Path planning method and device

Abstract

The invention discloses a path planning method and device, and relates to the technical field of logistics warehouse management. A specific embodiment of the method comprises the steps of judging a path conflict according to real-time environment parameters and task execution state information collected by a guided vehicle, generating a path adjustment suggestion through a preset conflict mechanism when the conflict exists, and further performing adjustment in combination with a current path planning result to obtain a final path planning result. Therefore, the guide vehicle executes the task. According to the embodiment, the task paths of the guide vehicles can be effectively coordinated according to the information collected in real time, path conflicts between the guide vehicles are avoided, and the task execution efficiency of the guide vehicles can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics warehousing management, and particularly to a method and device for path planning. Background Art

[0002] In modern logistics warehousing systems, path planning of automated guided vehicles (AGVs) is an important link to achieve high-efficiency automation. As one of the core devices in warehousing logistics, AGVs are widely used in scenarios such as material transportation, picking support, and in-warehouse handling. For example, in a manufacturing warehouse, an AGV can receive order information in real time, quickly identify the location of goods through an intelligent scheduling system, and transport raw materials or finished products to the designated workstations or outbound points along the optimal path, thereby reducing manual intervention and time waste. In e-commerce warehousing, AGVs can also work in cooperation with picking robots to help staff quickly locate the positions of goods and improve picking efficiency. In complex logistics scenarios, such as complex environments and multiple AGVs, the generation of paths is particularly important and path conflicts are likely to occur.

[0003] Common AGV path planning methods mainly select the shortest route for a single AGV to execute tasks according to dynamic environmental data using algorithms such as A*, which has a large amount of calculation and is prone to conflicts in the task execution routes of multiple AGVs. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and device for path planning, which can improve the accuracy of path planning results and avoid conflicts.

[0005] To achieve the above object, according to one aspect of the embodiments of the present invention, a method for path planning is provided, including:

[0006] During the process of the guided vehicle executing tasks according to the current path planning result, collecting real-time environmental parameters and task execution status information;

[0007] Judging whether there is a conflict in the path based on the real-time environmental parameters and task execution status information;

[0008] In response to the judgment result indicating the existence of a conflict, generating a path adjustment suggestion based on a preset conflict mechanism;

[0009] Performing path adjustment based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, and updating the current path planning result based on the adjusted path planning result, so that the guided vehicle executes tasks based on the current path planning result.

[0010] Optionally, before the guided vehicle executes tasks according to the current path planning result, the method further includes:

[0011] Obtaining initial environmental parameters and information on tasks to be executed;

[0012] Use a heuristic algorithm to generate an initial path planning result based on the initial environment parameters and the information of the task to be executed;

[0013] Adjust the path based on the path adjustment suggestions and the current path planning result to obtain an adjusted path planning result, including:

[0014] Use reinforcement learning and a heuristic algorithm to adjust the path based on the path adjustment suggestions and the current path planning result to obtain an adjusted path planning result.

[0015] Optionally, use reinforcement learning and a heuristic algorithm to adjust the path based on the path adjustment suggestions and the current path planning result to obtain an adjusted path planning result, including:

[0016] Use reinforcement learning and a heuristic algorithm to make a decision on the path adjustment plan based on the path adjustment suggestions and the current path planning result to obtain a target path adjustment plan;

[0017] Adjust the current path planning result based on the target path adjustment plan to obtain an adjusted path planning result.

[0018] Optionally, use a heuristic algorithm to generate an initial path planning result based on the initial environment parameters and the information of the task to be executed, including:

[0019] Determine the target algorithm in the heuristic algorithm based on the environmental characteristics corresponding to the initial environment parameters and the task requirements in the information of the task to be executed;

[0020] Use the target algorithm to train a model based on the historical static path planning results, and use the trained model to generate an initial path planning result based on the initial environment parameters and the information of the task to be executed.

[0021] Optionally, use the trained model to generate an initial path planning result based on the initial environment parameters and the information of the task to be executed, including:

[0022] Use the trained model to perform node search based on the initial environment parameters and the information of the task to be executed to generate an initialization path, and select the target initialization path in the initialization path by calculating the path cost;

[0023] Use the trained model to optimize and adjust the target initialization path through a global optimization method to obtain an initial path planning result.

[0024] Optionally, generate path adjustment suggestions based on a preset conflict mechanism, including:

[0025] Generate an adjustment strategy for the guided vehicle based on real-time environmental parameters and task execution status information, and adjust the operating parameters of the guided vehicle based on the adjustment strategy;

[0026] Generate a path adjustment suggestion based on the adjusted operating parameters of the guided vehicle and a preset conflict mechanism.

[0027] Optionally, the method further includes:

[0028] In response to detecting that the guided vehicle has a fault, reallocate tasks and re-plan the paths of the tasks.

[0029] According to another aspect of the embodiments of the present invention, there is provided a path planning device, including:

[0030] An acquisition module, configured to acquire real-time environmental parameters and task execution status information during the process of the guided vehicle executing tasks according to the current path planning result;

[0031] A judgment module, configured to judge whether there is a conflict in the path based on the real-time environmental parameters and task execution status information;

[0032] An adjustment module, configured to, in response to the judgment result indicating that there is a conflict, generate a path adjustment suggestion based on a preset conflict mechanism;

[0033] An adjustment module, configured to adjust the path based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, and update the current path planning result based on the adjusted path planning result, so that the guided vehicle executes tasks based on the current path planning result.

[0034] According to still another aspect of the embodiments of the present invention, there is provided an electronic device, including: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the one or more processors to implement the path planning method provided by the embodiments of the present invention.

[0035] According to still another aspect of the embodiments of the present invention, there is provided a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, the path planning method provided by the embodiments of the present invention is implemented.

[0036] According to yet another aspect of the embodiments of the present invention, there is provided a computer program product, including a computer program, and when the computer program is executed by a processor, the path planning method provided by the embodiments of the present invention is implemented.

[0037] One embodiment of the above invention has the following advantages or beneficial effects: It can determine whether there is an AGV conflict based on the real-time collected environmental parameters and the status information of AGV task execution. In the case of a conflict, it generates suggestions for adjusting the path planning based on the obtained environmental parameters and the status information of AGV task execution, and adjusts the current path planning result based on these suggestions to avoid conflicts between AGVs, obtaining an adjusted path planning result, improving the certainty of the path planning result generation, and combining real-time data for path adjustment to further ensure the accuracy of the path planning result. At the same time, through conflict judgment, it can effectively avoid possible AGV conflicts, ensure the smooth execution of AGV tasks, and thus improve the task execution efficiency.

[0038] The further effects of the above non-conventional optional methods will be described below in combination with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Among them:

[0040] Figure 1 is a schematic diagram of the main steps of the path planning method according to an embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of the main process of the path planning method according to an embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of the main modules of the path planning device according to an embodiment of the present invention;

[0043] Figure 4 is an exemplary system architecture diagram to which an embodiment of the present invention can be applied;

[0044] Figure 5 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following describes exemplary embodiments of the present invention with reference to the drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described here without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0046] It should be noted that in the technical solution disclosed in the present invention, in aspects such as the collection, gathering, updating, analysis, processing, use, transmission, and storage of the user's personal information, it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. Necessary measures are taken for the user's personal information to prevent illegal access to the user's personal information data and to safeguard the security of the user's personal information, network security, and national security.

[0047] Currently, the main path planning methods include static path planning, dynamic path planning, and machine learning-based path planning. Among them, static path planning is usually applicable to storage environments with simple structures and few changes. Its advantage lies in being easy to implement and manage. However, this method lacks flexibility and is difficult to cope with changes in dynamic environments; dynamic path planning adjusts the driving route of the AGV by real-time monitoring of environmental changes (such as dynamic obstacles and path congestion). Common algorithms include the A* algorithm, Dijkstra algorithm, and their various improved versions. These algorithms improve efficiency by calculating the shortest path or optimal path, but in complex environments, the computational complexity and real-time performance are still challenges; with the progress of artificial intelligence technology, machine learning methods (such as reinforcement learning and deep learning) have been gradually applied to the path planning of AGVs. By learning historical data and environmental characteristics, these methods can predict the optimal path to a certain extent and improve the self-adaptability of the system. However, the application of machine learning methods still faces problems such as large data requirements and high model complexity. The present invention comprehensively considers the above problems and proposes a method capable of path planning based on real-time environmental data and the task execution status of the guiding vehicle, which can effectively solve the above problems.

[0048] Figure 1 It is a schematic diagram of the main steps of the path planning method according to an embodiment of the present invention, as Figure 1 shown, including steps S101 to S104.

[0049] Step S101, during the process of the guiding vehicle executing tasks according to the current path planning result, collect real-time environmental parameters and task execution status information.

[0050] When an Automated Guided Vehicle (AGV, hereinafter collectively referred to as the guided vehicle) travels along the road corresponding to the current path planning result to perform tasks, it is necessary to collect the real-time environmental parameters corresponding to the current position and the information on the current task execution status of the guided vehicle in real time. Specifically, the real-time environmental parameters can be obtained through the acquisition devices installed on the guided vehicle. For example, data can be collected through sensors, including obtaining real-time environmental parameters through lidar, cameras, ultrasonic sensors, etc. The data may include map information, obstacle positions, dynamic change data, etc. Classified by type, the collected environmental parameters include two-dimensional map parameters, three-dimensional obstacle position parameters, dynamic object speed and other parameters. Among them, the dynamic change data includes the real-time road condition data during the AGV's driving, such as: traffic light changes, vehicle conditions in all directions on the road, weather changes, pedestrian flow changes, etc.; the task execution status information can include the current task completion degree, vehicle parameters when the AGV performs tasks (for example, the current vehicle speed of the AGV, the current energy consumption, etc.).

[0051] Optionally, the real-time environmental parameters can be parameter data within a preset range. For example, the environmental parameters within 20m are set to be collected, or the environmental parameters within the maximum range that the acquisition device can collect, etc. It can be specifically set according to the actual situation and is not limited thereto.

[0052] Optionally, the collected data also needs to be preprocessed before application and calculation, including noise filtering and formatting of the collected data, and multi-level data fusion processing to ensure the accuracy and real-time nature of the information. Specifically: Noise filtering: Use the Kalman Filter to smooth the sensor data. The filtering formula is as follows:

[0053]

[0054] Among them, is the updated state estimate, K k is the Kalman gain, z k is the measurement value, and H is the measurement matrix. Formatting processing: Convert multi-source data into a unified data format to ensure the compatibility of subsequent processing.

[0055] Optionally, the real-time environmental parameters also need to be subjected to data fusion processing to integrate data from multiple sensors (such as lidar, cameras, ultrasonic sensors, etc.) to form a unified environmental view.

[0056] Optionally, use a PID controller to adjust the speed and direction of the AGV to ensure the path tracking accuracy. The PID control formula:

[0057]

[0058] Among them, e(t) is the path deviation, and K p , K i , K d are the proportional, integral, and differential gains respectively.

[0059] Step S102: Determine whether there is a path conflict based on real-time environmental parameters and task execution status information.

[0060] Judge whether there is a path conflict problem among AGVs according to the obtained real-time environmental parameters and task execution status information. Specifically, according to the task execution status information such as the current running speed and current energy consumption of the AGV, combined with the implementation environment parameters, predict the time for the AGV to reach each location, and judge whether there will be a problem of location and time coincidence. If so, it means that there may be a conflict among AGVs.

[0061] Take a simple example. If the AGV is moving at a constant speed, calculate the time required for it to reach point a, and predict the waiting time for traffic lights generated by the path. Combine the two data to judge whether there is more than one AGV reaching point a at the same time. If there is more than one, there may be a conflict problem; if there is only one, there will be no conflict problem.

[0062] Step S103: In response to the judgment result that there is a conflict, generate a path adjustment suggestion based on a preset conflict mechanism.

[0063] If the judgment result is that there is a conflict, it is necessary to adjust the current path planning to avoid the path conflict problem among AGVs. Specifically, a path adjustment suggestion can be made according to a preset conflict mechanism. The preset conflict mechanism can include that when there is a conflict, the path of the AGV with a lower priority is adjusted first. For example, the path of the AGV with a lower priority is modified to another path with the same or similar distance. Among them, when adjusting, it is necessary to consider the factor of whether there will be a conflict with other AGVs, determine the path that will not cause a conflict as the path that can be modified, and generate a corresponding path adjustment suggestion based on this path. When modifying the path, the parameters such as the speed and energy consumption of the AGV can also be adaptively modified. For example, if the total distance becomes longer after the path is modified, the driving speed of the AGV can be appropriately increased, etc.

[0064] Optionally, the path adjustment suggestion can be generated uniformly according to a preset format. For example, the format generated according to the AGV number: AGV number - original path planning data - modified path planning data - original AGC driving parameters - modified AGV driving parameters, or a text description can be generated. The specific format of the path adjustment suggestion can be set according to actual needs and is not limited in this regard.

[0065] Optionally, in the generated path adjustment suggestion, multiple path modification opinions can be generated for the same AGV for further screening later.

[0066] Step S104: Adjust the path based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, and update the current path planning result based on the adjusted path planning result, so that the guided vehicle executes tasks based on the current path planning result.

[0067] Adjust the path according to the path adjustment suggestion and the current path planning result. During the adjustment process, conditions such as whether there is a conflict and whether it is the optimal route can be further judged to screen the path adjustment suggestion, and the current path planning result is adjusted and updated according to the screened path adjustment suggestion, and the AGV executes tasks based on the updated path planning result. Among them, the updated path planning result includes parameter data such as the driving route and driving speed of the AGV.

[0068] According to the path planning method provided by the embodiment of the present invention, it is possible to judge whether there is an AGV conflict based on the real-time collected environmental parameters and the status information of AGV task execution, and in the case of a conflict, generate a suggestion for adjusting the path planning based on the obtained environmental parameters and the status information of AGV task execution, and adjust the current path planning result based on this suggestion to avoid conflicts between AGVs, obtain an adjusted path planning result, improve the certainty of the generation of the path planning result, and combine real-time data for path adjustment to further ensure the accuracy of the path planning result. At the same time, through conflict judgment, possible AGV conflicts can be effectively avoided, ensuring the smooth execution of AGV tasks, and thus improving the task execution efficiency.

[0069] Optionally, before the guided vehicle executes tasks according to the current path planning result, the method further includes: obtaining initial environmental parameters and to-be-executed task information; using a heuristic algorithm to generate an initial path planning result based on the initial environmental parameters and the to-be-executed task information; adjusting the path based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, including: using reinforcement learning and a heuristic algorithm to adjust the path based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result.

[0070] Before the guiding vehicle executes a task, it is necessary to perform the first path planning to provide a data basis for subsequent path adjustment operations. First, obtain the initial environmental parameters and the information of the task to be executed. The initial environmental parameters can be obtained from historical data and can be static map data, including the coordinates of building obstacles, tree greenery, etc. The information of the task to be executed includes information such as the task arrival location and the required arrival time of the task. Combine the initial environmental parameters and the information of the task to be executed, and use a heuristic algorithm to generate the initial path planning result. Specifically, search for map nodes according to the initial environmental parameters and the information of the task to be executed, and generate an initial path based on the searched nodes. This initial path is the aggregated data composed of the path information of multiple AGVs. Subsequently, when adjusting the path planning result, a combination of reinforcement learning and heuristic algorithm is adopted, and the adjustment is made based on the generated path adjustment suggestions. Reinforcement learning formula:

[0071] Q(s,a)=Q(s,a)+α[r+γmax a′ Q(s ′ ,a ′ )-Q(s,a)],

[0072] where s is the current state, a is the current action, r is the reward, α is the learning rate, and γ is the discount factor. Heuristic adjustment: Combine with the A* algorithm for adjustment, and the heuristic function h(n) needs to consider environmental changes:

[0073]

[0074] where w i is the weight, and e i is the environmental change parameter.

[0075] According to the path planning method provided by the embodiment of the present invention, the path planning result can be adjusted by combining reinforcement learning and heuristic algorithm, avoiding conflicts between AGVs and improving the accuracy of path adjustment.

[0076] Optionally, adopt reinforcement learning and heuristic algorithm to perform path adjustment based on the path adjustment suggestion and the current path planning result to obtain the adjusted path planning result, including: adopt reinforcement learning and heuristic algorithm to make a path adjustment plan decision based on the path adjustment suggestion and the current path planning result to obtain the target path adjustment plan; adjust the current path planning result based on the target path adjustment plan to obtain the adjusted path planning result.

[0077] When performing path planning by combining two algorithms, first make a decision on the generated path adjustment suggestions, that is, judge whether to adjust according to the path adjustment suggestions. If not, regenerate an adjustment plan based on the current path planning result, and summarize it with the determined path adjustment suggestions to form a target adjustment plan, and adjust the current path planning result based on this target adjustment plan.

[0078] During the decision-making process, the influence of h(n) in the heuristic adjustment algorithm on path adjustment is mainly reflected in the path selection bias. Specifically, a high w i value: corresponds to an increase in the priority of parameter e i , and the path will be more inclined to avoid high-risk areas (such as bypassing obstacles); a low w i value: corresponds to a weakening of the influence of parameter e i , and the path may pay more attention to efficiency (such as choosing a more energy-consuming but shorter path). However, further analysis is required in specific scenarios, such as scenarios with an increase in dynamic obstacles, insertion of emergency orders, and equipment failure warnings. The dynamic adjustment of h(n) converts environmental changes into priority signals for path planning through a weight allocation strategy, and on the basis of ensuring global optimality, it realizes a rapid response to the dynamic environment (typical delay <50ms).

[0079] Optionally, a heuristic algorithm is adopted to generate an initial path planning result based on the initial environmental parameters and the information of the task to be executed, including: determining the target algorithm in the heuristic algorithm based on the environmental characteristics corresponding to the initial environmental parameters and the task requirements in the information of the task to be executed; adopting the target algorithm to train a model based on the historical static path planning result, and using the trained model to generate an initial path planning result based on the initial environmental parameters and the information of the task to be executed.

[0080] When generating the initial path planning result, it is first necessary to select the specific type of heuristic algorithm. When selecting the algorithm type, it can be selected according to the complexity of the environment. First, determine the complexity based on the environmental characteristics corresponding to the initial environmental parameters. For example, determine the complexity according to the number of features such as buildings and green belts within a certain range. The more the number of features, the greater the complexity value; or according to the feature density, the denser, the greater the complexity value. Then select the target algorithm according to the determined complexity. Commonly used algorithms include the A* algorithm, Dijkstra algorithm, genetic algorithm, etc. When the complexity value is relatively high, the genetic algorithm can be selected; when it is relatively low, the A* algorithm can be selected. Among them, the corresponding relationship between the complexity value and the algorithm can be preset, and different value ranges correspond to different algorithms. The specific values can be set according to the actual situation, and there is no restriction on this. After determining the algorithm, obtain the historical static path planning result, which can be the final static path planning result generated based on the data of historical task completion. Use this result as the input data of the model constructed based on the target algorithm, optimize and adjust the parameters of the target algorithm, that is, perform model training, obtain the model with adjusted parameters, and use the model with adjusted parameters, based on the initial environmental parameters and the information of the task to be executed, to generate the initial path planning result.

[0081] Among them, the A* algorithm: suitable for static environments, calculating the path cost:

[0082] f(n) = g(n) + h(n),

[0083] where g(n) is the actual cost from the starting point to node n, and h(n) is the heuristic estimate from node n to the target. The Dijkstra algorithm: used to find the shortest path, without using heuristic estimates. The genetic algorithm: suitable for dynamic environments, optimizing the path through population evolution.

[0084] Optionally, adopt the trained model to generate the initial path planning result based on the initial environmental parameters and the information of the task to be executed, including: adopting the trained model to perform node search based on the initial environmental parameters and the information of the task to be executed, generate the initialization path, and select the target initialization path in the initialization path by calculating the path cost; adopting the trained model to optimize and adjust the target initialization path through the global optimization method to obtain the initial path planning result.

[0085] When generating the initial path planning result, search for map nodes based on the trained model, the initial environmental parameters and the information of the task to be executed, and generate the initialized path according to the search result. After generating the initial path, it is necessary to calculate the costs of different paths and select the path with a lower cost as the finally generated path.

[0086] In the initial path planning, path cost calculation is the core link, directly affecting the quality of the path (such as the shortest distance, the lowest energy consumption, safety, etc.). Cost function design in a static environment: (1) Conventional weighted method, (2) Heuristic function (A* algorithm). Designing a heuristic algorithm requires a consistency condition, common solutions: Manhattan distance, Euclidean distance, potential field method enhancement, etc.; Real-time cost update in a dynamic environment: (1) Influence of dynamic obstacles (such as time-sensitive costs), (2) Sensor data fusion (involving multi-data source fusion); Cost prediction based on machine learning: (1) Data-driven cost modeling, (2) Reinforcement learning collaborative optimization.

[0087] After obtaining the generated path, further path optimization and adjustment operations can be carried out. The method of distributed computing is used for parallel computing to improve the computing efficiency. The optimization method can choose the simulated annealing method or the particle swarm optimization method. Among them, Simulated Annealing: used for global optimization, avoiding local optima by probabilistically accepting inferior solutions. Probability acceptance formula:

[0088] P = e -ΔE / T ,

[0089] where ΔE is the energy difference and T is the temperature.

[0090] Particle Swarm Optimization: Search for the optimal solution through multi-particle cooperation. Velocity update formula:

[0091] v i = wv i + c1r1(p i - x i ) + c2r2(g - x i ),

[0092] where w is the inertia weight, c1 and c2 are learning factors, and r1 and r2 are random numbers.

[0093] According to the path planning method provided by the embodiments of the present invention, a heuristic algorithm can be used to generate the path planning result, ensuring the accuracy of the path generation. At the same time, through optimization operations, the path planning result can be further improved.

[0094] Optionally, path adjustment suggestions are generated based on a preset conflict mechanism, including:

[0095] Generate an adjustment strategy for the guided vehicle based on real-time environmental parameters and task execution status information, and adjust the operation parameters of the guided vehicle based on the adjustment strategy; Generate path adjustment suggestions based on the adjusted operation parameters of the guided vehicle and the preset conflict mechanism.

[0096] Generate a strategy that adapts to the current environment and task requirements, and adjust the operation parameters of the AGV. Specifically, use a reinforcement learning algorithm (such as deep Q-learning or policy gradient method) to generate a strategy. The policy gradient method calculates the policy update:

[0097]

[0098] where J(θ) is the policy performance metric, and π θ is the policy, and Q π is the state-action value function.

[0099] Optionally, the parameters in the gradient algorithm can be adjusted and optimized. Specifically, use gradient descent or its variants (such as the Adam optimizer) to adjust the system parameters. Mathematical expression: Gradient descent method is used for parameter update, and the formula is as follows:

[0100]

[0101] where α is the learning rate.

[0102] Optionally, the method further includes:

[0103] In response to detecting that the guided vehicle has a fault, reassign the task and re-plan the path of the task.

[0104] If a fault occurs in the AGV during the driving process of the AGV, such as a collision, a sensor fault, or a motor overheat, and achieve fault self-healing and system protection through a preset strategy. Threshold-based detection, pattern-based detection, such as using the Isolation Forest algorithm to detect abnormal data points. When a fault is detected, the task of the faulty guided vehicle needs to be reassigned, and the path of the task needs to be re-planned according to the reallocation result.

[0105] According to the path planning method provided by the embodiment of the present invention, it is possible to determine whether there is an AGV conflict based on the real-time collected environmental parameters and the state information of the AGV task execution, generate a suggestion for adjusting the path planning based on the obtained data, and adjust the current path planning result based on this suggestion to avoid conflicts between AGVs and ensure the smooth progress of the AGV task execution process. Based on the obtained adjusted path planning result, the certainty of the path planning result generation is improved, and the path is adjusted in combination with real-time data, further ensuring the accuracy of the path planning result. In addition, through various path adjustment methods, the path during the AGV task execution process can be optimized and adjusted in real time to ensure the real-time performance of the path planning result.

[0106] Such as Figure 2 shown is the schematic flowchart of the path planning method according to the embodiment of the present invention.

[0107] 1) Environmental perception: (1) Sensor data acquisition: The AGV obtains real-time environmental data through lidar, cameras, ultrasonic sensors, etc. This data may include map information, obstacle positions, dynamic changes, etc. (2) Data preprocessing: Filter and format the collected data, and perform multi-level data fusion processing to ensure the accuracy and real-time nature of the information.

[0108] 2) Path calculation and planning: Combine multiple heuristic algorithms for initial path planning. According to the current environment and task requirements, select suitable heuristic algorithms (such as A* algorithm, Dijkstra algorithm, genetic algorithm, etc.). During this process, use distributed computing nodes to parallelly process path optimization tasks and reduce the computational complexity.

[0109] 3) Self-organizing system: Responsible for adaptive adjustment according to different tasks (such as task priorities, potential conflicts, etc.). Capabilities include: (1) Task allocation: Dynamically allocate tasks to the AGV through a decentralized cooperation mechanism based on the current environment and decisions. (2) Path coordination: Use the self-organizing system to coordinate the paths of multiple AGVs to avoid conflicts. (3) Conflict resolution mechanism: When path conflicts are detected, adjust priorities and re-plan paths.

[0110] 4) Path adjustment: After path planning is completed, during the path execution process, adjust the path based on real-time environmental changes (such as the appearance of obstacles) according to the feedback from the self-organizing system. The system will make adjustments in combination with the suggestions given by the self-organizing system.

[0111] 5) Task execution and feedback: Path execution, the AGV moves according to the calculated path; Task status monitoring, monitor the task execution status in real time to ensure that the task is completed as planned; Feedback collection: Adjust path planning parameters through real-time feedback to improve adaptability, and collect data during the execution process for subsequent optimization.

[0112] 6) Fault detection and self-healing: Fault monitoring, monitor the AGV status in real time through sensors and system logs; Self-healing mechanism, when a fault is detected, the system automatically adjusts task allocation and path planning to ensure that the task continues.

[0113] Figure 3 The following shows a schematic diagram of the main modules of the path planning device 300 provided by an embodiment of the present invention, as Figure 3 shown, including an acquisition module 301, a judgment module 302, a generation module 303, and an adjustment module 304.

[0114] The acquisition module 301 is used to collect real-time environmental parameters and task execution status information during the process of the guided vehicle executing tasks according to the current path planning result;

[0115] A judgment module 302, configured to judge whether there is a conflict in the path based on real-time environment parameters and task execution status information;

[0116] A generation module 303, configured to, in response to a judgment result indicating that there is a conflict, generate a path adjustment suggestion based on a preset conflict mechanism;

[0117] An adjustment module 304, configured to perform path adjustment based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, and update the current path planning result based on the adjusted path planning result, so that the guiding vehicle executes the task based on the current path planning result.

[0118] According to the path planning device provided by the embodiment of the present invention, it can judge whether there is an AGV conflict based on the real-time collected environment parameters and the status information of AGV task execution, and in the case of a conflict, generate a suggestion for adjusting the path planning based on the obtained environment parameters and the status information of AGV task execution, and adjust the current path planning result based on this suggestion to avoid conflicts between AGVs, obtain an adjusted path planning result, improve the certainty of the generated path planning result, and perform path adjustment in combination with real-time data, further ensuring the accuracy of the path planning result. At the same time, through conflict judgment, it can effectively avoid possible AGV conflicts, ensure the smooth execution of AGV tasks, and thus improve the task execution efficiency.

[0119] Optionally, the device further includes: an acquisition module 305 (not shown in the figure), configured to acquire initial environment parameters and to-be-executed task information; the generation module 303 is further configured to generate an initial path planning result based on the initial environment parameters and the to-be-executed task information by using a heuristic algorithm; the adjustment module 304 is further configured to perform path adjustment based on the path adjustment suggestion and the current path planning result by using reinforcement learning and a heuristic algorithm to obtain an adjusted path planning result.

[0120] Optionally, the adjustment module 304 is further configured to:

[0121] Use reinforcement learning and a heuristic algorithm to make a path adjustment plan decision based on the path adjustment suggestion and the current path planning result to obtain a target path adjustment plan;

[0122] Adjust the current path planning result based on the target path adjustment plan to obtain an adjusted path planning result.

[0123] Optionally, the generation module 303 is further configured to:

[0124] Determine the target algorithm in the heuristic algorithm based on the environmental characteristics corresponding to the initial environment parameters and the task requirements in the to-be-executed task information;

[0125] The target algorithm is adopted to train a model based on historical static path planning results, and the trained model is adopted to generate an initial path planning result based on initial environment parameters and information of a task to be executed.

[0126] Optionally, the generating module 303 is further configured to:

[0127] Adopt the trained model to perform node search based on initial environment parameters and information of a task to be executed, generate an initialization path, and select a target initialization path in the initialization paths by calculating path costs;

[0128] Adopt the trained model to optimize and adjust the target initialization path through a global optimization method to obtain an initial path planning result.

[0129] Optionally, the generating module 303 is further configured to:

[0130] Generate an adjustment strategy for a guided vehicle based on real-time environment parameters and task execution status information, and adjust operation parameters of the guided vehicle based on the adjustment strategy;

[0131] Generate a path adjustment suggestion based on the adjusted operation parameters of the guided vehicle and a preset conflict mechanism.

[0132] Optionally, the device further includes: an allocation module 306 (not shown in the figure), configured to re-allocate tasks and re-plan paths of the tasks in response to detecting that the guided vehicle fails.

[0133] According to the path planning device provided by the embodiment of the present invention, it can determine whether there is an AGV conflict according to real-time collected environment parameters and status information of AGV task execution, generate a suggestion for adjusting path planning based on the obtained data, and adjust the current path planning result based on the suggestion to avoid conflicts between AGVs and ensure the smoothness of the AGV task execution process. Based on the obtained adjusted path planning result, the certainty of generating the path planning result is improved, and the path is adjusted in combination with real-time data, further ensuring the accuracy of the path planning result. In addition, through various path adjustment methods, the path during the AGV task execution process can be optimized and adjusted in real time to ensure the real-time performance of the path planning result.

[0134] Figure 4 An exemplary system architecture 400 to which the path planning method or the path planning device according to the embodiment of the present invention can be applied is shown.

[0135] As Figure 4As shown, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 is used to provide a medium for communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0136] Users can use the terminal devices 401, 402, 403 to interact with the server 405 through the network 404 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 401, 402, 403, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for examples).

[0137] The terminal devices 401, 402, 403 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0138] The server 405 may be a server providing various services, such as a background management server (only for example) that supports the shopping websites browsed by users using the terminal devices 401, 402, 403. The background management server may analyze and process data such as received planning requests, etc., and feedback the processing results (such as path planning results - only for example) to the terminal devices.

[0139] It should be noted that the path planning method provided by the embodiments of the present invention is generally executed by the server 405. Correspondingly, the path planning device is generally set in the server 405.

[0140] It should be understood that Figure 4 the numbers of terminal devices, networks, and servers in

[0141] are merely illustrative. According to actual needs, there may be any number of terminal devices, networks, and servers. Figure 5 is merely illustrative. According to actual needs, there may be any number of terminal devices, networks, and servers. Figure 5 The terminal device or server shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0142] As shown in Figure 5As shown, computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0143] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom can be installed into the storage section 508 as needed.

[0144] Specifically, according to an embodiment disclosed by the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment disclosed by the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, the above functions defined in the system of the present invention are executed.

[0145] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] The units or modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described units or modules can also be provided in a processor. For example, it can be described as: a processor includes an acquisition module, a determination module, a generation module, and an adjustment module. Among them, the names of these units or modules do not constitute a limitation on the units or modules themselves in some cases. For example, the acquisition module can also be described as "a module for acquiring real-time environmental parameters and task execution status information during the process that the guided vehicle executes tasks according to the current path planning result".

[0148] As another aspect, the present invention also provides a computer-readable medium. The computer-readable medium can be included in the device described in the above embodiments; or it can exist independently without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by a device, the device includes:

[0149] During the process that the guided vehicle executes tasks according to the current path planning result, acquire real-time environmental parameters and task execution status information;

[0150] Based on the real-time environmental parameters and the task execution status information, determine whether there is a conflict in the path;

[0151] In response to the determination result that there is a conflict, generate a path adjustment suggestion based on a preset conflict mechanism;

[0152] Based on the path adjustment suggestion and the current path planning result, perform path adjustment to obtain an adjusted path planning result, and update the current path planning result based on the adjusted path planning result, so that the guided vehicle executes tasks based on the current path planning result.

[0153] According to the technical solution of the embodiments of the present invention, it is possible to improve the accuracy of the path planning result, improve the planning coordination ability, and avoid conflicts between AGVs.

[0154] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A path planning method, characterized in that: include: When the guided vehicle is executing the task according to the current path planning results, real-time environmental parameters and task execution status information are collected; Determining whether there is a conflict in the path based on the real-time environment parameter and the task execution status information; In response to the judgment result that there is a conflict, generating a path adjustment suggestion based on a preset conflict mechanism; The path is adjusted based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result, and the current path planning result is updated based on the adjusted path planning result, so that the guided vehicle performs the task based on the current path planning result.

2. The method according to claim 1, characterized in that Before the guided vehicle performs the task according to the current path planning result, the method further includes: Obtain initial environment parameters and information about tasks to be executed; Using a heuristic algorithm to generate an initial path planning result based on the initial environmental parameters and the task information to be performed; The step of performing path adjustment based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result includes: Reinforcement learning and heuristic algorithms are used to perform path adjustment based on the path adjustment suggestion and the current path planning result to obtain an adjusted path planning result.

3. The method according to claim 2, characterized in that The reinforcement learning and heuristic algorithm are used to adjust the path based on the path adjustment suggestion and the current path planning result to obtain the adjusted path planning result, including: Using the reinforcement learning and heuristic algorithm, a path adjustment plan decision is made based on the path adjustment suggestion and the current path planning result to obtain a target path adjustment plan; The current path planning result is adjusted based on the target path adjustment scheme to obtain an adjusted path planning result.

4. The method according to claim 2, characterized in that: The adopting of a heuristic algorithm to generate an initial path planning result based on the initial environment parameters and the information of the task to be performed includes: Determining a target algorithm in the heuristic algorithm based on the environmental characteristics corresponding to the initial environmental parameters and the task requirements in the task information to be performed; The target algorithm is used to perform model training based on historical static path planning results, and the trained model is used to generate an initial path planning result based on the initial environment parameters and the task information to be performed.

5. The method according to claim 4, characterized in that The adopting of the trained model to generate an initial path planning result based on the initial environment parameters and the information of the task to be performed includes: Using the trained model to perform node search based on the initial environment parameters and the task information to be executed, generating an initialization path, and selecting a target initialization path in the initialization path by calculating the path cost; The trained model is used to optimize and adjust the target initialization path through a global optimization method to obtain an initial path planning result.

6. The method according to claim 1, characterized in that The generating of the path adjustment suggestion based on the preset conflict mechanism includes: Generating an adjustment strategy for the guide vehicle based on the real-time environmental parameters and the task execution status information, and adjusting the operating parameters of the guide vehicle based on the adjustment strategy; The path adjustment suggestion is generated based on the adjusted operating parameters of the guided vehicle and the preset conflict mechanism.

7. The method according to claim 1, characterized in that The method further comprises: In response to detecting that the guided vehicle has failed, tasks are reallocated and paths of the tasks are replanned.

8. A path planning device, characterized in that: include: The acquisition module is used to collect real-time environmental parameters and task execution status information when the guided vehicle performs the task according to the current path planning results; A judgment module, used for judging whether there is a conflict in the path based on the real-time environment parameter and the task execution status information; A generating module, configured to generate a path adjustment suggestion based on a preset conflict mechanism in response to a judgment result that a conflict exists; The adjustment module is used to adjust the path based on the path adjustment suggestion and the current path planning result, obtain the adjusted path planning result, and update the current path planning result based on the adjusted path planning result, so that the guide vehicle performs the task based on the current path planning result.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images