Path planning method and device for photovoltaic unmanned cleaning vehicle and storage medium

Abstract

The invention relates to the technical field of path planning, and particularly discloses a path planning method and device for a photovoltaic unmanned cleaning vehicle and a storage medium, and the method comprises the steps: analyzing a preset grid map of a photovoltaic panel region; performing off-line path planning on the photovoltaic panel area based on an off-line path search algorithm to obtain an off-line path planning preliminary result, an evaluation function of the off-line path search algorithm at least comprising a heuristic function and a path cost function, the heuristic function being a cost function determined based on target point heuristic value information of each cleaning operation target point, and the path cost function being a cost function determined based on target point heuristic value information of each cleaning operation target point; the path cost function is a cost function determined based on kinematic characteristics and path movement consumption of the photovoltaic unmanned cleaning vehicle; and optimizing the offline path planning preliminary result according to a preset tracking rule of the photovoltaic unmanned cleaning vehicle. According to the path planning method for the photovoltaic unmanned cleaning vehicle, the cleaning effect can be improved while the path planning capability of the photovoltaic unmanned cleaning vehicle is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of path planning technology, and in particular to a path planning method for a photovoltaic unmanned cleaning vehicle, a path planning device for a photovoltaic unmanned cleaning vehicle, and a storage medium. Background Art

[0002] Photovoltaic power generation is a key source of clean energy. However, dust on the surface of photovoltaic panels significantly impacts their power generation efficiency, making panel cleaning a pressing issue. In the context of industrial automation, unmanned vehicles (AVs) offer a fast and effective solution for cleaning PV panels. The large size of PV farms, the unstructured nature of their routes, and the non-unique layout of PV panels make manually collecting AV routes challenging and time-consuming. Therefore, automated path planning is essential to ensure effective cleaning. Unlike conventional autonomous vehicle path planning, PV panels present both obstacles and the cleaning vehicle's workspace. This requires path planning to address both obstacle avoidance and obstacle traversal, ensuring the optimal path as much as possible. Existing AV path planning relies on perception and positioning technologies. Online, real-time computation requires expensive sensors and powerful hardware. This approach can amplify errors in various steps, resulting in incomplete cleaning of PV panels and blind spots. Furthermore, its focus is on finding the optimal (usually the shortest) collision-free path, lacking obstacle traversal, which does not meet the requirements of PV panel cleaning.

[0003] Several path planning methods have been proposed for photovoltaic panel cleaning. For example, a path planning method for an intelligent photovoltaic array cleaning robot divides the photovoltaic array into a two-dimensional index array. The method determines the starting point based on the distribution of cleaned and uncleaned portions of the photovoltaic array and plans a bow-shaped path. Road points, fence points, and parking spots in the scene are connected to form an undirected graph. The Dijkstra algorithm is then used to calculate the shortest path from the robot's current point to the starting point. However, this method's drawback is that it imposes a fixed connection order and defines the cleaning path as a bow, making it difficult to cover the entire area of a large photovoltaic field. Furthermore, the undirected graph must be constructed based on scene points, and its accuracy must be verified. This method requires manual definition and does not support automatic path planning for the entire photovoltaic field. Another path navigation system for photovoltaic cleaning robots includes multiple modules, including perception, positioning, path planning, obstacle avoidance, and control. It integrates numerous sensors, including cameras, lidar, infrared, and meteorological sensors. Through online real-time computing, it enables fully automated driving, completing photovoltaic cleaning tasks and dispatching cleaning vehicles. The drawback of this approach is that the perception, positioning, and obstacle avoidance modules of the full-process autonomous cleaning process rely heavily on information from multiple sensors. Furthermore, the real-time nature of online computing requires powerful computer hardware, resulting in high equipment costs. Furthermore, this approach focuses on system design and does not provide specific operational logic for the path planning module specifically for photovoltaic scenarios.

[0004] Therefore, how to propose a solution that can effectively improve the path planning capability of photovoltaic unmanned cleaning vehicles while improving the cleaning effect in photovoltaic unmanned cleaning scenarios, such as unstructured multi-objective path planning, relatively fixed maps, non-unique photovoltaic panel arrangement, large working area, and real-time cleaning blind spots, has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the Invention

[0005] The present invention provides a path planning method for a photovoltaic unmanned cleaning vehicle, a path planning device for a photovoltaic unmanned cleaning vehicle, and a storage medium, which solve the problem of lack of path planning for cleaning vehicles for photovoltaic unmanned cleaning scenarios in related technologies.

[0006] As a first aspect of the present invention, a path planning method for a photovoltaic unmanned cleaning vehicle is provided, which includes:

[0007] Analyzing a preset grid map of the photovoltaic panel area to determine cleaning operation target points, wherein each cleaning operation target point is configured with at least target point coordinate location information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence;

[0008] Determine the starting and ending points of the photovoltaic panel area according to the preset path planning task, and perform offline path planning on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, and obtain a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption;

[0009] The offline path planning preliminary result is optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0010] Furthermore, the preset grid map of the photovoltaic panel area is analyzed, including:

[0011] Performing a traversal search on the preset grid map according to a graph search algorithm to locate positions of all photovoltaic panels in the photovoltaic panel area;

[0012] Determining boundary line information of each photovoltaic panel based on the position of each photovoltaic panel and in combination with the direction information of the preset grid map, wherein the boundary line information of each photovoltaic panel at least includes a boundary line on one side along the length direction of the photovoltaic panel;

[0013] Multiple cleaning operation target points corresponding to each photovoltaic panel are determined based on the boundary line information of each photovoltaic panel and the preset interval distance.

[0014] Furthermore, multiple cleaning target points corresponding to each photovoltaic panel are determined based on the boundary line information of each photovoltaic panel and the preset interval distance, including:

[0015] The preset interval distance is determined based on the body size of the current photovoltaic unmanned cleaning vehicle and the preset cleaning range of the cleaning part;

[0016] The positions of multiple cleaning operation target points of each photovoltaic panel are determined according to the boundary line information of each photovoltaic panel and the preset interval distance.

[0017] Furthermore, the starting and ending points of the photovoltaic panel area are determined according to the preset path planning task, and offline path planning is performed on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, and a preliminary offline path planning result is obtained, including:

[0018] Determine the starting point for the unmanned photovoltaic cleaning vehicle to enter the photovoltaic panel area and the end point for leaving the photovoltaic panel area according to the preset path planning task;

[0019] Determining an evaluation function of the offline path search algorithm based on a target point heuristic value of each cleaning operation target point, kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and path movement consumption;

[0020] Performing offline path planning for the photovoltaic panel area according to the offline path search algorithm, target point coordinate position information, target point access status information, and target point cleaning status information;

[0021] Determine whether the access ratio of the current cleaning operation target point reaches the preset ratio threshold;

[0022] If the access ratio of the current cleaning operation target point reaches the preset ratio threshold, the search is stopped and the preliminary result of offline path planning is obtained.

[0023] Furthermore, the evaluation function of the offline path search algorithm is determined according to the target point heuristic value of each cleaning operation target point, the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and the path movement consumption, including:

[0024] The heuristic cost function is determined based on the target point heuristic value of each cleaning operation target point and the distance between the current grid point of the photovoltaic unmanned cleaning vehicle and the cleaning operation target point;

[0025] Determining a path length cost, a turning cost, and a reversing cost according to the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and determining a path cost function based on the path length cost, the turning cost, and the reversing cost;

[0026] An evaluation function of an offline path search algorithm is determined according to the heuristic cost function and the path cost function.

[0027] Furthermore, offline path planning is performed on the photovoltaic panel area according to the offline path search algorithm, the target point coordinate position information, the target point access status information, and the target point cleaning status information, including:

[0028] Accessing cleaning operation target points within the photovoltaic panel area according to the offline path search algorithm;

[0029] Each time a grid occupied by a cleaning operation target point is passed, the target point access status information and the target point cleaning status information of the grid are updated, and the access ratio of the current cleaning operation target point is counted based on the target point access status information.

[0030] Furthermore, the offline path planning preliminary result is optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle, including:

[0031] Determine the preset tracking rules for the photovoltaic unmanned cleaning vehicle based on its curvature limit, uniformity of curvature change, uniformity of spacing, and probability of collision;

[0032] Identifying abnormal cleaning operation target points based on the offline path planning results according to the preset tracking rules;

[0033] The offline path after eliminating abnormal cleaning operation target points is optimized to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0034] Furthermore, the offline path after eliminating abnormal cleaning operation target points is optimized, including:

[0035] The offline path after removing abnormal cleaning operation target points is smoothed according to the gradient descent method to increase the smoothness;

[0036] The offline path with increased smoothness is densified using the polynomial interpolation method to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0037] As another aspect of the present invention, a path planning device for a photovoltaic unmanned cleaning vehicle is provided, which is used to implement the path planning method for a photovoltaic unmanned cleaning vehicle described above, wherein the path planning device for a photovoltaic unmanned cleaning vehicle includes:

[0038] A grid map analysis module is used to analyze a preset grid map of the photovoltaic panel area to determine the target points for cleaning operations, wherein each cleaning operation target point is configured with at least target point coordinate position information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence;

[0039] A multi-objective traversal path planning module is used to determine the starting and ending points of the photovoltaic panel area according to the preset path planning task, and perform offline path planning on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, thereby obtaining a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, wherein the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption;

[0040] The path post-processing module is used to optimize the offline path planning preliminary result according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0041] As another aspect of the present invention, a storage medium is provided, which is used to store computer instructions. When the computer instructions are loaded and executed by a processor, the path planning method for a photovoltaic unmanned cleaning vehicle described above is implemented.

[0042] The path planning method for a photovoltaic unmanned cleaning vehicle provided by the present invention analyzes a preset grid map, traverses and extracts map information, and redefines the grid information of multiple target points; and constructs a cost function based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, the path movement consumption, and the target point heuristic value. Then, offline path planning of offline multi-target traversal is performed based on the results of offline path planning analysis performed in combination with an offline path search algorithm, thereby realizing automatic multi-target traversal path planning for the entire photovoltaic power plant scene. The path planning method for a photovoltaic unmanned cleaning vehicle is based on a preset grid map and is performed offline, without losing real-time performance, thereby reducing cumulative errors and overcoming cleaning blind spots, thereby effectively improving the path planning capability of the photovoltaic unmanned cleaning vehicle and improving the cleaning effect at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present invention, but do not constitute a limitation of the present invention.

[0044] Figure 1 This is a flow chart of the path planning method for a photovoltaic unmanned cleaning vehicle provided by the present invention.

[0045] Figure 2 This is a flow chart for analyzing a preset grid map of a photovoltaic panel area provided by the present invention.

[0046] Figure 3 A top view of the photovoltaic panel area with the distance between the target point and the edge provided by the present invention.

[0047] Figure 4 This is a flowchart of obtaining preliminary results of offline path planning provided by the present invention.

[0048] Figure 5a This is a schematic diagram of node expansion of the traditional A* algorithm provided by the present invention.

[0049] Figure 5b This is a schematic diagram of the node expansion of the Hybrid-A* algorithm provided by the present invention.

[0050] Figure 6 Schematic diagram of the Hybrid-A* subnode definition method provided by the present invention.

[0051] Figure 7 This is a schematic diagram of blind spot generation provided by the present invention.

[0052] Figure 8 This is a flowchart of optimizing the preliminary results of offline path planning provided by the present invention.

[0053] Figure 9 This is a structural block diagram of the path planning device for a photovoltaic unmanned cleaning vehicle provided by the present invention.

[0054] Figure 10 This is a structural block diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0055] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0056] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0057] It should be noted that the terms "first," "second," and the like in the specification and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the embodiments of the present invention described herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0058] In this embodiment, a path planning method for a photovoltaic unmanned cleaning vehicle is provided. Figure 1 FIG. 1 is a flow chart of a path planning method for a photovoltaic unmanned cleaning vehicle according to an embodiment of the present invention. Figure 1 As shown, including:

[0059] S100, analyzing a preset grid map of the photovoltaic panel area to determine cleaning operation target points, wherein each cleaning operation target point is configured with at least target point coordinate position information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence;

[0060] In the embodiment of the present invention, each photovoltaic power plant can form its own grid map, so the preset grid map of the photovoltaic power plant can be directly imported and analyzed.

[0061] Specifically, in an embodiment of the present invention, the preset grid map can be traversed by the Dijkstra graph search algorithm, and all photovoltaic panels can be identified based on the shape and area of the obstacles. The boundary line of the photovoltaic panel (the reference edge line of the photovoltaic unmanned cleaning vehicle) is then identified based on the map direction and the photovoltaic panel position information. The boundary line of the photovoltaic panel is spaced at a certain distance, and the same number of target points are defined along the boundary line of the photovoltaic panel. The grids occupied by the target points are defined with fixed heuristic values, visit flags (all initialized to not visited) and cleaning work flags (all initialized to not cleaned).

[0062] S200, determining the starting and ending points of the photovoltaic panel area according to a preset path planning task, and performing offline path planning on the photovoltaic panel area based on an offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, thereby obtaining a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, wherein the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption;

[0063] In an embodiment of the present invention, after defining the starting and ending points of the task, an offline path search is performed using the Hybrid-A* algorithm that takes into account the grid heuristic value, the kinematic characteristics of the cleaning vehicle, and the path movement cost. During the search process, the target points that have been visited and cleaned (the planned path passes through) are recorded. The cleaning task end point can only be visited when the target point visit ratio reaches the predetermined requirement.

[0064] S300: Optimize the offline path planning preliminary result according to the preset tracking rule of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0065] In an embodiment of the present invention, the preliminary offline path planning results obtained above can be optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle for the points such as curvature and spacing that do not meet the unmanned vehicle tracking requirements, and finally form a path that can be directly provided to the unmanned vehicle for tracking.

[0066] Therefore, the path planning method for photovoltaic unmanned cleaning vehicles provided by the present invention analyzes the preset grid map, traverses and extracts map information, and redefines the grid information of multiple target points; and constructs a cost function based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, the path movement consumption, and the target point heuristic value, and then combines the offline path search algorithm to perform offline path planning analysis and perform offline multi-target traversal offline path planning, thereby realizing multi-target traversal automatic path planning for the entire scene of the photovoltaic power plant. The path planning method for photovoltaic unmanned cleaning vehicles is based on the preset grid map and is performed offline, and does not need to be real-time, so it can reduce the cumulative error and overcome the cleaning blind spot, thereby effectively improving the path planning capability of the photovoltaic unmanned cleaning vehicle and at the same time improving the cleaning effect.

[0067] As a specific embodiment of the present invention, the preset grid map of the photovoltaic panel area is analyzed, such as Figure 2 As shown, including:

[0068] S110, performing a traversal search on the preset grid map according to a graph search algorithm to locate positions of all photovoltaic panels in the photovoltaic panel area;

[0069] In an embodiment of the present invention, specifically for a known photovoltaic field grid map, all obstacles in the grid map can be screened according to the length, width range and layout of the actual photovoltaic panels through the Dijkstra graph search algorithm, and all photovoltaic panels can be located, that is, the position coordinate information of the grid map occupied by each photovoltaic panel can be determined.

[0070] S120, determining boundary line information of each photovoltaic panel based on the position of each photovoltaic panel and in combination with the direction information of the preset grid map, wherein the boundary line information of each photovoltaic panel includes at least a boundary line on one side along the length direction of the photovoltaic panel;

[0071] In the embodiment of the present invention, after determining the position of each photovoltaic panel, the boundary line information of each photovoltaic panel can be determined based on the direction of the preset grid map. Specifically, most photovoltaic panels are oriented southward to better receive sunlight, so it can be combined with Figure 3 As can be seen from the top view of the photovoltaic panels shown, the south boundary line of each photovoltaic panel is determined, which can not only facilitate the cleaning operation of the cleaning vehicle, but also reduce the cleaning blind area and improve the cleaning efficiency.

[0072] More specifically, multiple cleaning target points corresponding to each photovoltaic panel are determined based on the boundary line information of each photovoltaic panel and the preset interval distance, including:

[0073] 1) Determine the preset interval distance based on the current body size of the photovoltaic unmanned cleaning vehicle and the preset cleaning range of the cleaning part;

[0074] 2) Determining the positions of multiple cleaning operation target points of each photovoltaic panel based on the boundary line information of each photovoltaic panel and the preset interval distance.

[0075] In the embodiment of the present invention, based on the position of each located photovoltaic panel and the map direction, a target point with the same number of grid cells is defined along the south edge at a distance K on one side of the south edge. The distance K(x) (x represents the number of grid cells) is defined as follows:

[0076] K(x)=F(x)+G(x),

[0077] Among them, F(x) is defined according to the length, width and height of the unmanned cleaning vehicle, and G(x) is defined according to the cleaning range of the unmanned cleaning vehicle's cleaning part (mechanical arm, nozzle, etc.). Therefore, the rationality of the definition of K(x) determines the cleaning effect of each photovoltaic panel and the blind area processing effect. In the embodiment of the present invention, the schematic diagram of the distance K definition is as follows Figure 3 shown.

[0078] S130 , determining a plurality of cleaning operation target points corresponding to each photovoltaic panel according to the boundary line information of each photovoltaic panel and the preset interval distance.

[0079] It should be understood that after determining the target point grid, a heuristic constant C, a visit flag FLAG, and a cleaning flag CLEAN are added to all target point grids. The heuristic value C is associated with the heuristics of the Hybrid-A* algorithm, the visit flag FLAG is associated with target point management, and the cleaning flag CLEAN is associated with the cleaning behavior of the unmanned cleaning vehicle.

[0080] Therefore, in an embodiment of the present invention, a grid map is traversed using the Dijkstra graph search algorithm, and all photovoltaic panels are identified based on their shape, area, and layout. The south edge of the photovoltaic panel is then identified based on the map direction and panel location information. Target points of the same number of grids are defined along the south edge at a certain distance south of the south edge of the photovoltaic panel. The grids occupied by the target points are defined with fixed heuristic values, access flags (visited and unvisited), and cleaning work flags. The heuristic values are used to guide the search of the subsequent path planning algorithm, the access flags are used to update the traversal information of the target points, and the cleaning work flags are used by the cleaning module to clean the photovoltaic panels.

[0081] As a specific embodiment of the present invention, the starting and ending points of the photovoltaic panel area are determined according to the preset path planning task, and offline path planning is performed on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target point reaches the preset ratio threshold, and the preliminary offline path planning results are obtained, such as Figure 4 As shown, including:

[0082] S210, determining a starting point for the unmanned photovoltaic cleaning vehicle to enter the photovoltaic panel area and an end point for the unmanned photovoltaic cleaning vehicle to leave the photovoltaic panel area according to a preset path planning task;

[0083] In the embodiment of the present invention, the starting and ending points of the task can be determined according to the preset path planning task, for example, Figure 3 As shown, the upper right corner can be used as the starting point of the task, and the lower left corner can be used as the end point of the task. The specific starting and ending points can be set as needed and are not limited here.

[0084] S220, determining an evaluation function of the offline path search algorithm according to the target point heuristic value of each cleaning operation target point, the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and the path movement consumption;

[0085] In an embodiment of the present invention, a heuristic cost function can be determined in combination with the target point heuristic value of each cleaning operation target point, and a path cost function can be determined according to the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption. The evaluation function of the offline path search algorithm is determined based on the heuristic cost function and the path cost function.

[0086] Specifically, the evaluation function of the offline path search algorithm is determined according to the target point heuristic value of each cleaning operation target point, the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and the path movement consumption, including:

[0087] 1) Determine the heuristic cost function based on the target point heuristic value of each cleaning operation target point and the distance between the current grid point of the photovoltaic unmanned cleaning vehicle and the cleaning operation target point;

[0088] It should be understood that the closer the setting of the heuristic function is to reality, the more efficient the path search will be. Since the heuristics in the prior art only use Euclidean distance (the straight-line distance between two points) or Manhattan distance (the sum of the absolute wheelbases of two points in the coordinate system) as heuristic functions, and do not take into account the obstruction of obstacles, they cannot play a good role in guiding path search in photovoltaic scenarios where a large number of photovoltaic panels are arranged in an orderly manner. Based on this, the embodiment of the present invention designs a heuristic based on the actual distance between the current grid point and the target point (cleaning point or task end point) taking into account the obstacles, and at the same time adds the target point heuristic value constant C in the grid map redefinition module to ensure that the search is prioritized towards the customized target point. Specifically, the heuristic function expression is as follows:

[0089] h(s)=d(s)+C,

[0090] Where d(s) represents the actual distance between the current grid position and the target point, which can be obtained by methods such as Dijkstra or RRT*. C represents the heuristic value of the target point, which is usually a constant. The optimal value of this constant can be determined based on experiments.

[0091] 2) determining a path length cost, a turning cost, and a reversing cost according to the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and determining a path cost function based on the path length cost, the turning cost, and the reversing cost;

[0092] In this embodiment of the present invention, the path cost function g(s) is used to evaluate the actual cost of moving from one grid to another. To make the planned path more consistent with actual photovoltaic cleaning scenarios and avoid energy consumption caused by meaningless turns and reversing, the path cost function takes into account the path length cost, turning costs, and reversing costs. The specific calculation formula is as follows:

[0093] g now =g parent +k1×g turn +k2×g back ,

[0094] Among them, g now Indicates the cost of the current target point, g parent Indicates the cost of the parent node of the current target point, g turn represents the turning cost, g back represents the reversing cost, k1 and k2 represent corresponding coefficients, which can be obtained from experiments.

[0095] In the embodiment of the present invention, the definition of sub-nodes can be specifically understood as follows: the traditional A* path search algorithm expands sub-nodes in eight directions, can only access fixed positions in the grid and does not consider the vehicle kinematic parameters, and the calculated path cannot be used directly. The Hybrid-A* algorithm takes into account the minimum turning radius and front wheel angle of the vehicle, and can achieve access to any position in the grid. The generated path can meet the vehicle kinematic requirements. The node expansion of the traditional A* algorithm is as follows: Figure 5a As shown, the node expansion of the Hybrid-A* algorithm of the embodiment of the present invention is as follows Figure 5b shown.

[0096] In each search step, the position of the child node is determined by the vehicle's minimum turning radius R and the discrete number of front wheel turning angles N. The larger N is, the more child node positions can be accessed and the smoother the path. The child node position definition method is as follows: Figure 6 Therefore, the path cost function in the embodiment of the present invention takes into account the path length cost, the cost of turning and reversing, and can adapt to different cleaning vehicles and cover various layouts of photovoltaic fields, thus expanding the applicable scenarios.

[0097] 3) Determining an evaluation function of an offline path search algorithm based on the heuristic cost function and the path cost function.

[0098] In summary, the offline path search algorithm Hybrid-A* according to the embodiment of the present invention is based on the evaluation function f(s)=g(s)+h(s) when searching in a grid map.

[0099] S230, performing offline path planning for the photovoltaic panel area according to the offline path search algorithm, target point coordinate position information, target point access status information, and target point cleaning status information;

[0100] In an embodiment of the present invention, offline path planning is performed based on the offline path search algorithm determined above, and the status of the target point is updated according to the target point access status information and the target point cleaning status information, so as to determine whether the access ratio is reached to end the path planning.

[0101] Specifically, offline path planning is performed on the photovoltaic panel area according to the offline path search algorithm, target point coordinate position information, target point access status information, and target point cleaning status information, including:

[0102] 1) accessing cleaning operation target points within the photovoltaic panel area according to the offline path search algorithm;

[0103] 2) Each time a grid occupied by a cleaning operation target point is passed, the target point access status information and the target point cleaning status information of the grid are updated, and the access ratio of the current cleaning operation target point is counted based on the target point access status information.

[0104] S240, determining whether the access ratio of the current cleaning operation target point reaches a preset ratio threshold;

[0105] S250: If the access ratio of the current cleaning operation target point reaches a preset ratio threshold, stop searching and obtain a preliminary result of offline path planning.

[0106] It should be understood that if the access ratio of the current cleaning operation target point does not reach the preset ratio threshold, the search will continue until the preset ratio threshold is reached.

[0107] Specifically, in an embodiment of the present invention, when a path search begins, a TargetPoint set and a VisitedPoint set are created. The initial number of TargetPoints is M (M is the number of grids occupied by target points). Each time the Hybrid-A*-planned path passes through a grid occupied by a target point, the grid's visit flag is updated to "visited" and the target point heuristic value is cleared. At the same time, the grid is moved from the TargetPoint set to the VisitedPoint set. After this, the target point grid is completely consistent with the idle grid except for the cleaning work flag, and can be passed freely. Considering that it is impossible to complete the cleaning of photovoltaic panels with the same accuracy as the grid map in practice, when the target point grid visit ratio reaches a custom P, the cleaning is considered complete, and a path can be planned from the current point to the task endpoint.

[0108] Therefore, in this embodiment of the present invention, since the PV power plant grid map is known and the cleaning vehicle workshop directly tracks the path, the Hybrid-A* path planning process can be performed offline. When replacing a cleaning vehicle with different parameters or changing the PV panel layout, it is only necessary to reset the path planning algorithm parameters and re-run offline planning. This method of the embodiment of the present invention adapts to changes in the vehicle and the actual environment while ensuring that the cleaning effect is not affected.

[0109] In addition, compared with online path planning that relies on perception positioning and sensors, the method of the embodiment of the present invention has a smaller cumulative error, the lateral distance change between the cleaning vehicle and the photovoltaic panel is more stable, and it is less likely to cause cleaning blind spots. The prior art that relies on perception positioning easily leads to the existence of upper blind spots or lower blind spots, for example Figure 7 As shown, the method of the embodiment of the present invention sets the south boundary line and determines the target point at a distance K from the south boundary line, so the cumulative error is smaller, and it is less likely to produce a cleaning blind spot.

[0110] In the embodiment of the present invention, the offline path planning preliminary result is optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle, such as Figure 8 As shown, including:

[0111] S310, determining a preset tracking rule for the photovoltaic unmanned cleaning vehicle based on the curvature limit, uniformity of curvature change, uniformity of spacing, and probability of collision of the photovoltaic unmanned cleaning vehicle;

[0112] S320, identifying abnormal cleaning operation target points of the offline path planning result according to the preset tracking rules;

[0113] S330: Optimize the offline path after removing abnormal cleaning operation target points to obtain a path planning result for the photovoltaic unmanned cleaning vehicle.

[0114] Specifically, the offline path after eliminating abnormal cleaning operation target points is optimized, including:

[0115] The offline path after removing abnormal cleaning operation target points is smoothed according to the gradient descent method to increase the smoothness;

[0116] The offline path with increased smoothness is densified using the polynomial interpolation method to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0117] It should be understood that the points in the offline path planning preliminary results generated by the above algorithm where the curvature exceeds the vehicle's minimum turning radius limit, the curvature changes unevenly, the spacing is uneven, and collisions may occur are screened, and the gradient descent method is used to optimize the path to increase the smoothness. Considering that the unmanned cleaning vehicle does not have high requirements for ride comfort, cubic polynomial interpolation is used for densification to obtain a smooth, dense, and uniform path.

[0118] Finally, actual vehicle testing can be conducted on the unmanned cleaning vehicle to verify whether it can successfully track and complete the cleaning behavior according to the cleaning marks to meet the photovoltaic panel cleaning requirements.

[0119] In summary, the path planning method for photovoltaic unmanned cleaning vehicles provided by the embodiment of the present invention uses a two-dimensional grid map for offline path planning. By extracting grid map information and redefining the grid information, the working target point of the unmanned cleaning vehicle is successfully located, avoiding manual labeling and topological path definition. This process can be effectively implemented based on existing grid map processing technology. In addition, in view of the characteristics of photovoltaic panels as both obstacles and cleaning objects, the embodiment of the present invention adopts a multi-target traversal offline path planning method to achieve the traversal of the planned path to the photovoltaic panels, while avoiding the cumulative error of multi-module online calculations that leads to large cleaning blind spots. The heuristic function is defined by the actual distance from the current point to the target point and the custom heuristic value to achieve efficient path search. In addition, the path planning method for photovoltaic unmanned cleaning vehicles provided by the present invention fully considers the influence of photovoltaic panel layout and vehicle parameters, improves the Hybrid-A* path planning algorithm, and only needs to modify some parameters to achieve adaptation to different vehicles and photovoltaic field layouts.

[0120] As another embodiment of the present invention, a path planning device for a photovoltaic unmanned cleaning vehicle is provided, which is used to implement the path planning method for a photovoltaic unmanned cleaning vehicle described above, wherein: Figure 9 As shown, the path planning device 10 for the photovoltaic unmanned cleaning vehicle includes:

[0121] A grid map analysis module 100 is configured to analyze a preset grid map of the photovoltaic panel area to determine cleaning operation target points, wherein each cleaning operation target point is configured with at least target point coordinate position information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence;

[0122] The multi-objective traversal path planning module 200 is used to determine the starting and ending points of the photovoltaic panel area according to the preset path planning task, and perform offline path planning on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, thereby obtaining a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, wherein the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption;

[0123] The path post-processing module 300 is used to optimize the offline path planning preliminary result according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

[0124] The path planning device for a photovoltaic unmanned cleaning vehicle provided by the present invention analyzes a preset grid map, traverses and extracts map information, and redefines the grid information of multiple target points; and constructs a cost function based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, the path movement consumption, and the target point heuristic value, and then combines the offline path search algorithm to perform offline path planning analysis and perform offline multi-target traversal offline path planning, thereby realizing multi-target traversal automatic path planning for the entire photovoltaic power plant scene. The path planning device for a photovoltaic unmanned cleaning vehicle is based on a preset grid map and is performed offline, without losing real-time performance, thereby reducing cumulative errors and overcoming cleaning blind spots, thereby effectively improving the path planning capability of the photovoltaic unmanned cleaning vehicle and at the same time improving the cleaning effect.

[0125] In an embodiment of the present invention, the Dijkstra graph search algorithm is specifically used to traverse the grid map to obtain photovoltaic panel and obstacle information as well as map direction. The photovoltaic panel edge is determined based on the traversal results and a series of target points are defined. Then, information is added to the target points for subsequent path planning. Based on the map analysis results and cleaning task instructions, a multi-target point management strategy is adopted, and Hybrid-A* offline path planning is performed in combination with vehicle kinematic parameters, costs and heuristic information, taking into account both cleaning and obstacle avoidance. Based on the path planning results, points whose curvature, spacing, etc. do not meet the unmanned vehicle tracking requirements are screened, and the path is optimized using interpolation and gradient descent methods to generate path information that can be directly tracked by the unmanned vehicle.

[0126] In this embodiment, the mature Dijkstra graph search algorithm is used to traverse a two-dimensional grid map, filtering and redefining map information, eliminating the need for tedious manual topological map construction. Multiple target points are set based on the geometric information of the photovoltaic panels, making this method simple, easy to obtain, and highly accurate. The input information is simply the established grid map, eliminating the need for multi-module autonomous driving strategies such as perception and positioning. High-performance computer hardware and expensive sensors are not required, significantly reducing errors and costs. Furthermore, the system utilizes multiple target points and their preset information to traverse the photovoltaic panels. The unmanned vehicle cleaning sequence is not fixed. Based on the Hybrid-A* method, which takes vehicle parameters into account, the system can adapt to different cleaning vehicles and cover various photovoltaic field layouts, expanding its applicability. The initial path is screened and optimized for anomalies to ensure that the generated path can be directly used by the unmanned vehicle, streamlining the process and improving performance. The entire process is performed offline, using the two-dimensional grid map as input, without real-time requirements. The system features clear logic, few steps, and minimal cumulative error. The lateral distance between the vehicle and the photovoltaic panel is relatively stable, effectively overcoming cleaning blind spots.

[0127] As another embodiment of the present invention, a storage medium is provided, which is used to store computer instructions. When the computer instructions are loaded and executed by a processor, the path planning method for a photovoltaic unmanned cleaning vehicle described above is implemented.

[0128] In an embodiment of the present invention, a non-transitory computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions can execute the path planning method for a photovoltaic unmanned cleaning vehicle in any of the above-mentioned method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the storage medium can also include a combination of the above-mentioned types of memory.

[0129] As another embodiment of the present invention, an electronic device is provided, which includes a memory and a processor, the memory and the processor are communicatively connected, the memory is used to store computer instructions, and the processor is used to load and execute the computer instructions to implement the path planning method for a photovoltaic unmanned cleaning vehicle as described above.

[0130] like Figure 10As shown, the electronic device 90 may include: at least one processor 91, such as a CPU (Central Processing Unit), at least one communication interface 93, a memory 94, and at least one communication bus 92. The communication bus 92 is used to realize the connection and communication between these components. The communication interface 93 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 93 may also include a standard wired interface and a wireless interface. The memory 94 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 94 may optionally be at least one storage device located away from the aforementioned processor 91. The memory 94 stores application programs, and the processor 91 calls the program code stored in the memory 94 to execute any of the above method steps.

[0131] The communication bus 92 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 92 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0132] Among them, the memory 93 may include a volatile memory (English: volatile memory), such as a random-access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 94 may also include a combination of the above types of memory.

[0133] The processor 91 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0134] The processor 91 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0135] Optionally, the memory 94 is also used to store program instructions. The processor 91 can call the program instructions to implement the present invention. Figure 1 The path planning method for a photovoltaic unmanned cleaning vehicle shown in the embodiment.

[0136] It will be understood that the above embodiments are merely exemplary embodiments for illustrating the principles of the present invention, and the present invention is not limited thereto. Those skilled in the art will appreciate that various modifications and improvements can be made without departing from the spirit and substance of the present invention, and such modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A path planning method for a photovoltaic unmanned cleaning vehicle, characterized in that: include: Analyzing a preset grid map of the photovoltaic panel area to determine cleaning operation target points, wherein each cleaning operation target point is configured with at least target point coordinate location information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence; Determine the starting and ending points of the photovoltaic panel area according to the preset path planning task, and perform offline path planning on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, and obtain a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption; The offline path planning preliminary result is optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

2. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 1, characterized in that: Analyze the preset grid map of the photovoltaic panel area, including: Performing a traversal search on the preset grid map according to a graph search algorithm to locate positions of all photovoltaic panels in the photovoltaic panel area; Determining boundary line information of each photovoltaic panel based on the position of each photovoltaic panel and in combination with the direction information of the preset grid map, wherein the boundary line information of each photovoltaic panel at least includes a boundary line on one side along the length direction of the photovoltaic panel; Multiple cleaning operation target points corresponding to each photovoltaic panel are determined based on the boundary line information of each photovoltaic panel and the preset interval distance.

3. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 2, characterized in that: Based on the boundary information and preset interval distance of each photovoltaic panel, multiple cleaning target points corresponding to each photovoltaic panel are determined, including: The preset interval distance is determined based on the body size of the current photovoltaic unmanned cleaning vehicle and the preset cleaning range of the cleaning part; The positions of multiple cleaning operation target points of each photovoltaic panel are determined according to the boundary line information of each photovoltaic panel and the preset interval distance.

4. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 1, characterized in that: The starting and ending points of the photovoltaic panel area are determined according to the preset path planning task, and offline path planning is performed on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, and the preliminary offline path planning results are obtained, including: Determine the starting point for the unmanned photovoltaic cleaning vehicle to enter the photovoltaic panel area and the end point for leaving the photovoltaic panel area according to the preset path planning task; Determining an evaluation function of the offline path search algorithm based on a target point heuristic value of each cleaning operation target point, kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and path movement consumption; Performing offline path planning for the photovoltaic panel area according to the offline path search algorithm, target point coordinate position information, target point access status information, and target point cleaning status information; Determine whether the access ratio of the current cleaning operation target point reaches the preset ratio threshold; If the access ratio of the current cleaning operation target point reaches the preset ratio threshold, the search is stopped and the preliminary result of offline path planning is obtained.

5. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 4, characterized in that: The evaluation function of the offline path search algorithm is determined according to the target point heuristic value of each cleaning operation target point, the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and the path movement consumption, including: The heuristic cost function is determined based on the target point heuristic value of each cleaning operation target point and the distance between the current grid point of the photovoltaic unmanned cleaning vehicle and the cleaning operation target point; Determining a path length cost, a turning cost, and a reversing cost according to the kinematic characteristics of the photovoltaic unmanned cleaning vehicle, and determining a path cost function based on the path length cost, the turning cost, and the reversing cost; An evaluation function of an offline path search algorithm is determined according to the heuristic cost function and the path cost function.

6. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 4, characterized in that: Performing offline path planning on the photovoltaic panel area according to the offline path search algorithm, target point coordinate position information, target point access status information, and target point cleaning status information includes: Accessing cleaning operation target points within the photovoltaic panel area according to the offline path search algorithm; Each time a grid occupied by a cleaning operation target point is passed, the target point access status information and the target point cleaning status information of the grid are updated, and the access ratio of the current cleaning operation target point is counted based on the target point access status information.

7. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 1, characterized in that: The offline path planning preliminary results are optimized according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle, including: Determine the preset tracking rules for the photovoltaic unmanned cleaning vehicle based on its curvature limit, uniformity of curvature change, uniformity of spacing, and probability of collision; Identifying abnormal cleaning operation target points based on the offline path planning results according to the preset tracking rules; The offline path after eliminating abnormal cleaning operation target points is optimized to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

8. The path planning method for a photovoltaic unmanned cleaning vehicle according to claim 7, characterized in that: Optimize the offline path after eliminating abnormal cleaning operation target points, including: The offline path after removing abnormal cleaning operation target points is smoothed according to the gradient descent method to increase the smoothness; The offline path with increased smoothness is densified using the polynomial interpolation method to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

9. A path planning device for a photovoltaic unmanned cleaning vehicle, used to implement the path planning method for a photovoltaic unmanned cleaning vehicle according to any one of claims 1 to 8, characterized in that: The path planning device for the photovoltaic unmanned cleaning vehicle includes: A grid map analysis module is used to analyze a preset grid map of the photovoltaic panel area to determine the target points for cleaning operations, wherein each cleaning operation target point is configured with at least target point coordinate position information, target point access status information, target point cleaning status information, and target point heuristic value information for guiding the cleaning sequence; A multi-objective traversal path planning module is used to determine the starting and ending points of the photovoltaic panel area according to the preset path planning task, and perform offline path planning on the photovoltaic panel area based on the offline path search algorithm until the access ratio of the cleaning operation target points reaches a preset ratio threshold, thereby obtaining a preliminary offline path planning result, wherein the evaluation function of the offline path search algorithm includes at least a heuristic function and a path cost function, wherein the heuristic function is a cost function determined based on the target point heuristic value information of each cleaning operation target point, and the path cost function is a cost function determined based on the kinematic characteristics of the photovoltaic unmanned cleaning vehicle and the path movement consumption; The path post-processing module is used to optimize the offline path planning preliminary result according to the preset tracking rules of the photovoltaic unmanned cleaning vehicle to obtain the path planning result of the photovoltaic unmanned cleaning vehicle.

10. A storage medium, characterized in that: Used to store computer instructions, when the computer instructions are loaded and executed by a processor to implement the path planning method for a photovoltaic unmanned cleaning vehicle as described in any one of claims 1 to 8.

Images