AGV path planning method and device, storage medium and computer equipment

Abstract

The embodiment of the invention discloses an AGV path planning method and device, a storage medium and computer equipment, and relates to the field of logistics automation. The method comprises the following steps: establishing a two-dimensional map according to an active area of the AGV; determining position coordinates of a starting point of the AGV in the two-dimensional map and position coordinates of n target points, wherein n is an integer greater than 1; sorting the n target points to obtain a first target point to an nth target point; planning an optimal sub-path from the starting point to the first target point, an optimal sub-path from the first target point to the second target point,..., an optimal sub-path from the (n-1) th target point to the nth target point, and generating a target path according to the planned n sub-paths; and indicating the AGV to move according to the target path. According to the technical scheme of the invention, through the steps of accurate modeling, intelligent sorting, global path planning, efficient execution and the like, optimal path planning of the AGV in a multi-target-point scene is realized.

Description

Technical Field

[0001] The present application relates to the field of logistics automation, and in particular to an AGV path planning method, device, storage medium and computer equipment. Background Art

[0002] AGV, the official name of Automated Guided Vehicle, is a type of unmanned automated vehicle that integrates cutting-edge automatic guidance technologies such as magnetic strips, tracks or lasers. This type of vehicle strictly follows a pre-planned and finely optimized driving path, uses batteries as a clean energy source, and not only has efficient autonomous mobility capabilities, but is also equipped with a full range of safety protection systems and a variety of auxiliary mechanisms, such as cargo transfer and precision assembly machinery, to meet complex and changing operational needs. In the current field of logistics automation, research on efficient and intelligent path planning for AGVs between a single starting point and multiple target points has become a hot topic in the industry. Summary of the invention

[0003] The embodiments of the present application provide an AGV path planning method, device, storage medium and computer equipment, which can solve the problem of low accuracy of long-term prediction results of offline training models in the prior art. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides an AGV path planning method, the method comprising:

[0005] Create a two-dimensional map based on the AGV's activity area;

[0006] Determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map, where n is an integer greater than 1;

[0007] Sort the n target points to obtain the first target point to the nth target point;

[0008] According to the sorting results, the optimal subpath between the starting point and the first target point, the optimal subpath between the first target point and the second target point, ..., the optimal subpath between the n-1th target point and the nth target point are planned, and the target path is generated according to the planned n subpaths;

[0009] Instruct the AGV to move according to the target path.

[0010] In a second aspect, an embodiment of the present application provides an AGV path planning device, the device comprising:

[0011] A building unit, used to build a two-dimensional map according to the activity area of ​​AGV;

[0012] A determination unit, used to determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map, where n is an integer greater than 1;

[0013] A sorting unit, used for sorting n target points to obtain the first target point to the nth target point;

[0014] A planning unit, used to plan, according to the sorting result, an optimal subpath between the starting point and the first target point, an optimal subpath between the first target point and the second target point, ..., an optimal subpath between the n-1th target point and the nth target point, and generate a target path according to the planned n subpaths;

[0015] The control unit is used to instruct the AGV to move according to the target path.

[0016] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0017] In a fourth aspect, an embodiment of the present application provides a computer device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0018] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0019] By accurately establishing a two-dimensional map and determining the specific coordinates of the AGV starting point and n target points, a solid foundation is laid for subsequent path planning. This coordinate-based precise positioning method ensures the accuracy and reliability of path planning. The rational sorting of n target points aims to reduce the moving distance or time of the AGV according to a certain optimization criterion, thereby improving the overall work efficiency and significantly improving the work efficiency. The segmented planning strategy is adopted to decompose the complex overall path planning problem into the optimal sub-path planning problem between multiple starting points and adjacent target points. This method not only simplifies the calculation process, but also facilitates local adjustment and optimization of a single sub-path according to actual conditions, ensuring the optimality of the overall path. Based on the above sorting and sub-path planning results, each sub-path is seamlessly connected to generate a complete target path. This step ensures that the AGV can complete the mobile task efficiently and accurately according to the established route, reducing errors or delays caused by improper path planning. The entire technical solution realizes a fully automated process from map establishment, coordinate positioning, target point sorting to path planning and execution, significantly reducing the need for manual intervention and improving the automation and intelligence level of production operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a schematic diagram of the network architecture provided by the embodiment of the present application;

[0022] Figure 2 It is a flowchart of the AGV path planning method provided in the embodiment of the present application;

[0023] Figure 3 It is a structural schematic diagram of an AGV path planning device provided by the present application;

[0024] Figure 4 It is a structural schematic diagram of a computer device provided by this application. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0026] It should be noted that the AGV path planning method provided in the present application is generally executed by a computer device, and accordingly, the AGV path planning device is generally set in the computer device.

[0027] Figure 1 An exemplary system architecture that can be applied to the AGV path planning method or AGV path planning device of the present application is shown.

[0028] like Figure 1 As shown, the system architecture may include: a computer device 101 and an AGV 102. The computer device 101 and the AGV 102 may communicate through a network, and the network is used as a medium for providing communication links between the above-mentioned units. The network may include various types of wired communication links or wireless communication links, for example: a wired communication link includes an optical fiber, a twisted pair or a coaxial cable, etc., and a wireless communication link includes a Bluetooth communication link, a wireless fidelity (WIreless-FIdelity, Wi-Fi) communication link or a microwave communication link, etc.

[0029] Among them, AGV (Automated Guided Vehicle), also known as automatic guided transporter or automatic guided transporter, is an intelligent transport vehicle equipped with an automatic guidance device that can travel along a specified guidance route and realize various transfer functions.

[0030] The computer device may also be equipped with a display device and a camera. The display device may be any device capable of realizing a display function, and the camera is used to collect video streams; for example, the display device may be a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. The user may use the display device on the computer device to view displayed text, pictures, videos and other information.

[0031] It should be understood that Figure 1 The number of computer devices, networks and AGVs in the embodiment is only for illustration. According to the implementation requirements, any number of computer devices, networks and AGVs can be used.

[0032] The following will be combined with the attached Figure 2 , the AGV path planning method provided in the embodiment of the present application is described in detail. Among them, the AGV path planning device in the embodiment of the present application can be Figure 1 Computer equipment shown.

[0033] See also Figure 2 , which is a flow chart of an AGV path planning method according to an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps:

[0034] S201. Create a two-dimensional map based on the activity area of ​​the AGV.

[0035] Appropriate sensors, such as laser radar (LIDAR), ultrasonic sensors, cameras, etc., are arranged in the activity area of ​​AGV to collect environmental information. The sensors are activated to collect environmental data such as obstacle positions, walls, ground textures, road markings, etc. in the activity area. The data is usually in the form of point clouds, images, or distance measurements. Computer equipment denoises the collected raw data to remove outliers caused by sensor errors or environmental factors. The data from different sensors are integrated to form a consistent description of the environment.

[0036] Computer equipment selects appropriate map building algorithms, such as SLAM (Simultaneous Localization and Mapping) and Occupancy Grid Mapping, according to the complexity and accuracy requirements of the application scenario.

[0037] The computer equipment extracts key features from the preprocessed data, such as wall edges, obstacle outlines, etc. The position of the AGV in the environment is estimated in real time using sensor data and possible prior knowledge (such as GPS signals, initial position, etc.). Based on the results of position estimation and feature extraction, the two-dimensional map is continuously updated. In the occupancy grid map, this means assigning an occupancy probability to each grid, indicating the probability that the position is occupied by an obstacle. During the movement of the AGV, the steps of position estimation and map update are continuously repeated to improve the accuracy and completeness of the map.

[0038] The computer equipment uses filtering techniques (such as Gaussian filtering) to smooth the map to reduce noise and irregularities. Check the connectivity in the map to ensure that all traversable areas are connected to each other. Mark special areas on the map, such as charging stations, dangerous areas, and impassable areas.

[0039] The computer equipment verifies the accuracy and reliability of the map by letting the AGV move on the map. Based on the results of the field verification, the map is adjusted and optimized as necessary to improve its performance in actual applications. The final constructed two-dimensional map is stored in the storage medium of the computer equipment for subsequent path planning and navigation. If necessary, the map can also be shared with other systems or devices to achieve multi-AGV collaborative operation or remote monitoring.

[0040] In some embodiments of the present application, a computer uses a grid method to establish a two-dimensional map according to the activity area of ​​the AGV. The specific establishment process includes:

[0041] According to the actual size of the AGV, motion characteristic parameters (such as rotation radius, driving speed, etc.) and the accuracy requirements of the map, determine the actual distance represented by each grid (such as 1 meter, 0.5 meter, etc.). The selection of grid size should ensure that the AGV can complete the necessary turns and movements within a single grid. According to the range of the AGV's activity area, set the total size of the two-dimensional map (such as length x width, in units of grid numbers or actual distance). This helps ensure that the map can fully cover the AGV's activity area and reserve enough buffer for it.

[0042] According to the map size and grid size, create a two-dimensional array (or matrix) to represent the grid map. Each element of the array corresponds to a grid on the map, and its value is used to indicate the state of the grid (such as free grid, barrier grid, etc.).

[0043] Initialize all grids in the map to an unknown state (such as represented by a specific value), and then set the corresponding grid to an obstacle grid or a free grid according to the actual environment information (such as obstacle location, road layout, etc.). This is usually achieved by reading map data files, sensor data, or user input.

[0044] According to the actual position and shape of the obstacles in the environment, the corresponding obstacle areas are drawn on the grid map. This usually involves mapping the outline of the obstacles onto the grid map and marking the grids occupied by the obstacles as obstacle grids. The road areas where the AGV can travel are planned on the grid map. This usually involves connecting the free grids to form a feasible path network so that the AGV can navigate and move along these paths.

[0045] The raster map is optimized to improve its accuracy and practicality. For example, jagged edges in the map can be reduced by smoothing; the complexity of the map can be reduced by merging adjacent free grids, etc. The generated raster map is verified and tested to ensure its accuracy and reliability. This usually involves simulating the AGV's driving process on the map to check whether it can correctly identify obstacles, plan paths, and avoid potential risk areas.

[0046] The generated raster map is saved to the storage medium of the computer device for subsequent path planning and navigation. As the environment of the AGV activity area changes (such as new obstacles, road changes, etc.), the raster map needs to be updated regularly to reflect the latest environmental information, which usually involves re-collecting environmental data, redrawing the map and replacing the old map file.

[0047] S202: Determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map.

[0048] Among them, a unified coordinate system is defined on a two-dimensional map, usually selecting the lower left corner of the map or a fixed point as the origin (0, 0), with the X axis horizontally pointing to the right and the Y axis vertically pointing upward. The computer device allows the operator to manually input the position coordinates of the starting point through a human-computer interaction interface. The operator selects or inputs the corresponding X and Y coordinate values ​​on the interface according to the actual position on the map.

[0049] If the two-dimensional map contains specific identifiers (such as QR codes, RFID tags, etc.), the computer device can automatically determine the location coordinates of the starting point by identifying these identifiers. The recognition process usually involves technologies such as image processing and pattern recognition.

[0050] Verify the entered or automatically identified starting point location coordinates to ensure they are accurate and, if necessary, make minor adjustments to ensure they match the actual location.

[0051] The number of target points n (n>1) is determined, and each target point is uniquely identified on the two-dimensional map, such as by numbering, color marking, etc. For each target point, the process of determining the position coordinates of the starting point is repeated. That is, its position coordinates can be determined by manual input, automatic recognition, or a combination of the two.

[0052] The computer device records the location coordinates of each target point in the computer device's memory, usually in the form of a list, array or database. Ensure that each coordinate value is associated with the corresponding target point identifier. Check the location coordinates of all target points to ensure that there are no omissions or errors. If necessary, make corrections based on actual conditions.

[0053] It should be noted that when determining the position coordinates, the uniformity and accuracy of the coordinate system should be ensured to avoid errors in subsequent path planning. For large or complex AGV activity areas, more advanced map processing technologies (such as multi-scale maps, layered maps, etc.) may be required to improve the accuracy and efficiency of the position coordinates. In practical applications, the position coordinates can also be integrated with the AGV's real-time positioning system to achieve more dynamic and flexible path planning.

[0054] In some embodiments of the present application, the computer device identifies the position coordinates of the starting point and n target points according to the two-dimensional code contained in the two-dimensional map, and the specific process is as follows:

[0055] The computer device first obtains a two-dimensional map image containing a QR code. This can be achieved by photographing with a camera, reading from a file system, or transmitting over a network. The obtained map image is preprocessed, including denoising, grayscale, binarization, and other operations to improve the accuracy and efficiency of QR code recognition.

[0056] Use a QR code detection algorithm (such as edge detection, corner detection, or template matching) to locate the QR code in the preprocessed image. Extract the bounding box of the QR code to prepare for subsequent decoding.

[0057] Decode the located QR code and parse out the information it contains. This information is usually stored in text form and may include the location coordinates of the starting point and the target point, identifiers, or other related information.

[0058] The position coordinates of the starting point and n target points are extracted from the decoded QR code information. These coordinates may be expressed in different formats (such as pixel coordinates, relative coordinates on a map, or actual geographic coordinates).

[0059] If the extracted coordinates are not directly available coordinates on the map (such as pixel coordinates), coordinate conversion is required. For example, convert pixel coordinates to relative coordinates on the map or coordinates in a geographic coordinate system (such as UTM, WGS-84, etc.).

[0060] Match the converted coordinates with the actual locations on the two-dimensional map and mark the locations of the starting point and n target points on the map. This can be achieved by drawing points, circles, rectangles or other graphic markers on the map.

[0061] S203, sorting the n target points to obtain the first target point to the nth target point.

[0062] Among them, the computer device specifies the sorting criteria, which can be distance (straight-line distance or path length from the starting point to the target point), time (estimated arrival time), cost (such as energy consumption, wear, etc.), priority (priority order set according to business needs) or other custom evaluation indicators. According to the selected sorting criteria, the sorting basis value of each target point relative to the starting point is calculated. For example, if distance is selected as the sorting criterion, the distance from the starting point to each target point needs to be calculated. According to the characteristics of the sorting basis and actual needs, select a suitable sorting algorithm. For a small-scale set of target points, a simple sorting algorithm (such as bubble sort, selection sort) can be used for sorting. For large-scale or efficient sorting scenarios, it is recommended to use a more efficient sorting algorithm, such as quick sort, merge sort or heap sort. Use the selected sorting algorithm to sort the target points. During the sorting process, the target points are rearranged into an ordered list according to the size (or order) of the sorting basis value.

[0063] If there are multiple target points with the same sorting basis value (such as equal distance), they need to be further sorted according to additional rules (such as node number, position, etc.) to ensure the uniqueness and certainty of the sorting result. Verify the sorting result to ensure the correctness and rationality of the sorting. If necessary, the sorting result can be fine-tuned according to the actual situation. Output the sorted target point list for subsequent path planning steps. The first element in the list is the first target point, the second element is the second target point, and so on, until the nth target point.

[0064] In practical applications, it is also possible to consider introducing heuristic information or constraints to optimize the sorting process. For example, if it is known that there are physical obstacles or traffic restrictions between certain target points, these factors can be taken into account when sorting to avoid planning infeasible paths. Through the above steps, the computer device can systematically sort the n target points and provide an ordered list of target points for subsequent path planning.

[0065] In some embodiments of the present application, the computer device uses an artificial potential field method to sort the n target points. The specific sorting method includes:

[0066] According to the methodology of artificial potential field, the calculation formula for determining the arrangement order of n target points is: Where T represents the sorted set of Togo target points, t represents the number of target points. After the planning is completed, each target point will no longer participate in the subsequent calculation. s(x, y) represents the shortest distance between two locations. U t Represents the total force field.

[0067] A gravitational field is assigned to each target point. The strength of the gravitational field is inversely proportional to the distance from the target point to the current position (such as the starting point or the current position of the AGV), that is, the closer the distance, the greater the gravitational force. If there are obstacles in the environment, a repulsive field needs to be set for each obstacle. The strength of the repulsive field is inversely proportional to the distance from the obstacle to the current position, but there is usually a maximum influence range, beyond which the repulsion is zero. For each target point, the potential field value of each point on the path from the starting point (or the current position of the AGV) to the target point is calculated, which involves superimposing the gravitational field and the repulsive field to obtain the total potential field value. For each target point, the difficulty of reaching the node is evaluated based on the potential field value on its path. This is achieved by calculating the total potential field value of the path (that is, the sum or weighted average of the potential field values ​​of all points on the path). The path quality can also be comprehensively evaluated based on factors such as the smoothness of the path, the density of obstacles, and the length of the path. According to the evaluated path quality (or just the path length), the n target points are sorted. The destination point with the best path quality (or the shortest path) is ranked first, the second best is ranked second, and so on, until the nth destination point.

[0068] Further, the computer device estimates the path cost from the starting point to the target point for each target point. This can be achieved in a variety of ways, such as using the A* algorithm or other path planning algorithms to find and evaluate the path. For each target point, the A* algorithm (or other applicable algorithm) is used to find the shortest path from the starting point to the target point, and the total cost of the path (such as distance, time, energy consumption, etc.) is recorded. In the path planning process, obstacles are taken into account and the path cost is adjusted accordingly or a repulsion term is introduced. For each point on the path, if it is close to an obstacle, the repulsion value of the point is increased (this can be a fixed value, or a value that varies based on the distance from the obstacle). However, in this sorting task, we may only care about the total cost of the path, rather than the specific repulsion value of each point on the path. Since we are mainly concerned with gravity (i.e., path cost), we can regard the path cost of each target point as its "total potential field value". For each target point, its total potential field value is the total cost of the shortest path from the starting point to the target point. According to the calculated total potential field value (i.e., path cost), the n target points are sorted in ascending order. This way, the destination with the lowest path cost (or the "easiest to reach") will be ranked first.

[0069] S204. According to the sorting results, plan the optimal subpath between the starting point and the first target point, the optimal subpath between the first target point and the second target point, ..., the optimal subpath between the n-1th target point and the nth target point, and generate a target path according to the planned n subpaths.

[0070] Among them, for the sorted target point list, use the path planning algorithm (such as Dijkstra algorithm, bidirectional A* algorithm, etc.) to plan the optimal sub-path from the starting point to the first target point, and then plan the optimal sub-path between each adjacent target point in turn. Merge the planned n sub-paths into a complete target path in sequence. During the merging process, pay attention to processing the connection points between the sub-paths to ensure the continuity and feasibility of the entire path.

[0071] The following describes the process of the bidirectional A* algorithm:

[0072] Determine the starting point (S) and end point (G) of the path planning. Select a suitable heuristic function h(n) to estimate the cost from the current node n to the end point. Common heuristic functions include Manhattan distance, Euclidean distance, etc. Create two priority queues, one for forward search (OPEN_fore) starting from the starting point and the other for backward search (OPEN_back) starting from the end point. These two queues will sort the nodes according to the value of the evaluation function f(n) = g(n) + h(n) (i.e., the total cost estimate), where g(n) is the actual path cost from the starting point (or end point) to the current node n. Create two CLOSED sets (CLOSED_fore and CLOSED_back) to store nodes that have been evaluated to avoid repeated evaluation; at the same time, create two dictionaries (PARENT_fore and PARENT_back) to record the parent node of each node so that the complete path can be traced back in the end.

[0073] Add the starting point S to the OPEN_fore queue of the forward search and assign initial f, g, and h values; add the end point G to the OPEN_back queue of the backward search and assign corresponding initial values.

[0074] Circular search: Select the node with the smallest f value from OPEN_fore and OPEN_back respectively for expansion. For the currently expanded node, generate all its possible neighbor nodes. For each neighbor node, calculate its g, h and f values, and perform the following checks: If the neighbor node is already in the corresponding CLOSED set, ignore it. If the neighbor node is in the OPEN set in the other direction and the g value is smaller (indicating that a shorter path has been found), update its g, f values ​​and parent node information. Otherwise, add the neighbor node to the OPEN set in the corresponding direction, and set its parent node and g, f values. Add the currently expanded node to the corresponding CLOSED set.

[0075] Check intersection: Each time you expand a node, check whether there is a node that has been visited in both directions (that is, whether it exists in the intersection of the two CLOSED sets). If there is such an intersection node, it means that the path from the starting point to the end point has been found, and the search can be terminated.

[0076] Starting from the intersection node, use the information in the PARENT_fore and PARENT_back dictionaries to trace forward and backward respectively until you reach the starting point and the end point. Combine the path fragments obtained by tracing forward and backward to form a complete optimal subpath from the starting point to the end point.

[0077] The choice of heuristic function has a great impact on the performance of the algorithm. A heuristic function that can closely estimate the actual path cost should be selected. When implementing, attention should be paid to handling boundary conditions and abnormal situations, such as unreachable starting and end points, obstacles in the search space, etc. The bidirectional A algorithm can significantly reduce the number of nodes searched and improve search efficiency, especially in large graph search problems.

[0078] In some embodiments of the present application, the computer device uses the improved bidirectional A* algorithm to plan each optimal sub-path. The difference from the existing bidirectional A* algorithm is that the evaluation function f(n)=g(n)+h'(n), h'(n)=ln(Q g )·ln(Q s )·h(n),Q g is the traction coefficient, Q s is the target traction coefficient, and the calculation formula is as follows: Where: (x g ,y g ) is the end point coordinate, (x s ,y s ) is the starting point coordinate, (x node ,y node) is the current node coordinate. It should be noted that the starting point and the end point are different in different paths. For example, in the path between the starting point and the first target point, the starting point is the starting point and the first target point is the end point; between the first target point and the second target point, the starting point is the first target point and the end point is the second target point, and so on. The role of the traction coefficient is to make it more likely that the two-way search will meet in the middle. The target traction coefficient can adaptively converge the search speed and increase the overall search efficiency.

[0079] S205: Instruct the AGV to move according to the target path.

[0080] Among them, the computer equipment transmits the generated target path information (including the coordinates of key points on the path, steering instructions, etc.) to the AGV through wireless communication or other means. After receiving the path information, the AGV uses its own navigation system and control algorithm to move according to the target path. During the movement process, the AGV needs to perceive the changes in the surrounding environment in real time and make path adjustments or obstacle avoidance operations as needed. The computer equipment continuously monitors the movement status and location information of the AGV to ensure that the AGV can reach each target point accurately and safely.

[0081] In some embodiments of the present application, the computer device displays the optimal path from the starting point to the target node (usually referred to as the target path), and monitors the position information of the automatic guided vehicle (AVG) or any mobile robot in the two-dimensional map in real time. The following is the detailed implementation process of this step:

[0082] Ensure that the optimal path from the starting point to the target node has been calculated using an appropriate search algorithm (such as a bidirectional A* algorithm) in the previous step (such as S204). The path data should contain a series of points or coordinates that are connected in sequence to form a path. Render a two-dimensional map on the display screen of a computer device. This is usually achieved through a graphics library (such as OpenGL, DirectX, or simpler libraries such as PIL / Pillow, Matplotlib, etc.). Ensure that the resolution and scale of the map are suitable for display and contain all necessary obstacles, boundaries and other important information.

[0083] Draw a path to your goal on a two-dimensional map. This is usually done by drawing line segments (or more complex shapes, such as arrows) at each point on the path. You can use different colors or line styles to distinguish the path from other elements on the map.

[0084] The computer device needs to receive the location information sent by the AVG in real time, usually through wireless communication (such as Wi-Fi, Bluetooth, RFID, etc.) or wired connection. The location information should contain the current coordinates of the AVG (such as x, y coordinates) and possible additional information (such as direction, speed, etc.).

[0085] Maintains the current location information of AVG in the memory of the computer device. When new location information is received, the location data in the memory is updated.

[0086] Update the position of the AVG on the two-dimensional map in real time. This is usually achieved by drawing a graphic representing the AVG on the map (such as a car icon). Move the AVG icon to the coordinates corresponding to the received position information.

[0087] If desired, the current position of the AVG and its expected position on the target path (i.e., the next point or the nearest point on the path) can be displayed on the map at the same time. This helps the user or the system monitor whether the AVG is moving along the expected path.

[0088] The computer device of the present application is provided with an intuitive user interface so that the user can easily view the target path and the real-time location of the AVG. The user interface should include necessary controls such as zooming, panning the map, pausing / resume monitoring, etc. Additional information display areas can be added to display the status information of the AVG, the path length, the estimated time of arrival, etc. Through the above steps, the computer device can effectively display the target path and monitor the location information of the AVG in the two-dimensional map in real time.

[0089] The embodiments of the present application have the following beneficial effects when executing path planning:

[0090] By building a two-dimensional map and clarifying the precise location coordinates of the AGV's starting point and multiple target points, a solid foundation is provided for subsequent path planning. This precise modeling and positioning method ensures the accuracy and reliability of path planning.

[0091] The multi-target point problem is transformed into the classic traveling salesman problem (TSP), and the artificial potential field method is used to determine the optimal visit order between the target points. This step not only reduces the total length of the path, but also improves the operating efficiency of the AGV, avoiding unnecessary detours and waiting time. At the same time, the optimal sub-path between each pair of adjacent target points is planned through the improved bidirectional A* search algorithm, further refining the accuracy and efficiency of path planning.

[0092] After determining the optimal sequence of target point visits and the optimal sub-path between each pair of adjacent points, these sub-paths are seamlessly integrated to form a global optimal path from the starting point to the final target point. This global path planning method ensures the continuity and efficiency of the AGV throughout the entire task execution process.

[0093] Finally, by instructing the AGV to move along the planned target path, the multi-target point task was efficiently executed. In addition, the technical solution also has a certain degree of dynamic adaptability, which can cope with environmental changes or emergencies to a certain extent, ensuring that the AGV can complete the task safely and stably.

[0094] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0095] See also Figure 3 , which shows a schematic diagram of the structure of an AGV path planning device provided by an exemplary embodiment of the present application, hereinafter referred to as device 3. The device 3 can be implemented as all or part of a computer device through software, hardware, or a combination of both. The device 3 includes: an establishment unit 301, a determination unit 302, a sorting unit 303, a planning unit 304, and a control unit 305.

[0096] A building unit, used to build a two-dimensional map according to the activity area of ​​AGV;

[0097] A determination unit, used to determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map, where n is an integer greater than 1;

[0098] A sorting unit, used for sorting n target points to obtain the first target point to the nth target point;

[0099] A planning unit, used to plan, according to the sorting result, an optimal subpath between the starting point and the first target point, an optimal subpath between the first target point and the second target point, ..., an optimal subpath between the n-1th target point and the nth target point, and generate a target path according to the planned n subpaths;

[0100] The control unit is used to instruct the AGV to move according to the target path.

[0101] In one or more possible embodiments, each subpath is planned according to the improved bidirectional A* search algorithm, and the evaluation function used by the bidirectional A* algorithm is f(n)=g(n)+h'(n), h'(n)=ln(Q g )·ln(Q s )·h(n),Q gis the traction coefficient, Q s is the target traction coefficient, (x g ,y g ) is the end point coordinate, (x s ,y s ) is the starting point coordinate, (x node ,y node ) are the current node coordinates.

[0102] In one or more possible embodiments, establishing a two-dimensional map according to the activity area of ​​the AGV includes:

[0103] Determine the grid size according to the actual size, motion characteristic parameters and accuracy requirements of the AGV;

[0104] A two-dimensional map is created based on the grid size and the activity area of ​​the AGV.

[0105] In one or more possible embodiments, the n target points are sorted using an artificial potential field method.

[0106] In one or more possible embodiments, the sorting of the n target points by using an artificial potential field method includes:

[0107] For each target point, the gravitational field and repulsive field of each point on the path from the starting point to the target point are superimposed to obtain the total potential field value;

[0108] Arrange the n target points in ascending order according to the total potential field value.

[0109] In one or more possible embodiments, determining the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map includes:

[0110] The location coordinates of the starting point and n target points are identified according to the two-dimensional code contained in the two-dimensional map.

[0111] In one or more possible embodiments, it further includes:

[0112] The monitoring unit is used to display the target path and monitor the position information of the AVG in the two-dimensional map in real time.

[0113] It should be noted that when the device 3 provided in the above embodiment executes the AGV path planning method, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above functions. In addition, the AGV path planning device provided in the above embodiment and the AGV path planning method embodiment belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0114] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0115] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 2 The method steps of the embodiment shown in the figure can be found in the specific implementation process. Figure 2 The specific description of the illustrated embodiment will not be repeated here.

[0116] The present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the AGV path planning method of each of the above embodiments.

[0117] See also Figure 4 , which is a schematic diagram of the structure of a computer device according to an embodiment of the present application. Figure 4 As shown, the computer device 400 may include: at least one processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0118] The communication bus 402 is used to realize the connection and communication between these components.

[0119] The user interface 403 may include a display screen (Display) and a camera (Camera), and the optional user interface 403 may also include a standard wired interface and a wireless interface.

[0120] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0121] Among them, the processor 401 may include one or more processing cores. The processor 401 uses various interfaces and lines to connect various parts within the entire computer device 400, and executes various functions and processes data of the computer device 400 by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the processor 401 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 401 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 401, and it can be implemented separately through a chip.

[0122] Among them, the memory 405 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 405 may optionally be at least one storage device located away from the aforementioned processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program.

[0123] exist Figure 4In the computer device 400 shown in FIG. 1 , the user interface 403 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 401 can be used to call the application program stored in the memory 405 and specifically execute the following steps: Figure 2 The specific process can be referred to Figure 2 As shown, no further description is given here.

[0124] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0125] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. An AGV path planning method, characterized in that: include: Create a two-dimensional map based on the AGV's activity area; Determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map, where n is an integer greater than 1; Sort the n target points to obtain the first target point to the nth target point; According to the sorting results, the optimal subpath between the starting point and the first target point, the optimal subpath between the first target point and the second target point, ..., the optimal subpath between the n-1th target point and the nth target point are planned, and the target path is generated according to the planned n subpaths; Instruct the AGV to move according to the target path.

2. The method according to claim 1, characterized in that Each subpath is planned according to the improved bidirectional A* search algorithm. The evaluation function used by the bidirectional A* algorithm is f(n)=g(n)+h'(n), h'(n)=ln(Q g )·ln(Q s )·h(n),Q g is the traction coefficient, Q s is the target traction coefficient, (x g ,y g ) is the end point coordinate, (x s ,y s ) is the starting point coordinate, (x node ,y node ) are the current node coordinates.

3. The method according to claim 1 or 2, characterized in that The two-dimensional map is established according to the activity area of ​​the AGV, including: Determine the grid size according to the actual size, motion characteristic parameters and accuracy requirements of the AGV; A two-dimensional map is created based on the grid size and the activity area of ​​the AGV.

4. The method according to claim 3, characterized in that The n target points are sorted using an artificial potential field method.

5. The method according to claim 4, characterized in that The method of sorting the n target points by using the artificial potential field method includes: For each target point, the gravitational field and repulsive field of each point on the path from the starting point to the target point are superimposed to obtain the total potential field value; Arrange the n target points in ascending order according to the total potential field value.

6. The method according to claim 1 or 2 or 4 or 5, characterized in that Determining the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map includes: The location coordinates of the starting point and n target points are identified according to the two-dimensional code contained in the two-dimensional map.

7. The method according to claim 6, characterized in that Also includes: The target path is displayed, and the position information of the AVG in the two-dimensional map is monitored in real time.

8. An AGV path planning device, characterized in that: include: A building unit, used to build a two-dimensional map according to the activity area of ​​AGV; A determination unit, used to determine the position coordinates of the starting point of the AGV and the position coordinates of n target points in the two-dimensional map, where n is an integer greater than 1; A sorting unit, used for sorting n target points to obtain the first target point to the nth target point; A planning unit, used to plan, according to the sorting result, an optimal subpath between the starting point and the first target point, an optimal subpath between the first target point and the second target point, ..., an optimal subpath between the n-1th target point and the nth target point, and generate a target path according to the planned n subpaths; The control unit is used to instruct the AGV to move according to the target path.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

10. A computer device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images