Humanoid robot cluster path planning method, system and device and storage medium

By obtaining the current distance and path redundancy in the humanoid robot cluster, re-planning the path, combining OCra* and push and rotation algorithms, local congestion and deadlock problems in the humanoid robot cluster path planning are solved, and the smooth operation is improved and Coordination ability.

CN119085662AActive Publication Date: 2024-12-06广州里工实业有限公司

Patent Information

Application Number
CN202411577373.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-06
Publication Date
2024-12-06
Estimated Expiration
2044-11-06

AI Technical Summary

Technical Problem

In the prior art, humanoid robot clusters are prone to local congestion and deadlocks when planning paths, and are highly real-time and computational complex in dynamic environments, making it difficult to coordinate multiple robots.

Method used

By obtaining the current distance and path redundancy between humanoid robots, as well as task priorities, determine whether the robots are in close or conflicting states, re-planning the path to avoid congestion and deadlocks, using the OCra* algorithm and push and rotation algorithm for Dynamic path adjustment.

Benefits of technology

It improves the smooth operation of humanoid robot clusters, reduces local congestion and deadlocks, and enhances coordination and autonomy in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119085662A_ABST
    Figure CN119085662A_ABST
Patent Text Reader

Abstract

The invention discloses a humanoid robot cluster path planning method, system and device and a storage medium. The method comprises the following steps: acquiring a current distance between any two humanoid robots on an initial path, a first distance of the current distance in a previous acquisition period, a first path redundancy from any humanoid robot to a target point and a first priority of a current task; a second path redundancy of the other humanoid robot to the target point and a second priority of the current task; according to the current distance and the first distance, whether any two humanoid robots are in a first state or not is determined; and when any two humanoid robots are in the first state, according to the first priority, the first path redundancy, the second priority and the second path redundancy, determining one humanoid robot which needs to re-plan a path, and performing path planning. The robot can be widely applied to the technical field of robots.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of robot control technology, and in particular to a method, system, device and storage medium for path planning of humanoid robot swarms. Background Technology

[0002] With the rapid development of robotics technology, humanoid robots, as a highly flexible and adaptable form of robot, have demonstrated enormous potential in multiple fields. These fields include service industries, healthcare, education, and home assistance. In these applications, humanoid robots not only need to mimic human movements but also need to possess autonomous navigation and path planning capabilities to cope with complex and dynamic environments.

[0003] Path planning is one of the core technologies for autonomous navigation of humanoid robots. Effective path planning requires not only that the robot find the optimal path in a static environment, but also that it has the ability to adjust the path in real time in a dynamic environment. Robots need to handle various challenges, such as avoiding static obstacles (e.g., furniture, walls) and dynamic obstacles (e.g., pedestrians, moving objects). In addition, path planning must also take into account the robot's motion constraints, task objectives, and changes in the environment.

[0004] In related technologies, improving the path planning problem for humanoid robot swarms faces numerous challenges, including local congestion and deadlock in humanoid robot operation, high real-time and dynamic requirements, high computational complexity, and difficulties in multi-robot coordination. Therefore, there are still technical problems that need to be solved in related technologies. Summary of the Invention

[0005] The purpose of this application is to at least partially solve one of the technical problems existing in the prior art.

[0006] Therefore, one objective of this application is to provide a path planning method, system, device, and storage medium for humanoid robot swarms. This solution can improve local congestion and deadlock in robot operation and enhance the smoothness of robot swarm operation.

[0007] To achieve the above technical objectives, the technical solution adopted in this application embodiment includes: a humanoid robot cluster path planning method, comprising: obtaining the current distance between any two humanoid robots on an initial path, the current distance being the first distance in the previous acquisition cycle, the first path redundancy of any one of the two humanoid robots to the target point and the first priority of the current task, and the second path redundancy of the other of the two humanoid robots to the target point and the second priority of the current task; Based on the current distance and the first distance, determine whether any two of the humanoid robots are in the first state; When any two humanoid robots are in the first state, based on the first priority, the first path redundancy, the second priority, and the second path redundancy, determine one of the humanoid robots that needs to replan its path and perform path planning.

[0008] In addition, the humanoid robot swarm path planning method according to the above embodiments of the present invention may also have the following additional technical features: Furthermore, in this embodiment of the application, the first state includes a state in which two humanoid robots are approaching each other and a state in which two humanoid robots are in conflict.

[0009] Further, in this embodiment of the application, determining whether any two humanoid robots are in a first state based on the current distance and the first distance specifically includes: when the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is greater than a constant 0, determining that any two humanoid robots are in a state where the two humanoid robots are approaching each other; when the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is equal to a constant 0, determining that any two humanoid robots are in a state where the two humanoid robots are in a conflict state.

[0010] Furthermore, in this embodiment of the application, the step of determining a humanoid robot that needs to replan its path based on the first priority, the first path redundancy, the second priority, and the second path redundancy, and then performing path planning, specifically includes: determining a first planning priority for any one of the humanoid robots based on the first priority and the first path redundancy; determining a second planning priority for another humanoid robot based on the second priority and the second path redundancy; and determining a humanoid robot that needs to replan its path based on the first planning priority and the second planning priority, and then performing path planning.

[0011] Further, in this embodiment of the application, determining the first planning priority of any humanoid robot based on the first priority and the first path redundancy specifically includes: inputting the first priority and the first path redundancy into the planning priority determination equation to determine the first planning priority of any humanoid robot; wherein, the planning priority determination equation is: ; in, Pi is the first priority in the planning process. This represents the redundancy of the first path. , There are two weighting coefficients. + =1.

[0012] Furthermore, in this embodiment of the application, the step of determining any humanoid robot whose path needs to be replanned based on the first planning priority and the second planning priority, and performing path planning, specifically includes: The humanoid robot with the lower planning priority in the first planning priority and the second planning priority is identified as the humanoid robot that needs to replan its path and path planning is performed.

[0013] Furthermore, in this embodiment of the application, the first path redundancy is obtained through the following steps: obtaining the number of initial planned paths of the humanoid robot; when the number of planned paths is 1, using the length of the initial planned path of the humanoid robot as the first path redundancy; when the number of planned paths is greater than 1, using the number of initial planned paths as the first path redundancy.

[0014] On the other hand, embodiments of this application also provide a humanoid robot swarm path planning system, including: The acquisition unit is used to acquire the current distance between any two humanoid robots on the initial path, the first distance in the previous acquisition cycle, the first path redundancy of any one of the two humanoid robots to the target point and the first priority of the current task, the second path redundancy of the other of the two humanoid robots to the target point and the second priority of the current task; The first processing unit is configured to determine whether any two humanoid robots are in a first state based on the current distance and the first distance. The second processing unit is used to determine, based on the first priority, the first path redundancy, the second priority, and the second path redundancy, one of the humanoid robots that needs to replan its path and to perform path planning when any two of the humanoid robots are in the first state.

[0015] On the other hand, this application also provides a path planning device for a humanoid robot swarm, comprising: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a humanoid robot swarm path planning method as described in any one of the inventions.

[0016] In addition, this application also provides a computer-readable storage medium storing processor-executable instructions, which, when executed by a processor, are used to perform a humanoid robot swarm path planning method as described in any of the preceding claims.

[0017] The advantages and beneficial effects of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application: This application can obtain the current distance between any two humanoid robots on the initial path, the first distance from the previous collection cycle, the first path redundancy from any one of the humanoid robots to the target point, the first priority of the current task, the second path redundancy from the other humanoid robot to the target point, and the second priority of the current task. Based on the current distance and the first distance, it determines whether any two humanoid robots are in a first state. When any two humanoid robots are in the first state, based on the first priority, the first path redundancy, the second priority, and the second path redundancy, it determines one of the humanoid robots that needs to replan its path and performs path planning. This application determines one of two humanoid robots that needs to replan its route by using the path redundancy from the robot to the target point and the priority of the robot task, and performs path planning for it. This application can improve local congestion and deadlock in robot operation and improve the smoothness of robot cluster operation. Attached Figure Description

[0018] Figure 1 This is a schematic diagram illustrating the steps of a humanoid robot swarm path planning method in a specific embodiment of the present invention; Figure 2 This is a flowchart illustrating the path planning process of the robot's initial path planning module in a specific embodiment of the present invention. Figure 3 This is a flowchart illustrating the dynamic path adjustment module's path adjustment in a specific embodiment of the present invention. Figure 4 This is a flowchart illustrating how a multi-robot coordination and collision avoidance module achieves collision avoidance in a specific embodiment of the present invention; Figure 5 This is a flowchart illustrating the task allocation and scheduling module's task allocation and scheduling process in a specific embodiment of the present invention; Figure 6 This is a flowchart illustrating the path planning method for a humanoid robot swarm in another specific embodiment of the present invention; Figure 7 This is a schematic diagram of a humanoid robot swarm path planning system in a specific embodiment of the present invention; Figure 8This is a schematic diagram of a humanoid robot swarm path planning device in a specific embodiment of the present invention. Detailed Implementation

[0019] The principles and processes of the humanoid robot swarm path planning method, system, device, and storage medium of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Reference Figure 1 This embodiment provides a path planning method for a humanoid robot swarm. The method may include steps S101-S103.

[0021] S101. Obtain the current distance between any two humanoid robots on the initial path, the first distance of the previous collection cycle, the first path redundancy of any humanoid robot to the target point and the first priority of the current task, the second path redundancy of the other humanoid robot to the target point and the second priority of the current task.

[0022] Understandably, the initial path can be a path calculated using a predetermined algorithm. However, as the surrounding environment changes, any two humanoid robots on the initial path will dynamically change their paths. The current distance can be the distance between any two robots within the same data acquisition cycle. Each robot can be equipped with sensors, and each sensor has several fixed data acquisition cycles. The duration of each acquisition cycle ensures that the sensors can successfully acquire data. The time difference between any two adjacent acquisition cycles for the same robot can be a fixed time difference. Priority and path redundancy can be obtained from the robot's processor or database.

[0023] In some feasible embodiments of this application, the processor can first establish a wired or wireless connection with the robot. After establishing the connection, the processor can obtain from the robot's processor or database the current distance between any two humanoid robots on the initial path, the first distance from the previous acquisition cycle, the first path redundancy from any humanoid robot to the target point, the first priority of the current task, the second path redundancy from the other humanoid robot to the target point, and the second priority of the current task.

[0024] S102. Based on the current distance and the first distance, determine whether any two humanoid robots are in the first state.

[0025] In this embodiment, after obtaining the current distance and the first distance, the processor can determine whether any two humanoid robots are in a first state. The first state can be used to characterize the movement state of any two robots being close to each other or in conflict.

[0026] S103. When any two humanoid robots are in the first state, determine the humanoid robot that needs to replan its path based on the first priority, the first path redundancy, the second priority, and the second path redundancy, and perform path planning.

[0027] In some feasible embodiments of this application, when any two humanoid robots are in a state of close proximity or in a state of conflict, the processor can determine the humanoid robot that needs to replan its path based on a first priority, a first path redundancy, a second priority, and a second path redundancy, and then perform path planning. Specifically, in this embodiment, path planning can involve avoiding the robot that needs to replan its path, allowing the other humanoid robot to pass first.

[0028] In summary, this embodiment can obtain the current distance between any two humanoid robots on the initial path, the first distance from the previous collection cycle, the first path redundancy from any one humanoid robot to the target point, the first priority of the current task, the second path redundancy from the other humanoid robot to the target point, and the second priority of the current task. Based on the current distance and the first distance, it is determined whether any two humanoid robots are in a first state. When any two humanoid robots are in the first state, based on the first priority, the first path redundancy, the second priority, and the second path redundancy, one humanoid robot that needs to replan its path is identified and path planning is performed. This embodiment determines the robot that needs to replan its route among two humanoid robots by using the path redundancy from the robot to the target point and the priority of the robot task, and performs path planning for it. This embodiment can improve local congestion and deadlock in robot operation and improve the smoothness of robot cluster operation.

[0029] Furthermore, in some feasible embodiments of this application, the first state may include a state in which two humanoid robots are approaching each other and a state in which two humanoid robots are in conflict.

[0030] Furthermore, the step of determining whether any two humanoid robots are in the first state based on the current distance and the first distance may specifically include step S201 or step S202.

[0031] S201. When the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is greater than a constant 0, determine that any two humanoid robots are in a state where the two humanoid robots are approaching each other.

[0032] S202. When the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is equal to a constant 0, determine that any two humanoid robots are in a state of conflict between the two humanoid robots.

[0033] In some feasible embodiments of this application, when the current distance is less than or equal to a preset threshold, and the current distance is less than a first distance, and the current distance is greater than a constant 0, the processor can determine that any two humanoid robots are in a state where they are approaching each other. When the current distance is less than or equal to a preset threshold, and the current distance is less than a first distance, and the current distance is equal to a constant 0, the processor can determine that any two humanoid robots are in a state where they are in conflict.

[0034] Furthermore, the step of determining a humanoid robot that needs to replan its path based on the first priority, the first path redundancy, the second priority, and the second path redundancy, and then performing path planning, may specifically include steps S301-S303.

[0035] S301. Determine the first planning priority of any humanoid robot based on the first priority and the first path redundancy.

[0036] S302. Based on the second priority and the second path redundancy, determine the second planning priority of another humanoid robot.

[0037] S303. Based on the first planning priority and the second planning priority, identify a humanoid robot whose path needs to be replanned and perform path planning.

[0038] In some feasible embodiments of this application, the processor can determine the first planning priority of any humanoid robot based on a first priority and a first path redundancy, and determine the second planning priority of another humanoid robot based on a second priority and a second path redundancy. Based on the first and second planning priorities corresponding to the two humanoid robots respectively, the processor can ultimately determine the humanoid robot whose path needs to be replanned and perform path planning.

[0039] Furthermore, in some feasible embodiments of this application, the step of determining the first planning priority of any humanoid robot based on the first priority and the first path redundancy may specifically include: The first priority and the first path redundancy are input into the planning priority determination equation to determine the first planning priority of any humanoid robot. The planning priority determination equation is as follows: .

[0040] in, Pi is the first priority in the planning process. This represents the redundancy of the first path. , There are two weighting coefficients. + =1.

[0041] Furthermore, in some feasible embodiments of this application, the step of determining any humanoid robot whose path needs to be replanned based on the first planning priority and the second planning priority, and performing path planning, may specifically include: The humanoid robot with the lower planning priority in the first and second planning priorities is identified as the one whose path needs to be replanned, and path planning is performed.

[0042] Furthermore, the first path redundancy is obtained through steps S401 and S402, or through steps S401 and S403.

[0043] S401. Obtain the initial number of planned paths for the humanoid robot.

[0044] S402. When the number of planned paths is 1, the length of the initial planned path of the humanoid robot is used as the first path redundancy.

[0045] S403. When the number of planned paths is greater than 1, the initial number of planned paths shall be used as the first path redundancy.

[0046] In some feasible embodiments of this application, the processor can obtain the initial number of planned paths for the humanoid robot. When the number of planned paths is 1, the processor can use the length of the initial planned path of the humanoid robot as the first path redundancy. When the number of planned paths is greater than 1, the processor can use the initial number of planned paths as the first path redundancy.

[0047] The specific implementation principle of this application is explained below with reference to the accompanying drawings: Reference Figures 2-6 This embodiment can improve the problems of local congestion and deadlock in path planning of humanoid robot swarms, and enhance the coordination and autonomy of robots in complex environments. The method of this embodiment can be programmed into each functional module.

[0048] The processing details of each functional module are described in detail below: 1. The robot's initial path planning module is executed in two steps: S11 and S12.

[0049] S11. Initialize the path using the OCra* algorithm: The OCra* (Optimal Cooperative Replanning A*) algorithm is a multi-robot path planning algorithm that can generate the optimal path while considering dynamic environments and multi-robot coordination. During initialization, each robot obtains its start and end positions and establishes a preliminary path from the start to the end.

[0050] S12. Path Generation: The OCra* algorithm is used to calculate the initial path for each robot. This path avoids static obstacles and the initial positions of other robots as much as possible in the global scope, ensuring the global optimality of the path.

[0051] 2. The path dynamic adjustment module is executed in steps S21 and S22.

[0052] S21. Real-time environmental perception: Each robot is equipped with sensors to perceive dynamic changes in the surrounding environment in real time, including changes in the position of obstacles and other robots.

[0053] S22. Path Adjustment: The robot's path is dynamically adjusted based on real-time environmental information. The OCra* algorithm recalculates the path during dynamic adjustment to ensure the robot can avoid new obstacles and adjust the path to avoid potential collisions.

[0054] 3. The multi-robot coordination and collision avoidance module executes processes S31 and S32.

[0055] S31. Application of Push and Rotation Algorithms: When multiple robots collide or approach each other on a path, push and rotation algorithms are used for coordination. This algorithm uses push and rotation operations to allow one robot to temporarily yield the path, enabling other robots to pass smoothly and thus avoiding congestion and deadlock.

[0056] S32. Conflict Detection and Resolution: The system continuously monitors potential conflict points on the robot's path. When a conflict is detected, it automatically invokes push and rotate algorithms to adjust and coordinate the path.

[0057] 4. The task allocation and scheduling module executes processes S41 and S42. S41. Task Allocation: Based on the robot's position and task priority, allocate tasks reasonably to ensure that each robot has a clear task objective.

[0058] S42. Task Scheduling: During task execution, dynamically adjust task allocation and scheduling strategies to cope with environmental changes and task priority adjustments.

[0059] 5. The system integration and optimization module executes processes S51 and S52.

[0060] S51. Path Optimization: Combining the advantages of OCra* and push and rotate algorithms, the path planning is comprehensively optimized to ensure the optimality and coordination of the path.

[0061] S52. Algorithm Integration: Seamlessly integrate OCra* and push and rotate algorithms into the robot control system to achieve efficient path planning and coordination through modular design.

[0062] In other embodiments, the method of this application is used for path planning of humanoid robot swarms in a warehousing and logistics environment.

[0063] 1. Experimental Environment A simulated warehouse logistics environment includes multiple shelves, narrow aisles, and randomly placed obstacles. Several humanoid robots are deployed in the environment to perform handling tasks.

[0064] 2. Experimental Procedure Step a1: Initial Path Planning. Each robot determines its start and end points according to the task requirements. An initial path is generated for each robot using the OCra* algorithm. The path avoids static obstacles and the initial positions of other robots globally as much as possible, ensuring global optimality.

[0065] Step a2: Dynamic Path Adjustment. During path execution, the robot uses sensors to perceive environmental changes in real time. Based on this real-time environmental information, the path is dynamically adjusted. The OCra* algorithm recalculates the path during the adjustment process, ensuring the robot can avoid new obstacles and adjust the path to prevent potential collisions.

[0066] Step a3: Multi-robot coordination and collision avoidance. The system continuously monitors potential conflict points on the robot paths.

[0067] When a conflict is detected, a push and rotate algorithm is invoked for coordination. Through push and rotate operations, one robot temporarily yields the passage to allow other robots to pass smoothly, avoiding congestion and deadlock.

[0068] Step a4: Task Allocation and Scheduling. Based on the robot's location and task priority, allocate tasks reasonably to ensure each robot has a clear task objective. During task execution, dynamically adjust the task allocation and scheduling strategy to adapt to environmental changes and task priority adjustments.

[0069] Step a5: System Integration and Optimization. Comprehensive optimization of path planning, combining the advantages of OCra* and push / rotate algorithms, ensures optimal path performance and coordination.

[0070] Seamlessly integrate OCra* and push and rotate algorithms into the robot control system to achieve efficient path planning and coordination through modular design.

[0071] Furthermore, the push and rotate algorithm may specifically include a collision and proximity judgment algorithm, as well as push and rotate operations.

[0072] In multi-robot path planning, conflict and proximity detection is a crucial step. By using conflict and proximity detection algorithms to determine the positional relationships of multiple robots on the path, the system can coordinate operations in a timely manner.

[0073] The specific conflict resolution algorithm is as follows: Set up a robot and In time The position is and Then the condition for conflict determination is:

[0074] The algorithm steps include steps c1-c3.

[0075] c1. Calculate the current position: time step Location and .

[0076] c2. Compare Positions: Determine if the two robots occupy the same position at the same time step, i.e., whether the condition is met. .

[0077] c3. Mark conflict: If the condition is met, mark it as a conflict; otherwise, continue.

[0078] The proximity judgment algorithm is as follows: Set up a robot and In time The position is and The safe distance between robots is Then the condition for making a judgment is:

[0079] The algorithm steps include steps d1-d3.

[0080] d1. Calculate distance: Calculate robot and At time step Euclidean distance between .

[0081] d2. Compare distance: Compare the calculated distance with the preset safety distance. Compare them.

[0082] d3. Mark proximity: If the distance is less than or equal to and If the result is positive, mark it as close; otherwise, continue.

[0083] Push and Rotate Operations: After identifying conflicts or proximity, the push and rotate algorithms resolve these issues through push and rotate operations.

[0084] Push Operation: The push operation aims to temporarily move one robot to a nearby available location to allow other robots to pass. Specifically, selecting the push target: Typically, a robot with less impact is selected for the push, based on criteria such as the robot's path redundancy to the target point or the priority of the current task. Finding an available location: Searching for available locations around the robot. And ensure that the location does not conflict with the paths of other robots.

[0085] Perform push: Move the selected robot to The location is recorded, the action is observed, and other robots are notified to update their path planning.

[0086] Furthermore, the formula for selecting push recipients. First, define the rating function for the push object. This function is for each robot A comprehensive score is calculated, and robots with lower scores are more suitable for being pushed to users.

[0087]

[0088] in: It's a robot. The first priority of the plan (the lower the priority, the easier it is to push).

[0089] It's a robot. The path redundancy to the target point can be defined as the robot's redundancy. The number of alternative paths available, or the length of the shortest path from the origin to the destination.

[0090] It's a robot. The task priority is indicated by a higher value, meaning the task has a higher priority. If the priority is lower, the robot is more likely to be pushed to the task.

[0091] and These are weighting parameters used to adjust the influence of path redundancy and task priority on the overall score. You can adjust these weights according to specific circumstances to balance different factors.

[0092] Path redundancy It can be calculated in the following ways: If the robot has an alternative path: Definition = ,in This represents the number of valid paths that robot iii can choose.

[0093] If the robot does not have an alternative path: the length of the main path can be used as redundancy, for example... = ,in It is the length of the main path.

[0094] Task Priority

[0095] Task Priority Priority tasks are typically defined based on their urgency, impact on the overall system, or timeframe. Higher priority tasks require more time from the robot. It's not suitable for being pushed. For all robots, calculation... ,choose The smallest robot is used as the target for delivery.

[0096] Specifically, if there are any two robots, the weights =0.7, =0.3, and the path redundancy of robot 1 is... =5, task priority =Path redundancy of robot 2 =2, task priority =5. Therefore, their scores are as follows:

[0097] .

[0098] In addition, refer to Figure 7 ,and Figure 1 Corresponding to the method described above, this application also provides a humanoid robot swarm path planning system in its embodiments. The system may include: an acquisition unit 1001, a first processing unit 1002, and a second processing unit 1003. The acquisition unit 1001 can be used to acquire the current distance between any two humanoid robots on the initial path, the first distance from the previous acquisition cycle, the first path redundancy from any one humanoid robot to the target point, the first priority of the current task, the second path redundancy from the other humanoid robot to the target point, and the second priority of the current task. The first processing unit 1002 can be used to determine whether any two humanoid robots are in a first state based on the current distance and the first distance. The second processing unit 1003 can be used to, when any two humanoid robots are in the first state, determine the humanoid robot whose path needs to be replanned based on the first priority, the first path redundancy, the second priority, and the second path redundancy, and perform path planning.

[0099] It should be noted that the acquisition unit can be any integrated circuit unit or microprocessor unit obtained by integrating a chip with processing functions and its peripheral circuits using existing integration technology. Similarly, the first processing unit and the second processing unit can also be any integrated circuit module or microprocessor module obtained by integrating a chip with processing functions and its peripheral circuits using existing integration technology. Furthermore, the first processing unit and the second processing unit may include one or more memories. These memories can be used to store the specific algorithm for route planning in this application.

[0100] The acquisition unit 1001 can transmit the acquired data to the processor via a wired or wireless connection with the processor of the processing unit 1002. The processor of the processing unit 1002 can process the data through its internal chip to obtain the search results. The specific connection method and device configuration between the acquisition unit 1001 and the first processing unit 1002, and between the first processing unit 1002 and the second processing unit 1003, are not limited.

[0101] It should be noted that the content of the above-described humanoid robot swarm path planning method embodiments is applicable to the humanoid robot swarm path planning system embodiments. The specific functions implemented by the humanoid robot swarm path planning system embodiments are the same as those of the above-described humanoid robot swarm path planning method embodiments, and the beneficial effects achieved are also the same as those achieved by the above-described humanoid robot swarm path planning method embodiments.

[0102] and Figure 1 Corresponding to the method described herein, embodiments of this application also provide a humanoid robot swarm path planning device, the specific structure of which can be referred to... Figure 8 ,include: At least one processor 1011; At least one memory 1012 is used to store at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the humanoid robot cluster path planning method.

[0103] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0104] and Figure 1 Corresponding to the method described above, embodiments of this application also provide a computer-readable storage medium storing processor-executable instructions, which, when executed by a processor, are used to perform the humanoid robot swarm path planning method.

[0105] The content of the above-described humanoid robot swarm path planning method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above-described humanoid robot swarm path planning method embodiments, and the beneficial effects achieved are also the same as those achieved in the above-described humanoid robot swarm path planning method embodiments.

[0106] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0107] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0108] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0110] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0111] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0112] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0113] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0114] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A humanoid robot cluster path planning method, characterized in that: The following steps are involved: Obtaining the current distance between any two humanoid robots on the initial path, the first distance of the current distance in a previous acquisition cycle, the first path redundancy of any one of the two humanoid robots to the target point and the first priority of the current task, and the second path redundancy of the other of the two humanoid robots to the target point and the second priority of the current task; Determining whether any two of the humanoid robots are in a first state according to the current distance and the first distance; When any two of the humanoid robots are in the first state, one of the humanoid robots that needs to replan its path is determined and path planning is performed according to the first priority, the first path redundancy, the second priority, and the second path redundancy.

2. According to claim 1, a humanoid robot cluster path planning method is characterized in that: The first state includes a state in which the two humanoid robots are approaching each other and a state in which the two humanoid robots are in conflict.

3. According to claim 2, a humanoid robot cluster path planning method is characterized in that: The determining, according to the current distance and the first distance, whether the two humanoid robots are in the first state specifically includes: When the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is greater than a constant 0, it is determined that the two humanoid robots are in a state where the two humanoid robots are approaching each other; When the current distance is less than or equal to a preset threshold, and the current distance is less than the first distance, and the current distance is equal to a constant 0, it is determined that the arbitrary two humanoid robots are in a conflict state.

4. The humanoid robot cluster path planning method according to claim 1, characterized in that: The determining a humanoid robot that needs to re-plan a path and performing path planning according to the first priority, the first path redundancy, the second priority, and the second path redundancy specifically includes: Determining a first planning priority of any one of the humanoid robots according to the first priority and the first path redundancy; Determining a second planning priority of another of the humanoid robots according to the second priority and the second path redundancy; According to the first planning priority and the second planning priority, a humanoid robot that needs to replan its path is determined and path planning is performed.

5. A humanoid robot cluster path planning method according to claim 4, characterized in that: The determining the first planning priority of any humanoid robot according to the first priority and the first path redundancy specifically includes: The first priority and the first path redundancy are input into a planning priority determination equation to determine the first planning priority of any humanoid robot; wherein the planning priority determination equation is: ; in, The first planning priority, P i As the first priority, is the first path redundancy; , are two weight coefficients, + =1.

6. A humanoid robot cluster path planning method according to claim 4, characterized in that: The determining, according to the first planning priority and the second planning priority, any humanoid robot that needs to replan its path and performing path planning specifically includes: A humanoid robot having a lower planning priority among the first planning priority and the second planning priority is determined as a humanoid robot that needs to replan a path, and path planning is performed.

7. The humanoid robot cluster path planning method according to claim 1, characterized in that: The first path redundancy is obtained by the following steps: Obtain the number of initial planned paths of the humanoid robot; When the number of planned paths is 1, the length of the initial planned path of the humanoid robot is used as the first path redundancy; When the number of planned paths is greater than 1, the number of initial planned paths is used as the first path redundancy.

8. A humanoid robot cluster path planning system, characterized in that: include: An acquisition unit, used for acquiring a current distance between any two humanoid robots on an initial path, a first distance of the current distance in a previous acquisition cycle, a first path redundancy from any one of the two humanoid robots to a target point and a first priority of a current task, and a second path redundancy from the other of the two humanoid robots to a target point and a second priority of the current task; a first processing unit, configured to determine whether any two of the humanoid robots are in a first state according to the current distance and the first distance; The second processing unit is used to determine one of the humanoid robots that needs to replan its path and perform path planning based on the first priority, the first path redundancy, the second priority and the second path redundancy when any two of the humanoid robots are in the first state.

9. A humanoid robot cluster path planning device, characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the humanoid robot cluster path planning method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions executable by a processor, characterized in that: The processor-executable instructions are used to execute a humanoid robot cluster path planning method as described in any one of claims 1-7 when executed by the processor.

Citation Information

Patent Citations

  • Multi-AGV anti-collision cooperative path planning method

    CN110989570A

  • Coordinated motion planning method of multi-robot vision detection system based on multi-stage task allocation

    CN111975767A

  • Multi-AGV path planning method and device based on dynamic priority express distribution center

    CN115097843A

  • Systems and methods for centralized control of a fleet of robotic devices

    US20220197304A1

  • Parking AGV route planning method based on improved ant colony algorithm

    WO2021189720A1

Cited By

  • Autonomous navigation method, system, program product and equipment for building robot cluster

    CN121067869A