A path planning method supporting multiple devices and multiple scenarios

Abstract

The present application provides a path planning method that supports multiple devices and multiple scenarios, including: obtaining the setting parameters for each type of AGV; obtaining the constraints of each planned path; splitting the setting parameters and constraints respectively, and constructing a path planning pipeline based on the split setting parameters and the constraints; obtaining the input constraints of the target logistics task, and filtering and planning the split setting parameters and the constraints through the path planning pipeline based on the input constraints, so as to obtain a path planning solution that meets the target logistics task. The above solution dynamically plans the shortest path between workstations through the construction of the path planning pipeline, improves the overall production efficiency of the factory, and realizes path planning for different types of AGVs in complex scenarios, which can adapt to most industrial scenarios.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle path planning, and in particular to a path planning method that supports multiple devices and multiple scenarios. Background Art

[0002] Logistics is an integral part of the production process. Whether it's raw materials before production, finished products, or even semi-finished products, they all require timely supply and transfer to avoid interruptions or delays and improve production efficiency. Therefore, rationally arranging material transfer routes based on different production scenarios plays a crucial role in the entire production process. Therefore, route planning, as the core of the entire logistics process, has become a pressing issue that needs to be addressed.

[0003] It is understood that the most common existing path planning for industrial scenarios is simply a pre-configured fixed path or a simple route based on nodes. Manufacturing companies often plan warehouse or workshop layouts based on the different products they produce, and also customize different types of logistics AGVs for logistics transfer. If the path is not properly planned, logistics efficiency will be low, leading to a series of problems such as substandard production cycles and delivery delays.

[0004] Therefore, there is an urgent need for an effective dynamic path planning that can ensure that the production rhythm meets the standards and achieve the timeliness of the entire logistics transfer. Summary of the Invention

[0005] This application provides a path planning method that supports multiple devices and multiple scenarios, realizes path planning for different types of AGVs in different scenarios, provides logistics flexibility, and improves the overall production efficiency of the factory. The technical solution is as follows.

[0006] In one aspect, a path planning method supporting multiple devices and multiple scenarios is provided, the method comprising:

[0007] Get the adjacency relationship of all nodes in the target map;

[0008] Obtain various types of AGVs, and for each type of AGV, obtain the setting parameters of the AGV;

[0009] Obtaining the planned paths for each scenario, and for each planned path, obtaining the constraints of the planned path;

[0010] Splitting the setting parameters and the restriction conditions respectively, and constructing a path planning pipeline according to the adjacency relationship, the split setting parameters, and the split restriction conditions;

[0011] The input constraints of the target logistics task are obtained, and based on the input constraints, the adjacency relationship, the split setting parameters, the split constraints and the pipeline processing logic are filtered and planned and calculated through the path planning pipeline to obtain a path planning solution that meets the target logistics task.

[0012] In another aspect, a path planning apparatus supporting multiple devices and multiple scenarios is provided, the apparatus comprising:

[0013] Adjacency relationship acquisition module, used to obtain the adjacency relationship of all nodes in the target map;

[0014] A setting parameter acquisition module is used to acquire various types of AGVs and, for each type of AGV, acquire the setting parameters of the AGV;

[0015] A planned path constraint condition acquisition module is used to obtain the planned path in each scenario and, for each planned path, obtain the constraint conditions of the planned path;

[0016] A path planning pipeline construction module, configured to split the setting parameters and the restriction conditions respectively, and construct a path planning pipeline according to the adjacency relationship, the split setting parameters, the split restriction conditions and the pipeline processing logic;

[0017] The path planning scheme acquisition module is used to obtain the input constraints of the target logistics task, and according to the input constraints, filter and plan the adjacency relationship, the split setting parameters and the split constraints through the path planning pipeline to obtain a path planning scheme that meets the target logistics task.

[0018] In a possible implementation, the setting parameters of the AGV include whether the AGV can rotate, whether the AGV can translate, the AGV starting angle, and the AGV docking end angle.

[0019] In a possible implementation, the restriction conditions of the planned path include a map number, an adjacent point type, a list of prohibited nodes, a list of prohibited roads, a list of nodes that must be passed through, and a route generation method.

[0020] In one possible implementation, the pipeline processing logic is that the path planning pipeline includes at least one of a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline;

[0021] The filtering pipeline is used to filter different adjacent point sets, path must-pass points, prohibited points, and prohibited roads according to the restriction conditions to obtain a target adjacent point set that meets the restriction conditions;

[0022] The data format pipeline is used to convert the data format of the target adjacent point set;

[0023] The control data pipeline is used to calculate the congestion level of each neighboring point in the target neighboring point set;

[0024] The algorithm pipeline is used to initialize point data, calculate the weight of each adjacent point in the target adjacent point set and the optimal path;

[0025] The motion algorithm pipeline is used to calculate the driving motion of the AGV during driving.

[0026] In a possible implementation, the algorithm pipeline includes an initialization point pipeline and a shortest path pipeline;

[0027] Wherein, the initialization point pipeline is used to initialize the value of the point;

[0028] The shortest path pipeline is used to calculate the weight of each adjacent point in the target adjacent point set, and obtain the optimal path corresponding to the target logistics task based on the weight of each adjacent point.

[0029] In one possible implementation, the path planning pipeline further includes an object pool;

[0030] The object pool is used to store a specified number of adjacent point sets so that each adjacent point set can be reused during path planning.

[0031] In a possible implementation, the path planning solution acquisition module is further configured to:

[0032] According to the input restriction condition, a node priority queue is constructed through the filtering pipeline, and a target adjacent point set corresponding to the node priority queue is obtained;

[0033] Obtaining the weight of each adjacent point through the shortest path pipeline according to the distance between points and the congestion level of each adjacent point in the target adjacent point set;

[0034] According to the current angle of the AGV, the angles between points, and the connection relationship between points, the weight of each connection segment passed by the AGV is obtained through the shortest path pipeline;

[0035] According to the weights of the respective adjacent points and the weights of the respective connection segments passed by the AGV, the optimal path corresponding to the target logistics task is obtained through the shortest path pipeline.

[0036] In one possible embodiment, the device is further used for:

[0037] According to the head angle of the AGV and the moving direction between points, the driving direction of the AGV is obtained through the motion algorithm pipeline;

[0038] Assigning an action to the AGV through the action algorithm pipeline according to the head angle of the previous adjacent point and the head angle of the next adjacent point of the current node of the AGV;

[0039] According to the driving direction of the AGV and the assigned action of the AGV, the moving direction of the head of the AGV during the driving process of the optimal path is updated through the action algorithm pipeline.

[0040] In a possible implementation, the path planning solution acquisition module is further configured to:

[0041] Obtain the target AGV type and target planning path corresponding to the target logistics task;

[0042] According to the setting parameters of the target AGV type and the constraint conditions of the target planning path, the input constraint conditions of the target logistics task are obtained.

[0043] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the above-mentioned path planning method that supports multiple devices and multiple scenarios.

[0044] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement the above-mentioned path planning method supporting multiple devices and multiple scenarios.

[0045] In another aspect, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned multi-device, multi-scenario path planning method.

[0046] The technical solution provided by this application may have the following beneficial effects:

[0047] Obtain various types of AGVs, and for each type of AGV, obtain the setting parameters of the AGV; obtain the planned paths in various scenarios, and for each planned path, obtain the constraints of the planned path; split the setting parameters and the constraints respectively, and construct a path planning pipeline based on the split setting parameters and the constraints; obtain the input constraints of the target logistics task, and based on the input constraints, filter and plan the split setting parameters and the constraints through the path planning pipeline to obtain a path planning solution that meets the target logistics task. The above solution dynamically plans the shortest path between workstations through the construction of the path planning pipeline, improves the overall production efficiency of the factory, realizes path planning for different types of AGVs in complex scenarios, provides logistics flexibility, and the time required for path planning is quite short, which can adapt to most industrial scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A schematic diagram of the basic structure of the path planning pipeline involved in the embodiment of the present application is shown.

[0050] Figure 2 A schematic diagram of the combination of AGV setting parameters and planned path parameters involved in an embodiment of the present application is shown.

[0051] Figure 3 The present invention is a flowchart of a path planning method supporting multiple devices and multiple scenarios according to an exemplary embodiment.

[0052] Figure 4 The present invention is a flowchart of a path planning method supporting multiple devices and multiple scenarios according to an exemplary embodiment.

[0053] Figure 5 A schematic diagram of the processing logic flow within the path planning pipeline involved in an embodiment of the present application is shown.

[0054] Figure 6 The figure is a structural block diagram of a path planning apparatus supporting multiple devices and multiple scenarios according to an exemplary embodiment.

[0055] Figure 7 A structural block diagram of a computer device shown in an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solution of this application in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0057] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0058] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0059] In an embodiment of the present application, "predefinition" can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). This application does not limit its specific implementation method.

[0060] Figure 1 The basic structural diagram of the path planning pipeline involved in the embodiment of the present application is shown. This application introduces a path planning system for industrial scenarios that can adapt to various types of logistics AGVs and provide reliable operation paths based on the performance and operation methods of different logistics equipment. In the embodiment, pipeline programming can be adopted, that is, input mode 1-pipeline calculation mode 2-output mode 3, thereby improving code maintainability and increasing the scalability of various business combinations.

[0061] Optional, such as Figure 1 As shown in the figure, in input mode 1, the input content includes the adjacency relationship of all nodes in the map, the setting parameters of each type of AGV, and the constraints of the planned path in each scenario. The path planning pipeline is constructed based on the input content and pipeline processing logic.

[0062] Optional, please refer to Figure 2The diagram below shows the combined AGV setup parameters and planned path parameters. To ensure compatibility with various AGV types, the AGV setup parameters are broken down into specific categories for each type, including: whether the AGV can rotate, whether the AGV can translate, the AGV starting angle, and the AGV docking angle. The planned path constraints are also broken down into specific categories: map number, neighbor point type, list of prohibited nodes, list of prohibited roads, list of required nodes, and route generation method. In practice, the breakdown of AGV setup parameters and planned path constraints can be customized as needed.

[0063] After the split is completed, all the above conditions are combined together and input into the "main pipeline" for calculation, that is, pipeline calculation mode 2. Each "small pipeline" within the "main pipeline" is calculated and planned corresponding to each split constraint condition.

[0064] Optionally, adjacency refers to the connection between points; and adjacency type refers to the type of point. Different types of AGVs correspond to different types of adjacency. In the constraints of path planning, the role of adjacency type is to set the direct adjacency between points in the map to adapt to AGVs from different manufacturers. There are two ways to generate routes: algorithm generation and fixed routes. The paths planned by the algorithm can currently cover 90% of the scenarios. The remaining 10% of the scenarios cannot be planned well by the algorithm due to their particularity. Therefore, the use of pre-configured fixed routes can effectively provide the desired path.

[0065] Optionally, when the path planning pipeline is initialized, a specified number of neighbor point sets are created and placed in a common object pool. Each time a path is planned, all neighbor point sets of the map stored in the object pool are assigned to the current plan. After use, the data changed during the calculation can be restored and returned to the object pool for the next use. Therefore, when multiple devices request path planning, this method can save the time spent on creating new objects and improve the time efficiency of a single planned path.

[0066] Optionally, the path planning pipeline's usage is also divided into five categories: algorithm-related, angle and action-related, control data-related, data format-related, and filter condition-related. Specifically, the pipeline processing logic for the path planning pipeline includes a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline. The algorithm-related class includes initializing point data, setting weights, and shortest path algorithms (such as Dijkstra's shortest path algorithm). The angle and action-related class includes calculating movement direction (forward / backward), setting actions (rotation, translation), and setting control directions. The control data-related class includes obtaining control road weights. The data format-related class includes data format conversion and data cloning. The filter condition-related class implements filtering of different sets of adjacent points, as well as filtering of required points, prohibited points, and prohibited roads. Through these pipelines, the input constraints and the output results after calculation are clearly defined. This model provides a clearer, more intuitive, and simpler approach for potentially adding search constraints or more complex calculation processing logic in the future.

[0067] Optionally, after the pipeline calculation mode 2 planning is completed, the output mode 3 can output the optimal path planning solution that meets the requirements.

[0068] Figure 3 FIG is a flow chart showing a path planning method supporting multiple devices and multiple scenarios according to an exemplary embodiment. Figure 3 As shown, the method may include the following steps:

[0069] Step S301: Obtain the adjacency relationship of all nodes in the target map.

[0070] In one possible implementation, when performing multi-device multi-scenario path planning, the adjacency relationships of all nodes in the target map are first obtained, and then a set of adjacent points can be constructed based on the adjacency relationships of all nodes. Each node in the map corresponds to a different workstation or point.

[0071] This adjacency relationship is also one of the parameter combinations for constructing the following path planning pipeline. When using this path planning pipeline to plan the path of the target logistics task, based on the adjacency relationship between each node involved in the target logistics task and all nodes in the target map, different sets of adjacent points are filtered to construct a node priority queue corresponding to the target logistics task.

[0072] Step S302: Acquire various types of AGVs, and for each type of AGV, acquire the setting parameters of the AGV.

[0073] In a possible implementation, in order to support path planning for multiple devices, it is also necessary to obtain multiple types of AGVs and the setting parameters of each type of AGV to expand the application scenarios.

[0074] Step S303: Obtain the planned paths for each scenario, and obtain the restriction conditions of each planned path.

[0075] In a possible implementation, in order to support path planning in multiple scenarios, it is also necessary to obtain the planned path in each scenario and obtain the restriction conditions of each planned path to expand the application scenarios.

[0076] Step S304: split the setting parameters and the restriction conditions respectively, and construct a path planning pipeline according to the adjacency relationship, the split setting parameters, the split restriction conditions and the pipeline processing logic.

[0077] In one possible implementation, in order to be compatible with various types of AGVs, the AGV setting parameters are subdivided for each type of AGV. In addition, the restriction conditions for the planned path are also broken down in detail. After the splitting is completed, all the above conditions are combined to construct a path planning pipeline, and each "small pipeline" within the path planning pipeline performs calculations and planning corresponding to each split condition.

[0078] In one possible implementation, the pipeline processing logic for a path planning pipeline includes a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline. Based on the adjacency relationships, the split configuration parameters, and the split constraint conditions, the pipeline processing logic constructs the path planning pipeline. This pipeline processing logic can be configured based on actual needs.

[0079] Step S305: Obtain the input constraints of the target logistics task, and based on the input constraints, filter and plan the adjacency relationship, the split setting parameters, and the split constraints through the path planning pipeline to obtain a path planning solution that meets the target logistics task.

[0080] In one possible implementation, after constructing the path planning pipeline, the input constraints of the target logistics task are used as the input of the path planning pipeline, and the adjacency relationship, the setting parameters after splitting, and the constraints after splitting are filtered and planned and calculated through the path planning pipeline to obtain a path planning plan that meets the target logistics task.

[0081] For a complete path planning task, its operation process is as follows: First, when there is a logistics task, the task module will combine the constraints of the planned path according to the issued constraints and the AGV type, and call the GetRoute method of the algorithm (that is, the shortest path algorithm of the shortest path pipeline). This method will first determine the [route generation method] in the constraints. If only a fixed route is available, it will return the preset path; if a fixed path is preferred, it will try to obtain the configured path. If there is no configured path, it will proceed with the algorithm planning. When using the algorithm planning, it will be based on Figure 3 、 Figure 4 as well as Figure 5 The algorithm calculates the path using a sequential process flow. Testing has shown that for a map with only 1,000 nodes, generating a suitable path takes less than 20 milliseconds. For a map with 10,000 nodes, the algorithm generates the path in less than 40 milliseconds. This extremely short path planning time is suitable for most industrial scenarios, providing effective, real-time routing and ensuring smooth logistics.

[0082] In summary, various types of AGVs are obtained, and for each type of AGV, the setting parameters of the AGV are obtained; the planned paths in various scenarios are obtained, and for each planned path, the constraints of the planned path are obtained; the setting parameters and the constraints are split respectively, and a path planning pipeline is constructed based on the split setting parameters and the constraints; the input constraints of the target logistics task are obtained, and based on the input constraints, the split setting parameters and the constraints are filtered and planned and calculated through the path planning pipeline to obtain a path planning solution that meets the target logistics task. The above solution dynamically plans the shortest path between workstations through the construction of a path planning pipeline, improves the overall production efficiency of the factory, realizes path planning for different types of AGVs in complex scenarios, provides logistics flexibility, and the time required for path planning is quite short, which can adapt to most industrial scenarios.

[0083] Figure 4 FIG is a flow chart showing a path planning method supporting multiple devices and multiple scenarios according to an exemplary embodiment. Figure 4 As shown, the method may include the following steps:

[0084] Step S401: Obtain the adjacency relationship of all nodes in the target map.

[0085] Step S402: Acquire various types of AGVs, and for each type of AGV, acquire the setting parameters of the AGV.

[0086] In a possible implementation, the setting parameters of the AGV include whether the AGV can rotate, whether the AGV can translate, the AGV starting angle, and the AGV docking end angle.

[0087] Step S403: Obtain the planned paths for each scenario, and obtain the restriction conditions of each planned path.

[0088] In a possible implementation, the restriction conditions of the planned path include a map number, an adjacent point type, a list of prohibited nodes, a list of prohibited roads, a list of nodes that must be passed through, and a route generation method.

[0089] Step S404: split the setting parameters and the restriction conditions respectively, and construct a path planning pipeline according to the adjacency relationship, the split setting parameters, the split restriction conditions and the pipeline processing logic.

[0090] In one possible implementation, please refer to Figure 5 A schematic diagram of the processing logic flow within the path planning pipeline is shown, wherein the pipeline processing logic is that the path planning pipeline includes at least one of a filtering pipeline, a data format pipeline, an algorithm class pipeline, a control data pipeline and an action algorithm pipeline; the path planning pipeline also includes an object pool; the object pool is used to store a specified number of adjacent point sets so that each adjacent point set can be reused during path planning.

[0091] The filtering pipeline is used to filter different adjacent point sets, path must-pass points, prohibited points, and prohibited roads according to the restriction conditions to obtain a target adjacent point set that meets the restriction conditions;

[0092] The data format pipeline is used to convert the data format of the target adjacent point set into a required data format;

[0093] The control data pipeline is used to calculate the congestion level of each adjacent point in the target adjacent point set; that is, to calculate the AGV congestion data of the entire field;

[0094] The algorithm pipeline is used to initialize point data, calculate the weight of each adjacent point in the target adjacent point set and the optimal path; the algorithm pipeline includes an initialization point pipeline and a shortest path pipeline (the shortest path pipeline can be Figure 5 The Dijkstra algorithm pipeline in the algorithm is used to initialize the point values ​​and assign them to satisfy the algorithm calculation. The shortest path pipeline is used to calculate the weight of each adjacent point in the target adjacent point set (i.e., the parent-child relationship of the adjacent points) and obtain the optimal path corresponding to the target logistics task based on the weight of each adjacent point.

[0095] This motion algorithm pipeline is used to calculate the AGV's driving motion based on each node angle. Finally, it outputs a path that meets the requirements and returns the used adjacent point data to the object pool for subsequent use.

[0096] Step S405: Obtain the input constraints of the target logistics task, and based on the input constraints, the distance relationship between points, the connection relationship between points, and the congestion level of each adjacent point, obtain the weight of each adjacent point and the weight of each connection segment passed by the AGV through the shortest path pipeline.

[0097] In one possible implementation, step S405 includes: obtaining a target AGV type and a target planning path corresponding to the target logistics task;

[0098] According to the setting parameters of the target AGV type and the constraints of the target planning path, the input constraints of the target logistics task are obtained;

[0099] According to the input constraints, a node priority queue is constructed through the filtering pipeline, and the target adjacent point set corresponding to the node priority queue is obtained.

[0100] According to the distance between points and the congestion level of each neighboring point in the target neighboring point set, the weight of each neighboring point is obtained through the shortest path pipeline;

[0101] According to the current angle of the AGV, the angles between points, and the connection relationship between points, the weight of each connection segment passed by the AGV is obtained through the shortest path pipeline.

[0102] Furthermore, the following is a detailed introduction to the path search algorithm based on Dijkstra's algorithm (the processing flow of the above shortest path pipeline):

[0103] 1. First, build a node priority queue, and the nodes with high weights are prioritized out of the queue.

[0104] 2. Starting from the starting point of the AGV, find the nearby adjacent points of each node in the node priority queue and filter the adjacent points using a filtering pipeline, and output the target adjacent point set that meets the input constraints.

[0105] 3. Obtain the weights of neighboring points that meet the input constraints; the weights of neighboring points are composed of two aspects: the distance between points and the weight converted from the congestion data obtained from the control data pipeline.

[0106] 4. Based on the AGV's current angle, the angle between the points, and whether the connection is a straight line or an arc, the AGV's head angle is assigned and the weight generated by passing through the connection segment is calculated. The adjacent points and their weights, as well as the connection segments and their weights, are added to the priority queue.

[0107] Furthermore, the following provides a detailed description of the control data (the processing flow of the control data pipeline mentioned above):

[0108] 1. When the shortest path pipeline's path-finding algorithm obtains the weight of a specific neighboring point, in addition to the length of the route itself as a weight, it will actively obtain the "congestion level" of reaching the neighboring point from the traffic control algorithm (the algorithm used by the control data pipeline) as a weight.

[0109] 2. The "level of congestion" is determined by the traffic control algorithm. When an AGV is passing through the adjacent point or multiple AGVs are about to pass through the adjacent point, the traffic control algorithm will coordinate and calculate the data and return a low weight for the adjacent point, indicating that it is not suitable for passage.

[0110] Step S406: According to the weights of the adjacent points and the weights of the connection segments passed by the AGV, the optimal path corresponding to the target logistics task is obtained through the shortest path pipeline.

[0111] Step S407: Based on the AGV's head angle and moving direction, the AGV's head moving direction is updated during its travel along the optimal path through the action algorithm pipeline to obtain a path planning solution that meets the target logistics task.

[0112] In one possible implementation, the motion algorithm pipeline obtains the AGV's travel direction based on the AGV's head angle and the point-to-point movement direction. The AGV's head angle is calculated by the shortest path pipeline based on the AGV's current angle, the angle between the points, and whether the connection is a straight line or an arc.

[0113] According to the head angle of the previous adjacent point and the head angle of the next adjacent point of the current node of the AGV, the AGV is assigned an action through the action algorithm pipeline;

[0114] According to the driving direction of the AGV and the assigned action of the AGV, the moving direction of the AGV's head during the driving process of the optimal path is updated through the action algorithm pipeline.

[0115] Furthermore, the following is a detailed introduction to the action algorithm (the processing flow of the above action algorithm):

[0116] 1. First, the AGV will determine whether to move forward or backward based on the vehicle head angle calculated by the shortest path pipeline and the movement direction between points.

[0117] 2. Secondly, the AGV is assigned actions based on the front angle of the previous node and the front angle of the next node: rotation and translation.

[0118] 3. Re-adjust the direction of movement of the vehicle head according to the assigned action.

[0119] In summary, various types of AGVs are obtained, and for each type of AGV, the setting parameters of the AGV are obtained; the planned paths in various scenarios are obtained, and for each planned path, the constraints of the planned path are obtained; the setting parameters and the constraints are split respectively, and a path planning pipeline is constructed based on the split setting parameters and the constraints; the input constraints of the target logistics task are obtained, and based on the input constraints, the split setting parameters and the constraints are filtered and planned and calculated through the path planning pipeline to obtain a path planning solution that meets the target logistics task. The above solution dynamically plans the shortest path between workstations through the construction of a path planning pipeline, improves the overall production efficiency of the factory, realizes path planning for different types of AGVs in complex scenarios, provides logistics flexibility, and the time required for path planning is quite short, which can adapt to most industrial scenarios.

[0120] Figure 6 This is a block diagram of a multi-device multi-scenario path planning device according to an exemplary embodiment. The device includes:

[0121] The adjacency relationship acquisition module 601 is used to obtain the adjacency relationship of all nodes in the target map;

[0122] The setting parameter acquisition module 602 is used to acquire various types of AGVs and, for each type of AGV, acquire the setting parameters of the AGV;

[0123] The planned path constraint condition acquisition module 603 is used to obtain the planned path in each scenario and obtain the constraint condition of each planned path;

[0124] A path planning pipeline construction module 604 is used to split the setting parameters and the constraint conditions respectively, and construct a path planning pipeline according to the adjacency relationship, the split setting parameters, the split constraint conditions and pipeline processing logic;

[0125] The path planning scheme acquisition module 605 is used to obtain the input constraints of the target logistics task, and based on the input constraints, filter and plan the adjacency relationship, the split setting parameters and the split constraints through the path planning pipeline to obtain a path planning scheme that meets the target logistics task.

[0126] In a possible implementation, the setting parameters of the AGV include whether the AGV can rotate, whether the AGV can translate, the AGV starting angle, and the AGV docking end angle.

[0127] In a possible implementation, the restriction conditions of the planned path include a map number, an adjacent point type, a list of prohibited nodes, a list of prohibited roads, a list of nodes that must be passed through, and a route generation method.

[0128] In one possible implementation, the pipeline processing logic is that the path planning pipeline includes at least one of a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline;

[0129] The filtering pipeline is used to filter different adjacent point sets, path must-pass points, prohibited points, and prohibited roads according to the restriction conditions to obtain a target adjacent point set that meets the restriction conditions;

[0130] The data format pipeline is used to convert the data format of the target adjacent point set;

[0131] The control data pipeline is used to calculate the congestion level of each neighboring point in the target neighboring point set;

[0132] This algorithm pipeline is used to initialize point data, calculate the weight of each neighboring point in the target neighboring point set, and calculate the optimal path;

[0133] The motion algorithm pipeline is used to calculate the driving motion of the AGV during driving.

[0134] In a possible implementation, the algorithm pipeline includes an initialization point pipeline and a shortest path pipeline;

[0135] The initialization point pipeline is used to initialize the value of the point;

[0136] The shortest path pipeline is used to calculate the weight of each adjacent point in the target adjacent point set, and obtain the optimal path corresponding to the target logistics task based on the weight of each adjacent point.

[0137] In one possible implementation, the path planning pipeline further includes an object pool;

[0138] The object pool is used to store a specified number of adjacent point sets so that each adjacent point set can be reused during path planning.

[0139] In a possible implementation, the path planning solution acquisition module 605 is further configured to:

[0140] According to the input restriction condition, a node priority queue is constructed through the filtering pipeline, and a target adjacent point set corresponding to the node priority queue is obtained;

[0141] According to the distance between points and the congestion level of each adjacent point in the target adjacent point set, the weight of each adjacent point is obtained through the shortest path pipeline;

[0142] According to the current angle of the AGV, the angle between points and the connection relationship between points, the weight of each connection segment passed by the AGV is obtained through the shortest path pipeline;

[0143] According to the weights of each adjacent point and the weights of each connection segment passed by the AGV, the optimal path corresponding to the target logistics task is obtained through the shortest path pipeline.

[0144] In one possible embodiment, the device is further used for:

[0145] According to the AGV's head angle and the direction of movement between points, the AGV's travel direction is obtained through the motion algorithm pipeline;

[0146] According to the head angle of the previous adjacent point and the head angle of the next adjacent point of the current node of the AGV, the AGV is assigned an action through the action algorithm pipeline;

[0147] According to the driving direction of the AGV and the assigned action of the AGV, the moving direction of the AGV's head during the driving process of the optimal path is updated through the action algorithm pipeline.

[0148] In a possible implementation, the path planning solution acquisition module is further configured to:

[0149] Obtain the target AGV type and target planning path corresponding to the target logistics task;

[0150] According to the setting parameters of the target AGV type and the constraints of the target planning path, the input constraints of the target logistics task are obtained.

[0151] In summary, various types of AGVs are obtained, and for each type of AGV, the setting parameters of the AGV are obtained; the planned paths in various scenarios are obtained, and for each planned path, the constraints of the planned path are obtained; the setting parameters and the constraints are split respectively, and a path planning pipeline is constructed based on the split setting parameters and the constraints; the input constraints of the target logistics task are obtained, and based on the input constraints, the split setting parameters and the constraints are filtered and planned and calculated through the path planning pipeline to obtain a path planning solution that meets the target logistics task. The above solution dynamically plans the shortest path between workstations through the construction of a path planning pipeline, improves the overall production efficiency of the factory, realizes path planning for different types of AGVs in complex scenarios, provides logistics flexibility, and the time required for path planning is quite short, which can adapt to most industrial scenarios.

[0152] See also Figure 7 , which is a schematic diagram of a computer device provided according to an exemplary embodiment of the present application, the computer device includes a memory and a processor, the memory is used to store a computer program, and when the computer program is executed by the processor, it implements the above-mentioned path planning method that supports multiple devices and multiple scenarios.

[0153] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0154] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of this application. The processor executes the non-transitory software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the processor, thereby implementing the methods in the above-mentioned method embodiments.

[0155] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0156] In an exemplary embodiment, a computer-readable storage medium is further provided, storing at least one computer program, which is loaded and executed by a processor to implement all or part of the steps of the above method. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, or an optical data storage device.

[0157] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0158] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A path planning method supporting multiple devices and multiple scenarios, characterized in that: The method comprises: Get the adjacency relationship of all nodes in the target map; Obtain various types of AGVs, and for each type of AGV, obtain the setting parameters of the AGV; Obtaining the planned paths for each scenario, and for each planned path, obtaining the constraints of the planned path; Separately splitting the setting parameters and the constraints, and constructing a path planning pipeline based on the adjacency relationship, the split setting parameters, the split constraints, and pipeline processing logic; the pipeline processing logic includes at least one of a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline for the path planning pipeline; The filtering pipeline is used to filter different adjacent point sets, path must-pass points, prohibited points, and prohibited roads according to the restriction conditions to obtain a target adjacent point set that meets the restriction conditions; The data format pipeline is used to convert the data format of the target adjacent point set; The control data pipeline is used to calculate the congestion level of each neighboring point in the target neighboring point set; The algorithm pipeline is used to initialize point data, calculate the weight of each adjacent point in the target adjacent point set and the optimal path; The motion algorithm pipeline is used to calculate the driving motion of the AGV during driving; Obtaining input constraints of a target logistics task, and filtering and planning calculations on the adjacency relationship, the split setting parameters, and the split constraints through the path planning pipeline based on the input constraints, so as to obtain a path planning solution that meets the target logistics task; The filtering and planning calculation of the adjacency relationship, the split setting parameters, and the split constraint conditions through the path planning pipeline according to the input constraint conditions includes: constructing a node priority queue through the filtering pipeline according to the input constraint conditions, and obtaining a target adjacent point set corresponding to the node priority queue; According to the distance between points and the congestion level of each adjacent point in the target adjacent point set, the weight of each adjacent point is obtained through the shortest path pipeline; According to the current angle of the AGV, the angles between points, and the connection relationship between points, the weight of each connection segment passed by the AGV is obtained through the shortest path pipeline; According to the weights of the respective adjacent points and the weights of the respective connection segments passed by the AGV, the optimal path corresponding to the target logistics task is obtained through the shortest path pipeline.

2. The method according to claim 1, characterized in that The setting parameters of the AGV include whether the AGV can rotate, whether the AGV can translate, the AGV starting angle, and the AGV docking end angle.

3. The method according to claim 1, characterized in that The restriction conditions of the planned path include map number, adjacent point type, a list of prohibited nodes, a list of prohibited roads, a list of nodes that must be passed through, and a route generation method.

4. The method according to claim 1, wherein The algorithm pipeline includes an initialization point pipeline and a shortest path pipeline; Wherein, the initialization point pipeline is used to initialize the value of the point; The shortest path pipeline is used to calculate the weight of each adjacent point in the target adjacent point set, and obtain the optimal path corresponding to the target logistics task based on the weight of each adjacent point.

5. The method according to claim 4, characterized in that The path planning pipeline also includes an object pool; The object pool is used to store a specified number of adjacent point sets so that each adjacent point set can be reused during path planning.

6. The method according to claim 1, wherein After obtaining the optimal path corresponding to the target logistics task, the method further includes: According to the AGV's head angle and the point-to-point movement direction, the AGV's travel direction is obtained through the motion algorithm pipeline; Assigning an action to the AGV through the action algorithm pipeline according to the head angle of the previous adjacent point and the head angle of the next adjacent point of the current node of the AGV; According to the driving direction of the AGV and the assigned action of the AGV, the moving direction of the head of the AGV during the driving process of the optimal path is updated through the action algorithm pipeline.

7. The method according to any one of claims 1 to 6, characterized in that: The input constraints for obtaining the target logistics task include: Obtain the target AGV type and target planning path corresponding to the target logistics task; According to the setting parameters of the target AGV type and the constraint conditions of the target planning path, the input constraint conditions of the target logistics task are obtained.

8. A path planning device supporting multiple devices and multiple scenarios, characterized in that: The device comprises: Adjacency relationship acquisition module, used to obtain the adjacency relationship of all nodes in the target map; A setting parameter acquisition module is used to acquire various types of AGVs and, for each type of AGV, acquire the setting parameters of the AGV; A planned path constraint condition acquisition module is used to obtain the planned path in each scenario and, for each planned path, obtain the constraint conditions of the planned path; a path planning pipeline construction module, configured to separate the setting parameters and the constraints, and construct a path planning pipeline based on the adjacency relationship, the separated setting parameters, the separated constraints, and pipeline processing logic; wherein the pipeline processing logic includes at least one of a filtering pipeline, a data format pipeline, an algorithm pipeline, a control data pipeline, and an action algorithm pipeline for the path planning pipeline; The filtering pipeline is used to filter different adjacent point sets, path must-pass points, prohibited points, and prohibited roads according to the restriction conditions to obtain a target adjacent point set that meets the restriction conditions; The data format pipeline is used to convert the data format of the target adjacent point set; The control data pipeline is used to calculate the congestion level of each neighboring point in the target neighboring point set; The algorithm pipeline is used to initialize point data, calculate the weight of each adjacent point in the target adjacent point set and the optimal path; The motion algorithm pipeline is used to calculate the driving motion of the AGV during driving; A path planning scheme acquisition module is used to obtain input constraints of the target logistics task and, based on the input constraints, filter and plan the adjacency relationship, the split setting parameters and the split constraints through the path planning pipeline to obtain a path planning scheme that meets the target logistics task; The path planning solution acquisition module is specifically configured to construct a node priority queue through the filtering pipeline according to the input restriction conditions, and obtain a target adjacent point set corresponding to the node priority queue; According to the distance between points and the congestion level of each adjacent point in the target adjacent point set, the weight of each adjacent point is obtained through the shortest path pipeline; According to the current angle of the AGV, the angles between points, and the connection relationship between points, the weight of each connection segment passed by the AGV is obtained through the shortest path pipeline; According to the weights of the respective adjacent points and the weights of the respective connection segments passed by the AGV, the optimal path corresponding to the target logistics task is obtained through the shortest path pipeline.

Images