scan the raster map can be a convolution kernel of any shape and size with the structural element as the reference point. This convolution kernel can be a binary matrix representing the neighborhood of the structural element defined in general expansion and erosion operations. Then a two-dimensional planar structural element is composed of a matrix with a value of 0 or 1, so that the origin of the structural element specifies the range of the grid area that needs to be processed in the raster map. The grid point with a value of 1 in the structural element determines whether the neighborhood grid of the structural element needs to participate in the calculation of the aforementioned path obstacle degree evaluation value when performing expansion or erosion operations.

[0026] Step P12: Set the robot body diameter of the preset multiple as the corrosion radius; then proceed to step P13; wherein the preset multiple is set to 1 by default. In the actual path planning operation, it will be adaptively adjusted according to the positioning error or reading accuracy of the grid map to overcome the robot's sensor acquisition error and interference from environmental factors. This is an adjustment method that can be mastered by those skilled in the art.

[0027] Step P13: Set the path obstruction degree evaluation value of the currently corroded grid point to be negatively correlated with the boundary search distance within the first circular region, such that the path obstruction degree evaluation value corresponding to the currently corroded grid point farther from the circle center decreases, and the path obstruction degree evaluation value corresponding to the currently corroded grid point closer to the circle center increases. Then proceed to Step P14.

[0028] It should be noted that before executing the gradual erosion operation in step P1, the initial value of the path obstacle degree evaluation value of the map boundary grid point is set to the preset maximum path obstacle degree evaluation value, and at the same time, the initial value of the path obstacle degree evaluation value of the unknown grid point in the grid map is set to the preset maximum path obstacle degree evaluation value, and the initial value of the path obstacle degree evaluation value of the remaining types of grid points in the grid map is set to the preset minimum path obstacle degree evaluation value. In this way, by setting the path obstacle degree evaluation value, the map boundary grid points are extracted in advance, and different types of grid points, especially unknown grid points, are distinguished and marked. Preferably, these grid points with pre-set path obstacle degree evaluation values ​​are stored in the same array to facilitate subsequent sequential traversal.

[0029] In this embodiment, the grid map pre-constructed by the robot includes free grid points, obstacle grid points and unknown grid points, which correspond to the three states of the map grid: free, occupied and unknown. The grid in the free state refers to the grid that is not occupied by obstacles, which is the grid position point reachable by the robot. It is the free grid point and can constitute an unoccupied area. The grid in the occupied state refers to the grid occupied by obstacles, which is the obstacle grid point and can constitute an occupied area. The unknown grid refers to the grid area whose specific situation is unclear during the robot's map construction process. Its position point is often blocked by obstacles and can constitute an unknown area.

[0030] It should be noted that, taking a sweeping robot as an example, a local probability grid can be established based on a single-line laser radar, or a local grid map can be established based on a visual sensor. The global map is generated when the sweeping robot is used for the first time. It uses its own various sensors (e.g., collision sensors, accelerometers, gyroscopes, ultrasonic rangefinders, cameras, single-line laser radars, etc.) to search the movement area of ​​each room, sensing the location, shape, and size of each room, as well as the location, shape, and size of obstacles encountered. Based on this, it draws an environmental boundary map. This is a map of the entire room drawn by walking and recording indoors. The map includes occupied areas, unoccupied areas, and unknown areas. Both occupied and unoccupied areas can be classified as cleaned areas.

[0031] Step P14: Determine whether the path obstacle degree evaluation value of the currently set corroded grid point is greater than the path obstacle degree evaluation value of the same grid point set previously. If so, proceed to step P15; otherwise, proceed to step P16.

[0032] Step P15: Maintain the currently set path obstacle degree assessment value of the currently corroded grid point unchanged, and then set the currently set path obstacle degree assessment value of the currently corroded grid point as the latest path obstacle degree assessment value of the currently corroded grid point; and take the maximum value of the path obstacle degree assessment values ​​obtained by the progressive corrosion operation of the currently corroded grid point through the first circular area corresponding to multiple map boundary grid points as the latest path obstacle degree assessment value of the currently corroded grid point.

[0033] Step P16: Update the previously set path obstacle degree evaluation value of the currently corroded grid point to the currently set path obstacle degree evaluation value of the currently corroded grid point, and then set the currently set path obstacle degree evaluation value of the currently corroded grid point as the latest path obstacle degree evaluation value of the currently corroded grid point.

[0034] Preferably, in step P1, when performing the aforementioned gradual erosion operation on each first circular domain, when the currently eroded grid point is not pre-set to a preset maximum path obstacle degree evaluation value (the currently eroded grid point is neither a map boundary grid point nor an unknown grid point), the path obstacle degree evaluation value of the currently eroded grid point is updated at least once after comparison in the manner of step P14.

[0035] Combined with the gradual erosion operation described in the aforementioned steps P11 to P16, it can be seen that this embodiment is an improvement on the conventional erosion operation. In the process of traversing each map boundary grid point, each first circular domain performs a gradual erosion operation from the corresponding map boundary grid point to the surrounding areas, and the path obstacle degree evaluation value of the currently eroded grid point is set to decrease as the boundary search distance increases within the first circular domain, so that within the first circular domain, the path obstacle degree evaluation values ​​of the grid points distributed from the outside to the inside increase in sequence; this technical solution is also based on the same grid point being traversed by multiple first circular domains. Based on the characteristics of the circle area covered, the path obstacle degree evaluation value of the currently set grid point is compared with the path obstacle degree evaluation value of the same grid point set previously, and the maximum path obstacle degree evaluation value obtained by the comparison is set as the latest path obstacle degree evaluation value of the currently corroded grid point. As the latest path obstacle degree evaluation value of the currently corroded grid point obtained under the gradual corrosion operation (which can be understood as filling the grid point with the maximum value), the currently corroded grid point closest to the corresponding map boundary grid point is obtained, which is conducive to planning the shortest detour path.

[0036] Based on the previous embodiment, when the boundary search distance is greater than the erosion radius, the path obstruction level assessment value of the currently eroded grid point is set to a preset minimum path obstruction level assessment value. This is equivalent to setting the most recent path obstruction level assessment value of the currently eroded grid point whose straight-line distance from the center of the corresponding first circular region is greater than the erosion radius to the preset minimum path obstruction level assessment value. Furthermore, the path obstruction level assessment value of the map boundary grid point is set to a preset maximum path obstruction level assessment value. This sets all grid points outside the currently eroded (progressively eroded) first circular region to the preset minimum path obstruction level assessment value, further constraining the path obstruction level assessment value of any grid point within the first circular region to be greater than the preset minimum path obstruction level assessment value and less than or equal to the preset maximum path obstruction level assessment value, which facilitates the formation of an erosion area. This embodiment creates critical grid positions at the edge of the first circular region by filling the grid points outside the first circular region with the preset minimum path obstruction level assessment value.

[0037] As an embodiment, the method of setting the path obstacle degree evaluation value of the currently corroded grid point to be negatively correlated with the boundary search distance within the first circular domain includes: the path obstacle degree evaluation value of the currently corroded grid point is the product of the ratio of the difference between the corrosion radius and the boundary search distance to the corrosion radius and a preset maximum path obstacle degree evaluation value, so that the negative correlation is a linear negative correlation. Among them, the difference between the corrosion radius and the boundary search distance is the difference obtained by subtracting the boundary search distance from the corrosion radius, so that the path obstacle degree evaluation value of the currently corroded grid point decreases as the boundary search distance increases, that is, the larger the boundary search distance, the smaller the difference between the corrosion radius and the boundary search distance, the farther the currently corroded grid point deviates from the center of the first circular domain to which it belongs (covered in the execution of the progressive corrosion operation), resulting in a smaller calculation result of the path obstacle degree evaluation value of the currently corroded grid point, and conversely, the larger the calculation result of the path obstacle degree evaluation value of the currently corroded grid point; in order to ensure the calculation accuracy to match the positioning accuracy of the map, this embodiment preferably sets the preset maximum path obstacle degree evaluation value to a decimal number of 100, and at the same time sets the preset minimum path obstacle degree evaluation value to a decimal number of 0.

[0038] As an embodiment, the step P2 specifically includes:

[0039] The robot body diameter of a preset multiple is set as the preset interval, and the robot traverses the map boundary grid points along the boundary of the pre-constructed grid map at the preset interval, that is, on the boundary of the pre-constructed grid map, one map boundary grid point is traversed every preset interval; the setting of the preset multiple also represents the setting of the preset interval, which can achieve a balance between the similarity between the detour path and the boundary of the grid map and the search repeatability of the grid points that meet the critical conditions.

[0040] Each time a map boundary grid point is traversed, a second circular area is constructed with the currently traversed map boundary grid point as the center and a preset multiple of the robot body diameter as the radius; then, within the second circular area, the neighborhood is expanded with the currently traversed map boundary grid point as the search center, including four-neighborhood expansion or eight-neighborhood expansion.

[0041] In the second circular area, when the latest path obstacle degree assessment value of the grid point currently expanded to is greater than the preset minimum path obstacle degree assessment value, and the latest path obstacle degree assessment value of at least one grid point in the eight neighborhoods of the grid point currently expanded to is the preset minimum path obstacle degree assessment value, the grid point with the smallest path obstacle degree assessment value among the grid points currently expanded to is set as the searched grid point that meets the critical condition, which also means that the grid point currently expanded to is adjacent to the grid point filled with the preset minimum path obstacle degree assessment value. As the intersection grid point of the grid point filled with the preset minimum path obstacle degree assessment value and the grid point not filled with the preset minimum path obstacle degree assessment value, it can be used as the target position for connecting the detour path in this embodiment.

[0042] In this embodiment, during the expansion process, if a grid point with the minimum path obstruction assessment value adjacent to a grid point whose path obstruction assessment value is set to the preset minimum path obstruction assessment value is searched every other fuselage diameter (i.e., the preset multiplier is set to 1), the grid point that satisfies the critical condition each time is searched, although the grid point found to satisfy the critical condition is the farthest from the currently searched map boundary grid point, it may be the same as the grid point found in the previous search. Therefore, preferably, the preset interval is set so that the grid points that satisfy the critical condition are found in different grids within the second circular region corresponding to different map boundary grid points. The setting of the preset interval and the adaptive setting of the preset multiplier achieve a balance between the degree of similarity between the detour path and the grid map boundary and the repetitiveness of the search for grid points that satisfy the critical condition.

[0043] Based on the above embodiment, in step P3, grid points that meet the critical condition and are searched within the second circular region corresponding to each map boundary grid point traversed at the preset interval in step P2 are sequentially connected to form the detour path, such that the detour path is parallel to the boundary of the grid map. A grid point with a latest path obstacle assessment value equal to the preset minimum path obstacle assessment value exists on one side of the detour path, and a grid point with a latest path obstacle assessment value not equal to the preset minimum path obstacle assessment value exists on the other side of the detour path. This ensures that a pair of grid points filled with the preset minimum path obstacle assessment value and grid points not filled with the preset minimum path obstacle assessment value are always found on both sides of the detour path, thus serving as a boundary line and thus enabling the detour path to function as a robot for obstacle avoidance. This ensures that the detour path is functional for robot obstacle avoidance, and the fact that it is parallel to the grid map boundary improves the coverage of the detour path and reduces the number of discontinuous and non-smooth path segments that are planned.

[0044] It should be emphasized that each of the grid points that meets the critical conditions corresponds to a map boundary grid point traversed at a specific time. The corresponding grid points that meet the critical conditions can be connected in sequence according to the traversal order of the map boundary grid points. The specific directions include but are not limited to clockwise and counterclockwise directions. Preferably, the planned detour path is guaranteed to be parallel to the boundary of the grid map.

[0045] The progressive erosion operation performed in this embodiment forms an erosion area between the detour path and the boundary of the grid map, wherein the boundary of the grid map is a closed boundary line, so that the detour path corresponding to the boundary of the grid map formed by the connection in the aforementioned step P3 is also a closed route. The detour path then becomes a boundary line obtained by subtracting the erosion area from the grid map, that is, the edge line of the remaining closed grid map area (including the grid points filled with the preset minimum path obstacle degree assessment value and the grid points filled with the preset maximum path obstacle degree assessment value).

[0046] Based on the aforementioned embodiments, a chip is also disclosed, on which program code is stored. When executed by the chip, the program code implements the aforementioned method for planning a detour path based on a map boundary, thereby ensuring the quality of the detour path planned within the map and parallel to the boundary.

[0047] The present invention also discloses a robot equipped with the chip, configured to execute the map boundary-based detour path planning method, thereby providing a navigation path for the robot to avoid obstacles and improving the smoothness of the robot's obstacle avoidance behavior.

[0048] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other manner. Any person skilled in the art may utilize the above-disclosed technical content to modify or modify the present invention into equivalent embodiments. However, any simple modifications, equivalent variations, and modifications to the above embodiments that do not depart from the technical content of the present invention and are based on the technical essence of the present invention remain within the scope of protection of the present invention.

Claims

1. A detour path planning method based on map boundaries, characterized in that: The detour path planning method includes: Step 1: Construct a first circular region with each map boundary grid point as the center and a preset multiple of the robot body diameter as the radius. Then, perform a gradual erosion operation on each first circular region to obtain a path obstacle degree assessment value for each grid point within the first circular region. The map boundary grid points are located on the boundary of the robot's pre-constructed grid map. The preset multiple is related to the positioning accuracy of the grid map. Step 2: Traverse a map boundary grid point at a preset interval, and construct a second circular area with the currently traversed map boundary grid point as the center and a preset multiple of the robot body diameter as the radius. Then, combine the path obstacle degree assessment value obtained in Step 1 to search for grid points that meet the critical condition; wherein, all grid points in the second circular area have been assigned the path obstacle degree assessment value in Step 1; Step 3: connect the grid points that meet the critical conditions found in step 2 in sequence to form a detour path; The gradual corrosion operation in step 1 includes: Calculate the straight-line distance between the currently eroded grid point and the center of the first circular region to which it belongs, and record it as the boundary search distance; wherein the currently eroded grid point is a grid point covered by the traversal unit starting from the center of the first circular region; the traversal unit is equivalent to the structural element of the erosion operation; The robot body diameter of the preset multiple is set as the corrosion radius; Then, setting the path obstacle degree evaluation value of the currently corroded grid point to be in a negative correlation with the boundary search distance within the first circular region; Determine whether the path obstacle degree evaluation value of the currently set currently corroded grid point is greater than the path obstacle degree evaluation value of the same grid point set previously. If so, maintain the path obstacle degree evaluation value of the currently set currently corroded grid point unchanged, and then set the path obstacle degree evaluation value of the currently set currently corroded grid point as the latest path obstacle degree evaluation value of the currently corroded grid point; otherwise, update the path obstacle degree evaluation value of the currently corroded grid point set previously to the path obstacle degree evaluation value of the currently set currently corroded grid point, and then set the path obstacle degree evaluation value of the currently set currently corroded grid point as the latest path obstacle degree evaluation value of the currently corroded grid point.

2. The detour path planning method according to claim 1, characterized in that: When the boundary search distance is greater than the corrosion radius, the path obstacle degree evaluation value of the currently corroded grid point is set to a preset minimum path obstacle degree evaluation value; The path obstacle degree evaluation value of the map boundary grid point is set to a preset maximum path obstacle degree evaluation value.

3. The detour path planning method according to claim 1, characterized in that: Before executing the gradual erosion operation in step 1, the initial value of the path obstacle degree evaluation value of the map boundary grid point is set to the preset maximum path obstacle degree evaluation value, and the initial value of the path obstacle degree evaluation value of the unknown grid point in the grid map is set to the preset maximum path obstacle degree evaluation value, and the initial value of the path obstacle degree evaluation value of the remaining types of grid points in the grid map is set to the preset minimum path obstacle degree evaluation value.

4. The detour path planning method according to any one of claims 2 to 3, characterized in that: The method of setting the path obstacle degree evaluation value of the currently corroded grid point to be negatively correlated with the boundary search distance within the first circular region includes: The path obstruction degree evaluation value of the currently corroded grid point is the product of the difference between the corrosion radius and the boundary search distance, the ratio of the corrosion radius, and a preset maximum path obstruction degree evaluation value, such that the path obstruction degree evaluation value of the currently corroded grid point decreases as the boundary search distance increases; The difference between the corrosion radius and the boundary search distance is the difference obtained by subtracting the boundary search distance from the corrosion radius.

5. The detour path planning method according to any one of claims 2 to 3, characterized in that: The step 2 specifically includes: Setting a preset multiple of the robot body diameter as the preset interval, following the boundary of a pre-constructed grid map of the robot, and traversing the map boundary grid points according to the preset interval; A second circular area is constructed with the currently traversed map boundary grid point as the center and a preset multiple of the robot body diameter as the radius. Then, within the second circular area, the neighborhood is expanded with the currently traversed map boundary grid point as the search center. When the latest path obstacle degree assessment value of the grid point currently expanded to in the second circular domain is greater than the preset minimum path obstacle degree assessment value, and there is at least one grid point in the eight neighborhoods currently expanded to the grid point whose latest path obstacle degree assessment value is the preset minimum path obstacle degree assessment value, then the grid point with the smallest path obstacle degree assessment value among the grid points currently expanded to is set as the searched grid point that meets the critical condition.

6. The detour path planning method according to claim 5, characterized in that: In step 3, the grid points satisfying the critical condition that are searched for in the second circular region corresponding to each map boundary grid point traversed at the preset interval in step 2 are sequentially connected to form the detour path, such that the detour path is parallel to the boundary of the grid map; Wherein, on one side of the detour path, there is a grid point whose latest path obstacle degree assessment value is the preset minimum path obstacle degree assessment value, and on the other side of the detour path, there is a grid point whose latest path obstacle degree assessment value is not the preset minimum path obstacle degree assessment value; Each of the grid points meeting the critical condition corresponds to a map boundary grid point traversed at a specific time, so that the acquisition order of the grid points meeting the critical condition is the same as the traversal order of the map boundary grid points.

7. The detour path planning method according to claim 6, characterized in that: The preset interval is set so that the grid points meeting the critical condition searched out in the second circular area corresponding to different map boundary grid points are different grid points.

8. A chip having program code stored thereon, characterized in that: When the program code is executed by the chip, the detour path planning method based on map boundaries as described in any one of claims 1 to 7 is implemented.

9. A robot, characterized in that: The robot is provided with the chip according to claim 8, and the robot is configured to execute the detour path planning method based on map boundaries according to any one of claims 1 to 7.

Images