A path planning method and storage medium for an inspection robot

Abstract

This invention provides a path planning method and storage medium for an inspection robot, belonging to the field of path planning technology. The method includes: converting an undirected inspection graph into a directed inspection graph, with the goal of the inspection robot only turning at turning points during the inspection process; determining the mapping point corresponding to each inspection point on the directed inspection graph; determining the inspection point order of all inspection points of the inspection robot by analyzing the topological relationship between the mapping points; responding to the issued current inspection task, determining the inspection order of the points to be inspected in the current inspection task according to the inspection point order, and realizing the path planning of the current inspection task using the directed inspection graph. The path planning method for inspection robots provided by this invention can quickly realize multi-target point path planning for inspection robots according to user inspection requirements, and ensures the safety of the inspection robot and equipment in the inspection area by introducing methods such as turning at turning points.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a path planning method and storage medium for an inspection robot. Background Technology

[0002] With technological advancements, market demand for equipment inspection has increased significantly, while the cost of manual inspection has gradually risen, and manual inspection is difficult to complete under certain conditions. These factors have spurred the application of inspection robots (such as quadruped inspection robots).

[0003] Currently, most inspection robots on the market use the A* algorithm as the mainstream path planning algorithm. As a heuristic search algorithm, the A* algorithm can find the shortest path between two points in a known environment, and has the advantages of high efficiency and accuracy.

[0004] However, due to the complexity of inspection tasks and scenarios, the movement of inspection robots is limited, making it difficult to adapt to complex environments. Furthermore, the traditional A* algorithm, which can only perform path planning between two points, has significant limitations and is ill-suited for adapting to varied tasks. In addition, some inspection scenarios involve numerous devices, narrow roads, and directional requirements necessitating multiple U-turns. Paths planned by the traditional A* algorithm may cause collisions when the inspection robot turns at corners in narrow roads, damaging both the equipment within the inspection area and the robot itself. Summary of the Invention

[0005] This invention provides a path planning method for an inspection robot to address at least one deficiency in the prior art.

[0006] In a first aspect, the present invention provides a path planning method for an inspection robot, comprising: acquiring a skeleton map of an inspection area; determining the turning points of the inspection robot on the skeleton map; and dividing the skeleton map into multiple segments based on the turning points; if the length of any segment is greater than a preset length, setting path points at preset intervals starting from one endpoint of the segment to complete the setting of path points for the segment; traversing all segments to construct an undirected inspection graph based on all path points; converting the undirected inspection graph into a directed inspection graph with the goal that the inspection robot only turns at turning points during the inspection process; using the directed path points corresponding to each inspection point in the directed inspection graph that are closest in distance and in the same preset interval as mapping points; and determining the inspection point order of all inspection points of the inspection robot by analyzing the topological relationship between the mapping points; wherein the inspection points are pre-planned and include the inspection starting point; and responding to the issued current inspection task, determining the inspection order of the points to be inspected in the current inspection task based on the inspection point order, and using the directed inspection graph to realize the path planning of the current inspection task.

[0007] According to the path planning method for the inspection robot provided by the present invention, obtaining the skeleton map of the inspection area includes: converting the SLAM map of the inspection area into a binary black and white image; determining the largest connected region of the white part in the black and white image to generate a safe area map; and extracting the skeleton map from the safe area map; wherein the largest connected region of the white part is the feasible area of ​​the inspection robot.

[0008] According to the path planning method for the inspection robot provided by the present invention, determining the turning points of the inspection robot on the skeleton map includes: drawing a circle with any pixel on the skeleton map as the center and a first preset number of pixels as the radius, and counting the number of white boundary pixels of the circle; if the number of white boundary pixels is greater than a second preset number, taking the any pixel as a turning point; and traversing all pixels on the skeleton map to determine all turning points of the inspection robot on the skeleton map.

[0009] According to the path planning method for inspection robots provided by the present invention, with the goal of ensuring that the inspection robot only turns at turning points during the inspection process, the method transforms an undirected inspection graph into a directed inspection graph, including:

[0010] Starting from a path point at one end of any interval in the undirected graph, traverse all path points sequentially to calculate the direction angle of each path point. The calculation is divided into two cases:

[0011] Case 1: Calculate the direction angle of each path point from the starting point to the second-to-last path point. Specifically, determine the line connecting the currently traversed path point and the next path point to be traversed, and take the angle between the connecting line and the positive direction of the horizontal coordinate axis as the direction angle of the currently traversed path point; wherein the range of the angle is [-90°, 90°).

[0012] The second case: find the direction angle of the last traversed path point, specifically: take the direction angle of the second to last traversed path point as the direction angle of the last traversed path point.

[0013] Based on the position and orientation angle of any path point in the undirected inspection graph, generate two directed path points in the directed inspection graph corresponding to any path point; wherein, the positions of the two corresponding directed path points are the same as the position of any path point, the orientation of one of the two directed path points is the orientation angle of any path point, and the orientation of the other directed path point is the orientation angle of any path point plus 180 degrees.

[0014] For any interval, if there are two adjacent directed path points, and the directions of the two adjacent directed path points are both in the range of [-90°, 90°), add an edge between the two adjacent directed path points, with the edge pointing towards the positive half-axis of the horizontal coordinate axis; if the directions of the two adjacent directed path points are both in the range of [90°, 270°), add an edge between the two adjacent directed path points, with the edge pointing towards the negative half-axis of the horizontal coordinate axis.

[0015] Specifically, by analyzing the topological relationships between mapping points, the inspection point ranking of all inspection points of the inspection robot is determined, including:

[0016] Using the mapping point corresponding to the inspection start point as the starting point, perform path planning with the mapping points corresponding to other inspection points whose order is not determined, in order to determine the next inspection point with the shortest path;

[0017] Starting from the mapping point corresponding to the next inspection point with the shortest path, perform path planning with the mapping points corresponding to the inspection points whose sorting is not yet determined, and determine the next inspection point with the shortest path. Continue in this manner until all inspection points are sorted.

[0018] According to the path planning method for the inspection robot provided by the present invention, the method for determining the mapping point of any inspection point on the directed inspection graph includes: calculating the distance between the any inspection point and each directed path point on the directed inspection graph, and determining the directed path point closest to the any inspection point; determining, from the closest directed path points, a directed path point whose direction is in the same preset interval as the direction of the any inspection point, as the mapping point of the any inspection point; wherein the direction of the any inspection point is pre-planned and set.

[0019] According to the path planning method for the inspection robot provided by the present invention, the order of inspection points of all inspection points of the inspection robot is determined by analyzing the topological relationship between mapping points. The method includes: taking the mapping point corresponding to the inspection start point as the starting point, performing path planning with the mapping points corresponding to other inspection points whose order is not determined, to determine the next inspection point with the shortest path; taking the mapping point corresponding to the next inspection point with the shortest path as the starting point, performing path planning with the mapping points corresponding to other inspection points whose order is not determined, to determine the next inspection point with the shortest path, and so on, until the order of all inspection points is completed.

[0020] According to the path planning method for the inspection robot provided by the present invention, the inspection order of the points to be inspected in the current inspection task is determined according to the inspection point sorting, and the path planning of the current inspection task is realized using the directed inspection graph. The method includes: determining the inspection order of the points to be inspected in the current inspection task according to the relative position of the points to be inspected in the inspection point sorting; determining the inspection order of the mapping points corresponding to the points to be inspected based on the inspection order of the points to be inspected; taking the path point closest to the current position of the inspection robot as the starting point, and determining the shortest path between each pair of adjacent mapping points according to the inspection order of the mapping points, so as to realize the path planning of the current inspection task.

[0021] According to the path planning method for the inspection robot provided by the present invention, when there are doors and entrances in the path planning, the method further includes: a door entry process: controlling the inspection robot to stop moving forward before entering a dangerous area, and after determining that the door has been opened, controlling the inspection robot to pass through the dangerous area and enter the door; a door exit process: sending a door closing command when it is determined that the inspection robot has left the dangerous area; wherein, the dangerous area is determined based on the door's position information and the door's rotation radius, and no path points are set in the dangerous area.

[0022] According to the path planning method for the inspection robot provided by the present invention, determining the shortest path between each pair of adjacent mapping points includes: when the shortest path between adjacent mapping points has been predetermined, directly using the predetermined shortest path; when the shortest path between adjacent mapping points has not been predetermined, generating the shortest path using a preset path optimization algorithm.

[0023] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the path planning method for the inspection robot as described above.

[0024] The path planning method for inspection robots provided by this invention can quickly realize multi-target point path planning for inspection robots according to user inspection requirements, and ensure the safety of inspection robots and equipment in the inspection area by introducing turning points and other methods.

[0025] This invention successfully reduces the time complexity significantly by cyclically utilizing the planned inspection point sorting (time complexity from...). It dropped to This not only significantly shortened the planning time but also enabled efficient path planning for multiple target points.

[0026] This invention introduces a turning point design, an innovative measure that can effectively prevent the inspection robot from colliding at the corners of narrow roads, thereby ensuring that both the factory equipment and the inspection robot itself are protected from damage during the inspection process.

[0027] This invention transforms undirected graphs into directed graphs by applying specific transformation criteria. This improvement greatly reduces the need for inspection robots to frequently adjust their direction during movement, thereby improving inspection efficiency and operational stability. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 This is a flowchart illustrating the path planning method for the inspection robot provided by the present invention.

[0030] Figure 2 This is a schematic diagram of the process for constructing an undirected graph for inspection provided by the present invention;

[0031] Figure 3 This is a schematic diagram of the SLAM map provided by the present invention;

[0032] Figure 4 This is a schematic diagram of the largest connected region in the white area provided by the present invention;

[0033] Figure 5 This is a schematic diagram of the skeleton map of the inspection area provided by the present invention;

[0034] Figure 6 This is a schematic diagram of the turning point determination provided by the present invention;

[0035] Figure 7 This is the path point map provided by the present invention;

[0036] Figure 8 This is a comparison chart of the path planning effects using directed and undirected graphs provided by the present invention;

[0037] Figure 9 This is a comparison diagram of undirected and directed path graphs provided by the present invention;

[0038] Figure 10 This is a schematic diagram of directional path planning provided by the present invention;

[0039] Figure 11 This is a logical block diagram of the path planning for the current inspection task provided by the present invention;

[0040] Figure 12 This is a schematic diagram of the danger zone formed by the rotation of the door, provided by the present invention;

[0041] Figure 13 This is a schematic diagram of opening and closing doors during the inspection process provided by the present invention;

[0042] Figure 14 This is a schematic diagram illustrating the application of the reuse concept in the path planning provided by this invention;

[0043] Figure 15 This is a preliminary workflow diagram provided by the present invention;

[0044] Figure 16 This is the overall operation flowchart provided by the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0046] It should be noted that, in the description of the embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0047] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more.

[0048] The following is combined with Figures 1-16 This invention describes the path planning method for an inspection robot provided in an embodiment of the invention.

[0049] Figure 1 This is a flowchart illustrating the path planning method for the inspection robot provided by the present invention, as shown below. Figure 1 As shown, including but not limited to the following steps:

[0050] Step 101: Obtain the skeleton map of the inspection area, determine the turning points (also known as intersections) of the inspection robot on the skeleton map, and divide the skeleton map into multiple segments based on the turning points.

[0051] Among them, inspection robots can be quadrupedal, wheeled, or tracked inspection robots.

[0052] Step 102: If the length of any interval is greater than the preset length, set path points at preset intervals starting from one endpoint of the interval to complete the setting of path points for the interval. Traverse all intervals to construct an undirected inspection graph based on all path points.

[0053] Step 103: With the goal of the inspection robot only turning at turning points during the inspection process, transform the undirected inspection graph into a directed inspection graph;

[0054] Step 104: On the directed inspection graph, the directed path point that is closest to each inspection point and whose direction is in the same preset interval is taken as the mapping point. By analyzing the topological relationship between the mapping points, the inspection point ranking of all inspection points of the inspection robot is determined. The inspection points are pre-planned and include the inspection starting point.

[0055] Step 105: In response to the issued current inspection task, determine the inspection order of the points to be inspected in the current inspection task according to the inspection point sorting, and use the directed inspection graph to realize the path planning of the current inspection task.

[0056] The following is a detailed explanation.

[0057] (1) Generate the path points for inspection and construct the undirected inspection graph.

[0058] Figure 2 This is a schematic diagram of the process for constructing an undirected graph for inspection provided by the present invention, as shown below. Figure 2 As shown, the detailed steps are as follows:

[0059] Step a: Obtain the SLAM map of the inspection area.

[0060] Specifically, the inspection robot is manually controlled via remote control to move to various locations within the inspection area. During movement, the robot performs a comprehensive scan of its surroundings. Using its onboard radar system, it emits electromagnetic waves and receives reflected signals, thereby accurately capturing distance data of the surrounding environment. This data is fused with the robot's own movement trajectory information to achieve precise positioning of the robot. Furthermore, the robot meticulously compares newly acquired environmental information with previous scan results, continuously updating and optimizing the SLAM map to generate the final SLAM map, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the SLAM map provided by the present invention.

[0061] Step b: Convert the SLAM map of the inspection area into a binary black and white image, determine the largest connected region of the white part in the black and white image, and generate a safe area map.

[0062] Specifically, for the SLAM map obtained in step a, each pixel is evaluated: if the pixel value is less than 128, it is assigned a value of 0; if it is greater than 128, it is assigned a value of 255. This converts the SLAM map into a binary black and white image. Next, the largest connected region of the white area is found in the black and white image. This region represents the feasible area for the inspection robot and is extracted, such as... Figure 4 As shown, Figure 4 This is a schematic diagram of the largest connected region in the white area provided by the present invention.

[0063] Step c: Extract the skeleton map from the safe zone map.

[0064] Specifically, for the largest connected region obtained in step b, for each foreground pixel, its removability is determined based on the state of its surrounding pixels. A pixel is marked as removable only if removing it does not disrupt the image's connectivity or alter its topology. By iteratively refining the binary image using this morphological skeleton extraction method, the skeleton can be extracted. Deburring the extracted skeleton yields a smoother skeleton, resulting in a skeleton map effect, as shown below. Figure 5 As shown, Figure 5 This is a schematic diagram of the skeleton map of the inspection area provided by the present invention.

[0065] Step d: Determine the turning points (intersections) of the inspection robot on the skeleton map.

[0066] Optionally, a circle is drawn with any pixel on the skeleton map as the center and a first preset number of pixels as the radius, and the number of white boundary pixels of the circle is counted; if the number of white boundary pixels is greater than a second preset number, the aforementioned pixel is taken as a turning point; all pixels on the skeleton map are traversed to determine all turning points of the inspection robot on the skeleton map.

[0067] Specifically, for the skeleton map generated in step c, a circle is drawn with a radius of one (i.e., the first preset number) pixels. Each boundary pixel of the circle is checked to see if it is white. If the number of white boundary pixels is 3 (i.e., the second preset number) or more, then the pixel is considered a turning point. All turning points are found by traversing the lines of the entire skeleton map, forming a set of turning points. ,in m The number of turning points. Figure 6 The points circled in red are all turning points (intersections). Figure 6 This is a schematic diagram of the turning point determination provided by the present invention:

[0068] ;

[0069] in, The first part of the skeleton map m A turning point.

[0070] Step e: Divide the skeleton map into multiple segments based on the turning points. If the length of any segment is greater than the preset length, set path points at preset intervals, starting from one endpoint of any segment. Complete the setting of path points for any segment. Traverse all segments to construct an undirected inspection graph based on all path points.

[0071] Specifically, the skeleton map is divided into multiple segments using the turning points obtained in step d. For each segment, if the distance from one end to the other exceeds 1.5u pixels, a path point is set every u pixels (in practice, u=20, but can be adjusted according to the actual situation). This process continues until the distance to the other end is less than 1.5u pixels, at which point no further path points are set. The generated effect diagram is shown below, using segment 14 as an example. Figure 7 As shown, Figure 7 This is the path point map provided by the present invention. The generated path points and turning points are added to the path point set V, wherein... n The number of path points:

[0072] ;

[0073] in, The first part of the skeleton map n There are path points.

[0074] Through the above steps, this invention can obtain all the path points needed in the robot's inspection process. Combining these path points and the skeleton image, an undirected inspection graph G can be generated. 无 =( V , E ),in, Let be the set of path points in an undirected graph, i.e., the set of vertices in an undirected graph. Let be the set of edges in an undirected graph. For any path point, if there are other path points directly connected to it, then add an undirected edge between the path point and the other path points.

[0075] (2) With the goal of the inspection robot turning only at turning points during the inspection process, the undirected graph (hereinafter referred to as the undirected graph) is transformed into a directed graph (hereinafter referred to as the directed graph) G. 有 =( , ),in, Let be the set of directed path points in a directed graph, that is, the set of vertices in a directed graph. Let be the set of edges in a directed graph.

[0076] Path planning based on the undirected graph generated above presents a risk of the inspection robot turning around in narrow passages and potentially colliding with equipment. To address this issue, this invention transforms the obtained undirected inspection graph into a directed inspection graph using specific transformation logic. The achieved effect is as follows: Figure 8 As shown, Figure 8 This is a comparison diagram of the path planning effects using directed and undirected graphs provided by this invention. The black lines represent equipment boundaries, and the green lines in the middle represent patrol lines on the skeleton map. The inspection sequence is ①→②→③. If the previous undirected graph planning is used, the robot will turn at point ②, easily touching the equipment on the black boundary. After the conversion of this invention, the inspection robot will only turn at wide turning points, thus avoiding the danger of collisions and equipment damage.

[0077] To achieve the effects described above, the present invention provides a method for converting an undirected inspection graph into a directed inspection graph as follows:

[0078] (a) Determine the orientation angles of path points in the undirected graph of the inspection:

[0079] The direction angle of a path point in an undirected graph is calculated by dividing the graph into intervals. The method for calculating the direction angle of a path point within any interval is as follows: starting from the path point at one end of the interval, all path points are traversed sequentially to calculate the direction angle of each path point. Specifically, the calculation is divided into two cases:

[0080] Case 1: Calculate the orientation angle of each path point from the starting point to the second-to-last path point. Specifically: Determine the line connecting the currently traversed path point to the next path point to be traversed. The angle between this line and the positive direction of the horizontal coordinate axis is taken as the orientation angle of the currently traversed path point; this angle ranges from -90° to 90°. The horizontal coordinate axis is the X-axis of a pre-established standard horizontal rectangular coordinate system. See [link to relevant documentation]. Figure 9 The settings in [the system / mechanism].

[0081] The second case: Find the direction angle of the last traversed path point. Specifically, take the direction angle of the second to last traversed path point as the direction angle of the last traversed path point.

[0082] (b) First determine the directed path points in the directed graph of the inspection:

[0083] Specifically, based on the position and orientation angle of any path point in the undirected graph being inspected, two directed path points corresponding to any path point are generated in the directed graph being inspected.

[0084] In this context, the positions of the two corresponding directed path points are the same as the position of any path point. The direction of one of the two directed path points is the direction angle of any path point, ranging from [-90°, 90°), and the direction of the other directed path point is the direction angle of any path point plus 180 degrees, ranging from [90°, 270°].

[0085] (c) In step (b) above, only the directed path points in the inspected directed graph are determined. Next, based on the directed path points in the inspected directed graph, the edges in the inspected directed graph are set to form the final inspected directed graph:

[0086] The edges in a directed graph are determined by dividing the graph into intervals. The method for determining the edges in any interval of the directed graph is as follows:

[0087] For any interval, if there are two adjacent directed path points, and the directions of the two adjacent directed path points are both in the range of [-90°, 90°), add an edge between the two adjacent directed path points with the direction of the edge pointing to the positive half-axis of the horizontal coordinate axis, that is, the direction of the edge is also in the range of [-90°, 90°); if the directions of the two adjacent directed path points are both in the range of [90°, 270°), add an edge between the two adjacent directed path points with the direction of the edge pointing to the negative half-axis of the horizontal coordinate axis, that is, the direction of the edge is also in the range of [90°, 270°).

[0088] Based on the above transformation, the direction of the inspection robot can only be changed at turning points and boundaries through the transformation of directed path points, such as... Figure 9 As shown, Figure 9This is a comparison diagram of undirected and directed path graphs provided by this invention. For a more intuitive representation, in... Figure 9 In this invention, two paths with different directions are presented using red dashed lines, but in fact, the positions of these two red dashed lines are the same, both located in the middle of the black solid line.

[0089] The number of directed path points obtained after the transformation is calculated as follows, where n is the number of path points in the undirected graph, and m is the number of turning points. For the set of turning points, The number of vertices (i.e., points on a directed path) in a directed graph:

[0090] ;

[0091] Through this part of the processing, the present invention generates a directed graph for inspection, which avoids the situation where the inspection robot damages the equipment when turning in narrow places. Based on this directed graph, subsequent path planning and other operations can be realized.

[0092] (3) On the directed inspection graph, the directed path point that is closest to each inspection point and whose direction is within the same preset interval is used as the mapping point. The inspection points in this invention are pre-planned and include the inspection starting point. The specific setting method is as follows:

[0093] The locations of the inspection points are fixed and unchanging. In the early stages, staff manually remotely control the inspection robot to the appropriate position and adjust the angle according to the requirements of the equipment recognition task. The coordinates of the inspection robot and the angle value of its direction are recorded at this time (the angle range is [-90°, 270°)) as the parameters of the inspection point.

[0094] The ultimate goal of this invention is to achieve path planning between inspection points. However, the locations of the inspection points are not consistent with the locations of the directed path points generated above. Therefore, this invention needs to store the inspection starting point of the inspection robot and the location information of all other inspection points in a set P. The structure of set P is shown below, where... Let r be the location of the inspection starting point (which can be a charging station), and r be the number of other inspection points.

[0095]

[0096] Due to the limitations of the A* algorithm, which can only plan directed path points in the aforementioned directed graph, to plan inspection points, this invention needs to find the corresponding mapping point of each inspection point in the directed graph. Then, the planning of inspection points can be achieved by planning the mapping points. The method for determining the mapping point of any inspection point in the inspection directed graph includes, but is not limited to, the following steps:

[0097] Step a: Calculate the distance between any inspection point and each directed path point on the inspection directed graph, and determine the directed path point that is closest to any inspection point.

[0098] The distance can be Euclidean distance.

[0099] Step b: Determine a directed path point from the nearest directed path point that is in the same preset interval as the direction of any inspection point, and use it as the mapping point of any inspection point.

[0100] The preset interval is [-90°, 90°) or [90°, 270°), where [-90°, 90°) represents the positive X-axis interval and [90°, 270°) represents the negative X-axis interval.

[0101] For example, if the direction of the inspection point is 110°, the directions of the two closest directed path points determined in step a are 30° and 210°, respectively. Since the directions of the inspection point 110° and 210° are both in the negative X-axis region, the directed path point with the direction of 210° is determined as the mapping point of the inspection point.

[0102] One possible method for determining this is as follows:

[0103] Subtract 90° from the direction of the inspection point. If the result is greater than 0, select the directed path point with the direction between [90, 270) as the mapping point. If the result is less than 0, select the directed path point with the direction between [-90, 90) as the mapping point.

[0104] Store the mapping points obtained above in the corresponding point set. The structure is as follows, where, It can be a mapping point corresponding to the location of the charging pile (inspection starting point). r Number of other inspection points:

[0105]

[0106] Using the generated corresponding point set The overall planning idea for the sub-invention can be derived as follows, where, let... and If there are two inspection points to be planned, then and These are the directed path points (i.e., mapping points) corresponding to the two inspection points:

[0107]

[0108] (4) By analyzing the topological relationship between the mapping points, the inspection point ranking of all inspection points of the inspection robot is determined.

[0109] Optionally, the mapping point corresponding to the inspection start point is taken as the starting point, and path planning is performed with the mapping points corresponding to other inspection points whose sorting is not determined, so as to determine the next inspection point with the shortest path; the mapping point corresponding to the next inspection point with the shortest path is taken as the starting point, and path planning is performed with the mapping points corresponding to other inspection points whose sorting is not determined, so as to determine the next inspection point with the shortest path, and so on, until the sorting of all inspection points is completed.

[0110] Since the inspection points are fixed, this invention can predetermine the inspection order of all inspection points using a greedy optimization algorithm. This avoids the hassle of reordering the inspection points for each subsequent inspection task, greatly saving inspection time. The specific sorting method is as follows:

[0111] charging piles First add it to the sorting queue Q, then from the charging station Initially, using the planning approach mentioned in (3), path planning is performed with all other inspection points. The specific steps of path planning are as follows: For two inspection points and First in the corresponding set Find the corresponding directed path points in each. and Then, in the set of directed path points in the directed graph. Find these two path points and use the A* algorithm to plan the shortest path. Compare all planned paths, select the shortest path and store it in a two-dimensional array Array, and add the inspection point corresponding to the shortest path to the sorted queue Q. Repeat this process until all inspection points are in Q, and the sorted queue Q is the final sorted list of inspection points.

[0112] It is particularly important to note that because the inspection points in this invention are directional, the directional requirements must be taken into account when planning the route. Figure 10 This is a schematic diagram of directional path planning provided by the present invention, such as... Figure 10 As shown, if there is no direction requirement, the inspection sequence is ①→②→③→④→⑤. However, if there is a direction requirement, the inspection sequence becomes ①→④→⑤→③→②. The red arrows represent the path. At this time, the inspection point closest to inspection point 1 becomes inspection point 4.

[0113] (5) In response to the current inspection task issued, the inspection order of the points to be inspected included in the current inspection task is determined according to the inspection point sorting, and the path planning of the current inspection task is realized by using the inspection directed graph.

[0114] Optionally, the inspection order of the points to be inspected in the current inspection task is determined according to their relative positions in the inspection point sorting. Based on the inspection order of the points to be inspected, the inspection order of the corresponding mapping points is determined. The path point closest to the current position of the inspection robot is taken as the starting point, and the shortest path between each pair of adjacent mapping points is determined according to the inspection order of the mapping points, so as to realize the path planning of the current inspection task.

[0115] Figure 11 This is a logical block diagram of the path planning for the current inspection task provided by the present invention, such as... Figure 11 As shown, the specific processing approach is as follows:

[0116] According to the user's instructions, obtain all the points to be inspected in the current inspection task and the current position and orientation of the inspection robot (which can be a quadruped inspection robot) (as the inspection starting point). Find the corresponding mapping point in the vertex set of the directed graph based on the current position and orientation; for all the points to be inspected in the current task, sort them according to the sorted queue Q obtained in (4) to obtain an ordered queue of points to be inspected. .exist Find each corresponding mapping point, and then, starting from the mapping point corresponding to the current position, proceed according to... The order in the queue is used to perform path planning between two points one by one using the A* algorithm, and finally the planned path is obtained.

[0117] Of course, this invention can also directly add the nearest path point to The queue will be used directly for subsequent path planning, which will not be elaborated on here.

[0118] (6) Implement automatic door opening and closing in the planning.

[0119] In the inspection path, there will be doors. In order to ensure the safety of the inspection robot (which can be a quadruped inspection robot) and the smooth completion of the inspection task, this invention realizes that the inspection robot can automatically identify doors and complete the opening and closing actions. Figure 12 This is a schematic diagram of the danger zone formed by the rotation of the door, as provided by the present invention. Figure 12 As shown, the present invention pre-stores the door's position information and radius. A circle is drawn with the door hinge as the vertex and the door's radius as the circle. This area is the danger zone, and no path points can be set within the danger zone. Figure 13 This is a schematic diagram of opening and closing doors during the inspection process provided by the present invention, as shown below. Figure 13 As shown, the inspection robot must send instructions to open or close the door outside this danger zone.

[0120] Optionally, the process of entering the door is as follows: the inspection robot is controlled to stop moving forward before entering the danger zone, and after the door is confirmed to be open, the inspection robot is controlled to pass through the danger zone and enter the door; the process of exiting the door is as follows: after the inspection robot is confirmed to have left the danger zone, a door closing command is sent.

[0121] Additionally, in scenarios where the inspection area is a substation, rodent barriers are also present. These barriers can be installed on doors and can move up and down along the door frame. Specifically, during path planning, if a door is encountered, the robot stops before entering the danger zone and sends a command to move the rodent barrier to a fixed position, simultaneously issuing an open door command. Once the inspection robot detects that the door is fully open, it passes through the door. Upon leaving the danger zone, it stops and sends a command to move the rodent barrier down to the bottom, simultaneously issuing a close door command. After the door closes, it continues moving forward. This ensures that the inspection robot can pass through doors smoothly and safely.

[0122] (7) Fast planning strategy: If the shortest path between adjacent mapping points has been predetermined, the predetermined shortest path is directly adopted; if the shortest path between adjacent mapping points has not been predetermined, the shortest path is generated by using a preset path optimization algorithm.

[0123] In the actual planning process, this invention introduces the concept of reuse, because in the queue of items to be inspected... There might be adjacent inspection points that are also adjacent in the two-dimensional array, meaning the path between the two inspection points has already been generated. To handle this situation, for the planning of these two points, this invention can directly copy the corresponding path from the two-dimensional array. For other inspection points, normal path planning can be performed, such as... Figure 14 As shown, Figure 14 This is a schematic diagram illustrating the application of the reuse concept in the path planning provided by this invention.

[0124] The following is a brief explanation of the operation process of the inspection robot.

[0125] Figure 15 This is a preliminary workflow diagram provided by the present invention, such as... Figure 15 As shown, the robot proceeds to the inspection scene, scans with radar to generate a SLAM map, and uploads it to the cloud server database. The map undergoes a series of processing steps to obtain an undirected graph. The inspection robot then marks the points and uploads the obtained inspection point information to the cloud server database. Finally, the generated turning points and waypoints (i.e., patrol points) are uploaded to the cloud server database for storage.

[0126] Figure 16 This is the overall operation flowchart provided by the present invention, such as... Figure 16As shown, the user sends an inspection request to the server via a specific IP address and port. After receiving the command, the server sends a request to the robot dog (a quadruped inspection robot) to obtain its current location. The server combines the user's request and the quadruped inspection robot's current location, reads information from the cloud service database, and performs path planning. The planned path is returned to the client, and the planned path instructions are also sent to the quadruped inspection robot. After receiving the instructions, the quadruped inspection robot executes the task step by step.

[0127] In summary, the path planning method for inspection robots provided by this invention has the following advantages:

[0128] (1) This invention proposes the concept of turning point (intersection point), which allows the inspection robot to turn only at the intersection point during planning, thus avoiding damage to the equipment and the inspection robot itself caused by turning in narrow places.

[0129] (2) This invention provides a method for automatically generating path points based on turning points, which solves the problems of low efficiency and low accuracy of traditional manual marking, and can generate path points with different densities by changing variables.

[0130] (3) In order to meet the requirements of inspection, the present invention proposes a new criterion for converting undirected graphs into directed graphs.

[0131] (4) To solve the problem that A* cannot be used directly to plan between two inspection points, this invention proposes a new planning approach. By finding the correct directed path points (mapping points) corresponding to the inspection points and planning between the path points, the planning of inspection points can be indirectly achieved.

[0132] (5) In the traditional path planning, the planning of each inspection point requires calculation with all remaining points to find the shortest path, with a time complexity of O(n). To improve planning efficiency, this invention proposes pre-sorting all inspection points. Subsequent inspection tasks can then be sorted before path planning, thus reducing time complexity from... It dropped to .

[0133] (6) In order to achieve smooth inspection, the present invention sets instructions to enable the inspection robot to automatically open and close the door.

[0134] (7) To further improve planning efficiency, the present invention utilizes the idea of ​​reuse, and under certain circumstances, the previously stored shortest path can be directly copied.

[0135] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to execute the path planning method of the inspection robot provided in the above embodiments.

[0136] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the path planning method for the inspection robot provided in the above embodiments.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A path planning method for an inspection robot, characterized in that, include: Obtain the skeleton map of the inspection area, determine the turning points of the inspection robot on the skeleton map, and divide the skeleton map into multiple segments based on the turning points; If the length of any interval is greater than the preset length, set path points at preset intervals starting from one endpoint of the interval to complete the setting of path points for the interval. Traverse all intervals to construct an undirected inspection graph based on all path points. With the goal of ensuring that the inspection robot only turns at turning points during the inspection process, the undirected inspection graph is transformed into a directed inspection graph. On the directed graph of the inspection, the directed path point that is closest to each inspection point and whose direction is in the same preset interval is used as the mapping point. By analyzing the topological relationship between the mapping points, the inspection point ranking of all inspection points of the inspection robot is determined. The inspection points are pre-planned and include the inspection starting point. In response to the issued current inspection task, the inspection order of the points to be inspected in the current inspection task is determined according to the inspection point sorting, and the path planning of the current inspection task is realized by using the inspection directed graph. Specifically, with the goal of ensuring that the inspection robot only turns at turning points during the inspection process, the undirected inspection graph is transformed into a directed inspection graph, which includes: Starting from a path point at one end of any interval in the undirected graph, traverse all path points sequentially to calculate the direction angle of each path point. Specifically, the calculation of the direction angle of each path point is divided into two cases: Case 1: Calculate the direction angle of each path point from the starting point to the second-to-last path point. Specifically, determine the line connecting the currently traversed path point and the next path point to be traversed, and take the angle between the connecting line and the positive direction of the horizontal coordinate axis as the direction angle of the currently traversed path point; wherein the range of the angle is [-90°, 90°). The second case: find the direction angle of the last traversed path point, specifically: take the direction angle of the second to last traversed path point as the direction angle of the last traversed path point. Based on the position and orientation angle of any path point in the undirected inspection graph, generate two directed path points in the directed inspection graph corresponding to any path point; wherein, the positions of the two corresponding directed path points are the same as the position of any path point, the orientation of one of the two directed path points is the orientation angle of any path point, and the orientation of the other directed path point is the orientation angle of any path point plus 180 degrees. For any interval, if there are two adjacent directed path points, and the directions of the two adjacent directed path points are both in the range of [-90°, 90°), add an edge between the two adjacent directed path points, with the edge pointing towards the positive half-axis of the horizontal coordinate axis; if the directions of the two adjacent directed path points are both in the range of [90°, 270°), add an edge between the two adjacent directed path points, with the edge pointing towards the negative half-axis of the horizontal coordinate axis. Specifically, by analyzing the topological relationships between mapping points, the inspection point ranking of all inspection points of the inspection robot is determined, including: Using the mapping point corresponding to the inspection start point as the starting point, perform path planning with the mapping points corresponding to other inspection points whose order is not determined, in order to determine the next inspection point with the shortest path; Starting from the mapping point corresponding to the next inspection point with the shortest path, perform path planning with the mapping points corresponding to the inspection points whose sorting is not yet determined, and determine the next inspection point with the shortest path. Continue in this manner until all inspection points are sorted.

2. The path planning method for the inspection robot according to claim 1, characterized in that, Obtain the skeleton map of the inspection area, including: The SLAM map of the inspection area is converted into a binary black and white image. The largest connected region of the white part in the black and white image is determined to generate a safe area map. The largest connected region of the white part is the feasible area of ​​the inspection robot. Extract the skeleton map from the safe zone map.

3. The path planning method for the inspection robot according to claim 1, characterized in that, Determine the turning points of the inspection robot on the skeleton map, including: Draw a circle with any pixel on the skeleton map as the center and a first preset number of pixels as the radius, and count the number of white boundary pixels of the circle. If the number of white boundary pixels is greater than the second preset number, any of the aforementioned pixels will be used as a turning point. Iterate through all the pixels on the skeleton map to determine all turning points of the inspection robot on the skeleton map.

4. The path planning method for the inspection robot according to claim 1, characterized in that, Methods for determining the mapping point of any inspection point on the directed inspection graph include: Calculate the distance between any inspection point and each directed path point on the inspection directed graph, and determine the directed path point that is closest to any inspection point; From the nearest directed path points, determine the directed path points whose direction is in the same preset interval as any of the inspection points, and use them as the mapping points of any of the inspection points; wherein, the preset interval is [-90°, 90°) or [90°, 270°); The direction of any of the inspection points is pre-planned and set.

5. The path planning method for the inspection robot according to claim 4, characterized in that, Based on the inspection point sorting, the inspection order of the points to be inspected in the current inspection task is determined, and the path planning for the current inspection task is implemented using the directed inspection graph, including: Based on the relative position of the point to be inspected in the sorting of the inspection points, determine the inspection order of the points to be inspected in the current inspection task, and based on the inspection order of the points to be inspected, determine the inspection order of the corresponding mapping points. Starting from the path point closest to the current position of the inspection robot, the shortest path between each pair of adjacent mapping points is determined according to the inspection order of the mapping points, so as to realize the path planning of the current inspection task.

6. The path planning method for the inspection robot according to claim 1, characterized in that, In path planning where there are entrances and exits, it also includes: Entry process: Control the inspection robot to stop moving forward before entering the danger zone. After confirming that the door has been opened, control the inspection robot to pass through the danger zone and enter the door. Exit process: Once it is confirmed that the inspection robot has left the danger zone, a door-closing command is sent; The danger zone is determined based on the door's location and rotation radius, and no waypoints are set within the danger zone.

7. The path planning method for the inspection robot according to claim 5, characterized in that, Determine the shortest path between each pair of adjacent mapping points, including: If the shortest path between adjacent mapping points has been predetermined, the predetermined shortest path is used directly. If the shortest path between adjacent mapping points is not predetermined, a pre-defined path optimization algorithm is used to generate the shortest path.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the path planning method for the inspection robot as described in any one of claims 1 to 7.

Images