Group robot cooperation method and device, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of robot control, and discloses a swarm robot cooperation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the task information of a to-be-allocated task and the robot information of a swarm robot, and carrying out the task allocation of a to-be-allocated task according to the task information and the robot information through a task allocation model; dividing a to-be-allocated task to the robot with the minimum cost function value in the group robots, performing path planning on the robot receiving the to-be-allocated task according to the navigation target function to obtain task path information, controlling the robot to move to a corresponding task site based on the task path information, and performing task allocation in the process of moving to the corresponding task site. Controlling the swarm robots to cooperate according to the conflict prediction model and the state updating model; through the task distribution model, the navigation objective function, the conflict prediction model and the state updating model, the swarm robots are cooperatively controlled, and the cooperation efficiency of the swarm robots is improved.

Description

Technical Field

[0001] The present application relates to the technical field of controlling robots, and more specifically, to a group robot collaboration method, device, electronic device and storage medium. Background Art

[0002] In recent years, multi-robot systems (MRS) have been widely used in the fields of industry, services and emergency rescue. Compared with a single robot system, swarm robots can effectively complete complex tasks through the collaborative work of multiple individuals. They are highly applicable to scenarios such as sorting and handling of multiple items in warehousing and logistics, multi-point coverage in security inspections, and search and rescue in disaster scenarios.

[0003] Although swarm robots have shown great potential in improving task flexibility, efficiency and robustness, there are still many technical bottlenecks in distributed navigation and collaboration. In terms of navigation and path planning, swarm robots rely on local perception and neighborhood communication to independently plan paths. However, the decentralized nature of distributed navigation leads to the lack of a global perspective of robots, and they can only make decisions on path selection based on perception information within a limited range. In addition, traditional path planning methods often only focus on the path optimality of a single robot, ignoring the coordination of the overall behavior of swarm robots. In terms of task allocation and collaboration, existing task allocation methods are mostly static allocations, which cannot effectively cope with task changes in dynamic environments. In terms of system robustness and stability, when some robots fail due to faults or communication is interrupted, existing systems usually lack the ability to respond quickly and dynamically recover.

[0004] Therefore, in order to solve the technical problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in dynamic environments in task allocation and collaboration, a swarm robot collaboration method, device, electronic device and storage medium are urgently needed. Summary of the invention

[0005] The purpose of the present application is to provide a swarm robot collaboration method, device, electronic device and storage medium, which control the swarm robots to execute the assigned tasks through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, collaboratively control the swarm robots to avoid collisions according to a preset conflict prediction model and a preset state update model, thereby solving the problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in dynamic environments in task allocation and collaboration. The dynamic control method is used to optimize the path conflict problems, task allocation problems and collaborative cooperation problems of swarm robots in a real-time environment, thereby improving the collaborative efficiency of swarm robots.

[0006] In a first aspect, the present application provides a group robot collaboration method, comprising: Obtaining task information of the task to be assigned and robot information of the swarm robot; By using a preset task allocation model, according to the task information and the robot information, the task to be allocated is allocated to the robot with the smallest cost function value in the group of robots; According to a preset navigation objective function, a path planning is performed on the robot that receives the task to be assigned to obtain task path information; Based on the task path information, control the robot that has received the task to be assigned to move to a corresponding task location to perform the task to be assigned; In the process of moving to the corresponding task location, the group robots are controlled to cooperate in a coordinated manner according to a preset conflict prediction model and a preset state update model to avoid collision.

[0007] The swarm robot collaboration method provided in the present application can realize the control of swarm robots. Through a preset task allocation model and a preset navigation objective function, the swarm robots are controlled to execute the assigned tasks. In the process of moving to the corresponding task location, the swarm robots are collaboratively controlled to avoid collisions according to a preset conflict prediction model and a preset state update model. This solves the problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in dynamic environments in task allocation and collaboration. Through a dynamic control method, the path conflict problems, task allocation problems and collaborative cooperation problems of swarm robots are optimized in a real-time environment, thereby improving the collaborative efficiency of swarm robots.

[0008] Optionally, the task to be assigned is assigned to a robot with the smallest cost function value in the swarm of robots according to the task information and the robot information through a preset task assignment model, including: By using a preset task allocation model, according to the task information and the robot information, a cost function value of dividing the task to be allocated to each robot in the group of robots is calculated; Extracting the minimum value among the cost function values; The task to be assigned is divided into the robot corresponding to the minimum value of the cost function value.

[0009] The swarm robot collaboration method provided in the present application can realize the control of swarm robots. Through a preset task allocation model, the tasks to be assigned are divided into the robots with the smallest cost function value in the swarm robots. The robots with the smallest cost function value perform the corresponding tasks to be assigned, which is beneficial to improving the collaboration efficiency of swarm robots.

[0010] Optionally, in the process of moving to the corresponding task location, according to a preset conflict prediction model and a preset state update model, the group robots are controlled to cooperate to avoid collision, including: In the process of moving to the corresponding task location, periodically obtaining the relative distance between each robot in the group of robots; According to a preset conflict prediction model and a preset state update model, a conflict analysis is performed on the robots whose relative distance is less than a preset conflict distance, and a conflict risk value is calculated; Adjusting the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance to obtain an adjusted conflict path; Based on the adjusted conflict path, corresponding robots in the swarm of robots are controlled to move to avoid collision among the swarm of robots.

[0011] The swarm robot collaboration method provided in the present application can realize the control of swarm robots. After calculating the conflict risk value of the robot through a preset conflict prediction model and a preset state update model, the path of the robot whose conflict risk value is greater than a preset safety threshold is adjusted within a preset conflict distance to obtain an adjusted conflict path. The swarm robots are controlled by the adjusted conflict path, which is beneficial to improving the collaboration efficiency of the swarm robots.

[0012] Optionally, periodically acquiring the relative distance between each robot in the swarm robot comprises: Periodically obtaining the real-time position of each robot in the swarm of robots; The relative distances between the robots are calculated based on the real-time positions.

[0013] Optionally, according to a preset conflict prediction model and a preset state update model, conflict analysis is performed on the robots whose relative distance is less than a preset conflict distance, and a conflict risk value is calculated, including: Determine whether the relative distance between the robots is less than the preset conflict distance; If so, after updating the states of the robots whose relative distances are less than the preset conflict distance according to the preset state update model, the conflict risk values ​​between the robots whose relative distances are less than the preset conflict distance after the state update are calculated based on the preset conflict prediction model; If not, the robot whose relative distance is greater than or equal to the preset conflict distance is controlled to move according to the task path information.

[0014] Optionally, adjusting the path of the robot whose conflict risk value is greater than a preset safety threshold within a preset conflict distance to obtain an adjusted conflict path includes: Determine whether the conflict risk value between the robots is greater than a preset safety threshold; If yes, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted through a preset speed adjustment model to obtain an adjusted conflict path; If not, the robot whose conflict risk value is less than or equal to the preset safety threshold is controlled to move according to the task path information.

[0015] Optionally, the preset status update model is specifically: ; The preset conflict prediction model is specifically: ; Among them, x i (t+1) is the state vector of robot i at time t+1; x i (t) is the state vector of robot i at time t; ϵ is the learning rate, that is, the amplitude of the robot state update; is the communication weight between robot i and robot j; N i is the set of robots within the preset conflict distance of robot i; x j (t) is the state vector of robot j at time t; R ij (t) is the conflict risk value between robot i and robot j at time t; is an exponential function with the natural constant e as base, The natural constant e power; p i (t) is the current position of robot i at time t; p j (t) is the current position of robot j at time t; is the norm symbol; is the conflict range parameter.

[0016] In a second aspect, the present application provides a group robot collaboration device, comprising: An acquisition module, used to acquire task information of the task to be assigned and robot information of the swarm robot; A division module, used for dividing the to-be-assigned task to the robot with the smallest cost function value in the group of robots according to the task information and the robot information through a preset task allocation model; A planning module, used to plan a path for the robot that has received the task to be assigned according to a preset navigation objective function, and obtain task path information; A moving module, used for controlling the robot that has received the task to be assigned to move to a corresponding task location to perform the task to be assigned based on the task path information; The collaboration module is used to control the group robots to collaborate to avoid collisions according to a preset conflict prediction model and a preset state update model during the process of moving to the corresponding task location.

[0017] The swarm robot collaborative device controls the swarm robots to execute the assigned tasks through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, according to a preset conflict prediction model and a preset state update model, collaboratively controls the swarm robots to avoid collisions. This solves the problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in a dynamic environment in task allocation and collaboration. It optimizes the path conflict problems, task allocation problems and collaborative cooperation problems of swarm robots in a real-time environment through a dynamic control method, thereby improving the collaborative efficiency of swarm robots.

[0018] In a third aspect, the present application provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, it runs the steps in the group robot collaboration method described above.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, runs the steps in the swarm robot collaboration method described above.

[0020] Beneficial effects: The swarm robot collaboration method, device, electronic device and storage medium provided in the present application control the swarm robots to perform the assigned tasks through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, collaboratively control the swarm robots to avoid collisions according to a preset conflict prediction model and a preset state update model. This solves the problem that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in dynamic environments in task allocation and collaboration. It optimizes the path conflict problems, task allocation problems and collaborative cooperation problems of swarm robots in a real-time environment through a dynamic control method, thereby improving the collaborative efficiency of swarm robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1A flowchart of a group robot collaboration method provided in an embodiment of the present application.

[0022] Figure 2 A schematic diagram of the structure of a group robot collaboration device provided in an embodiment of the present application.

[0023] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0024] Explanation of reference numerals: 1. Acquisition module; 2. Division module; 3. Planning module; 4. Movement module; 5. Collaboration module; 301. Processor; 302. Memory; 303. Communication bus. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] Please refer to Figure 1 , Figure 1 A group robot collaboration method in some embodiments of the present application is used to control the group robots, comprising the steps of: Step S101, obtaining task information of the task to be assigned and robot information of the swarm robot; Step S102, using a preset task allocation model, according to task information and robot information, the task to be allocated is allocated to the robot with the smallest cost function value in the group of robots; Step S103, performing path planning for the robot that has received the task to be assigned according to a preset navigation objective function to obtain task path information; Step S104, based on the task path information, controlling the robot that has received the task to be assigned to move to the corresponding task location to perform the task to be assigned; Step S105 , in the process of moving to the corresponding task location, the group robots are controlled to cooperate according to the preset conflict prediction model and the preset state update model to avoid collision.

[0028] The swarm robot collaboration method controls the swarm robots to execute the assigned tasks through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, collaboratively controls the swarm robots to avoid collision according to a preset conflict prediction model and a preset state update model. This solves the problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in a dynamic environment in task allocation and collaboration. The path conflict problem, task allocation problem and collaborative cooperation problem of the swarm robots are optimized in a real-time environment through a dynamic control method, thereby improving the collaborative efficiency of the swarm robots.

[0029] Specifically, in step S101, task information of the task to be assigned and robot information of the swarm robot are obtained, wherein the task information includes the task priority, task location, and energy consumption required to complete the task to be assigned, and the robot information includes the location and remaining energy of each robot.

[0030] Specifically, in step S102, the task to be assigned is divided into the robot with the smallest cost function value in the group of robots according to the task information and the robot information through the preset task assignment model, including: Through the preset task allocation model, according to the task information and robot information, the cost function value of each robot in the group robot is calculated; Extract the minimum value of the cost function; Divide the task to be assigned to the robot corresponding to the minimum value of the cost function.

[0031] In step S102, the corresponding task information and robot information are input into the preset task allocation model, and the cost function value of each robot in the group robot is calculated. The preset task allocation model is specifically: ; in, is the cost function value; k is the kth task (task to be assigned), that is, task k; N is the total number of robots; M is the total number of tasks; w k is the importance weight of task k (the importance weight can be set according to actual needs, for example, it can be calculated using a preset conversion formula based on the task priority); d ik is the straight-line distance from the ith robot (i.e., robot i) to task k; E iis the remaining energy of robot i; E max is the standard maximum energy value of the swarm robot; λ is the energy balance coefficient, which is used to prevent high-energy-consuming robots from performing unnecessary tasks.

[0032] The minimum value is extracted from the cost function value, and the task to be assigned corresponding to the minimum value is divided into the corresponding robot.

[0033] In some optional embodiments, when an emergency occurs (such as the arrival of a new task, low battery of the robot (such as the robot makes multiple path adjustments during operation to avoid collisions, resulting in insufficient battery to complete the task), robot failure, or robot communication interruption), task reallocation will be automatically triggered. For example, in complex warehousing tasks, the robot can dynamically adjust the allocation plan based on factors such as the urgency of the task and the status of resources, significantly reducing the time to complete the task. This resource-aware task allocation method has significant adaptability in a dynamic environment.

[0034] Specifically, in step S103, the preset navigation objective function not only focuses on the optimality of the path length, but also introduces obstacle avoidance cost and energy consumption. Through the preset navigation objective function, the robot that receives the task to be assigned is path planned to obtain task path information. The preset navigation objective function is specifically: ; in, is the navigation objective function value; L(t) is the path length, which represents the time cost for the robot to complete the task; C obstacle (t) is the obstacle avoidance cost, which can be determined by the robot obtaining a safe path generated by the dynamic obstacle distribution (for example, it can be calculated using a preset obstacle avoidance calculation formula based on the local obstacle avoidance route and the corresponding additional energy consumption); E(t) is the energy consumption; α, β and γ are path weight parameters, obstacle avoidance weight parameters and energy weight parameters, respectively; [t0, t f ] is the time integration interval, t0 is the minimum value of the time integration interval (i.e. the task start time), t f is the maximum value of the time integration interval (i.e., task completion time).

[0035] In step S103, multiple operation paths are first generated through algorithms such as A* algorithm, Dijkstra algorithm or ant algorithm (A* algorithm, Dijkstra algorithm or ant algorithm are existing technologies and are not described in detail here), and then considering the path length, obstacle avoidance cost and energy consumption, the data corresponding to each operation path is input into the preset navigation objective function, and the navigation objective function value of each operation path is calculated to extract the operation path corresponding to the minimum value from the navigation objective function values ​​of each operation path to obtain the task path information.

[0036] Specifically, in step S104, the robot that has received the task to be assigned is controlled to move according to the task path information to move to the corresponding task location to perform the task to be assigned.

[0037] Specifically, in step S105, in the process of moving to the corresponding task location, according to the preset conflict prediction model and the preset state update model, the group robots are controlled to cooperate to avoid collision, including: In the process of moving to the corresponding task location, the relative distance between each robot in the swarm robot is periodically obtained; According to the preset conflict prediction model and the preset state update model, conflict analysis is performed on robots whose relative distance is less than the preset conflict distance, and the conflict risk value is calculated; The path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted to obtain an adjusted conflict path; Based on the adjusted conflict path, the corresponding robots in the swarm robot are controlled to move to avoid collision among the swarm robots.

[0038] Specifically, in step S105, the relative distance between each robot in the swarm robot is periodically obtained, including: Periodically obtain the real-time position of each robot in the swarm robot; According to the real-time position, the relative distance between each robot is calculated.

[0039] In step S105, the real-time position of each robot in the swarm robot is obtained at intervals of a preset period (the preset period can be set according to actual needs), and the relative distance between each robot is calculated based on the real-time position. Each robot is equipped with a multimodal sensor (such as a laser radar, a camera, etc.), through which each robot can obtain information such as the position of surrounding obstacles, the coordinates of the target area, and the status of neighboring robots.

[0040] Specifically, in step S105, according to the preset conflict prediction model and the preset state update model, a conflict analysis is performed on the robots whose relative distance is less than the preset conflict distance (that is, according to the preset state update model, after the state of the robots whose relative distance is less than the preset conflict distance is updated, based on the preset conflict prediction model, the conflict risk value between the robots whose relative distance after the state update is less than the preset conflict distance is calculated), and the conflict risk value is calculated, including: Determine whether the relative distance between the robots is less than the preset conflict distance; If so, after updating the states of the robots whose relative distances are less than the preset conflict distance according to the preset state update model, the conflict risk values ​​between the robots whose relative distances after the state update are less than the preset conflict distance are calculated based on the preset conflict prediction model; If not, the robots whose relative distance is greater than or equal to the preset conflict distance are controlled to move according to the task path information.

[0041] In step S105, it is determined whether the relative distance between the robots is less than the preset conflict distance (the preset conflict distance can be set according to actual needs, and the neighborhood of the corresponding robot can be constructed by drawing a circle with the preset conflict distance as the radius and the robot itself as the origin). When the relative distance between any robot and other robots is less than the preset conflict distance (that is, there are other robots in the neighborhood of any robot), the robot with a relative distance less than the preset conflict distance is updated according to the preset state update model (that is, the state vector of the robots in the neighborhood is updated and synchronized, and the state vector includes the position vector (x, y, z) and velocity vector (v) of the robot in the three-dimensional space. x , v y , v z ), where x, y, and z are the horizontal, vertical, and vertical coordinates of the robot, respectively, and v x 、v y 、v z are the speeds of the robots in the horizontal, vertical and vertical directions respectively), then based on the preset conflict prediction model, the conflict risk value between the robots whose relative distance after state update is less than the preset conflict distance is calculated, wherein the preset state update model is specifically: ; Among them, x i (t+1) is the state vector of robot i at time t+1; x i (t) is the state vector of robot i at time t; ϵ is the learning rate, that is, the amplitude of the robot state update; is the communication weight between robot i and robot j; N i is the set of robots within the preset conflict distance of robot i (i.e., the set of robots in the neighborhood of robot i); x j (t) is the state vector of robot j at time t.

[0042] Through the preset state update model, information is exchanged, the states of the robots in the neighborhood are updated and synchronized, so that the state vectors of each robot obtained by the robots in the neighborhood gradually converge, thereby optimizing the collaborative behavior of the entire group. Through the state update mechanism, each robot gradually coordinates with the robots in its neighborhood on path selection and task priority until the entire group of robots reaches consistency. For example, during the execution of a task, when multiple robots need to cooperate to pass through a narrow passage, after the state is updated and synchronized, (the control system or between multiple robots) will dynamically adjust their passing order and speed, thereby significantly improving the efficiency of task completion.

[0043] The preset conflict prediction model is as follows: ; Among them, R ij (t) is the conflict risk value between robot i and robot j at time t; is an exponential function with the natural constant e as base, The natural constant e power; p i (t) is the current position of robot i at time t; p j (t) is the current position of robot j at time t; is the norm symbol; is the conflict range parameter.

[0044] Through the preset conflict prediction model, the corresponding conflict risk value can be calculated according to the position of the robot. When there is no data of the relative distance between any robot and other robots being less than the preset conflict distance, the robots whose relative distance is greater than or equal to the preset conflict distance are controlled to move according to the task path information.

[0045] Specifically, in step S105, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted to obtain an adjusted conflict path, including: Determine whether the conflict risk value between the robots is greater than the preset safety threshold; If yes, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted through the preset speed adjustment model to obtain an adjusted conflict path; If not, the robot whose conflict risk value is less than or equal to the preset safety threshold is controlled to move according to the task path information.

[0046] In step S105, it is determined whether the conflict risk value between the robots is greater than the preset safety threshold. When there is a conflict risk value greater than the preset safety threshold between the robots, the speed of the robots during movement can be adjusted through a preset speed adjustment model (wherein, speed refers to a speed vector, and adjusting the speed of the robots during movement includes numerical adjustment and directional adjustment. The movement speed of a single robot or two robots can be adjusted according to actual needs to calculate the corresponding collision integral through the preset speed adjustment model, and then the corresponding adjustment measures can be determined according to the minimum value of the collision integral) to adjust the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance to obtain an adjusted conflict path. The adjusted conflict paths of the robots are coordinated with each other to avoid collisions between the robots. The preset speed adjustment model is specifically: ; in, is the collision integral; v i (t) is the speed of robot i at time t; v j (t) is the speed of robot j at time t. The robot's movement speed is adjusted so that the collision integral reaches the minimum value after adjustment. The adjusted collision path is determined by determining the robot's movement speed corresponding to the minimum value.

[0047] In some optional embodiments, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance can be adjusted by using methods such as A* algorithm, Dijkstra algorithm or ant algorithm to obtain an adjusted conflict path. Among them, methods such as A* algorithm, Dijkstra algorithm or ant algorithm are prior arts and will not be described in detail here.

[0048] When there is no conflict risk value greater than a preset safety threshold between the robots, the robots whose conflict risk values ​​are less than or equal to the preset safety threshold are controlled to move according to the task path information.

[0049] In step S105, the corresponding robots in the swarm of robots are controlled to move according to the adjusted conflict path to avoid collision among the swarm of robots.

[0050] As can be seen from the above, the swarm robot collaboration method obtains the task information of the task to be assigned and the robot information of the swarm robots, and divides the task to be assigned to the robot with the smallest cost function value in the swarm robots according to the task information and the robot information through a preset task allocation model, and performs path planning on the robot that receives the task to be assigned according to a preset navigation objective function to obtain task path information, and controls the robot that receives the task to be assigned to move to the corresponding task location to perform the task to be assigned based on the task path information, and in the process of moving to the corresponding task location, controls the swarm robots to collaborate to avoid collision according to a preset conflict prediction model and a preset state update model; thus, the swarm robots are controlled to perform the task to be assigned through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, controls the swarm robots to collaborate to avoid collision according to a preset conflict prediction model and a preset state update model, and solves the problem that the existing swarm robot control method ignores the coordination of the swarm robots in terms of navigation and path planning, and cannot effectively cope with task changes in a dynamic environment in terms of task allocation and collaboration, and optimizes the path conflict problem, task allocation problem and collaborative cooperation problem of the swarm robots in a real-time environment through a dynamic control method, thereby improving the collaborative efficiency of the swarm robots.

[0051] refer to Figure 2 The present application provides a group robot collaboration device for controlling group robots, comprising: An acquisition module 1 is used to acquire task information of the task to be assigned and robot information of the swarm robot; A division module 2 is used to divide the task to be assigned to the robot with the smallest cost function value in the group of robots according to the task information and robot information through a preset task allocation model; The planning module 3 is used to plan the path of the robot that has received the task to be assigned according to the preset navigation objective function to obtain the task path information.

[0052] The mobile module 4 is used to control the robot that has received the task to be assigned to move to the corresponding task location to perform the task to be assigned based on the task path information; The collaboration module 5 is used to control the group robots to collaborate and avoid collisions according to a preset conflict prediction model and a preset state update model during the process of moving to the corresponding task location.

[0053] The swarm robot collaborative device controls the swarm robots to execute the assigned tasks through a preset task allocation model and a preset navigation objective function, and in the process of moving to the corresponding task location, according to a preset conflict prediction model and a preset state update model, collaboratively controls the swarm robots to avoid collisions. This solves the problems that the existing swarm robot control methods ignore the coordination of swarm robots in navigation and path planning, and cannot effectively cope with task changes in a dynamic environment in task allocation and collaboration. It optimizes the path conflict problems, task allocation problems and collaborative cooperation problems of swarm robots in a real-time environment through a dynamic control method, thereby improving the collaborative efficiency of swarm robots.

[0054] Specifically, when the acquisition module 1 is executed, it obtains the task information of the task to be assigned and the robot information of the swarm robot, wherein the task information includes the task priority, task location and energy consumption required to complete the task to be assigned, and the robot information includes the location and remaining energy of each robot.

[0055] Specifically, when the division module 2 divides the to-be-assigned task to the robot with the smallest cost function value in the group of robots according to the task information and the robot information through the preset task allocation model, it executes: Through the preset task allocation model, according to the task information and robot information, the cost function value of each robot in the group robot is calculated; Extract the minimum value of the cost function; Divide the task to be assigned to the robot corresponding to the minimum value of the cost function.

[0056] When the acquisition module 1 is executed, the corresponding task information and robot information are input into the preset task allocation model, and the cost function value of each robot in the group robot is calculated. The preset task allocation model is specifically: ; in, is the cost function value; k is the kth task (task to be assigned), that is, task k; N is the total number of robots; M is the total number of tasks; w k is the importance weight of task k (the importance weight can be set according to actual needs, for example, it can be calculated using a preset conversion formula based on the task priority); d i k is the straight-line distance from the ith robot (i.e., robot i) to task k; E i is the remaining energy of robot i; E max is the standard maximum energy value of the swarm robot; λ is the energy balance coefficient, which is used to prevent high-energy-consuming robots from performing unnecessary tasks.

[0057] The minimum value is extracted from the cost function value, and the task to be assigned corresponding to the minimum value is divided into the corresponding robot.

[0058] In some optional embodiments, when an emergency occurs (such as the arrival of a new task, low battery of the robot (such as the robot makes multiple path adjustments during operation to avoid collisions, resulting in insufficient battery to complete the task), robot failure, or robot communication interruption), task reallocation will be automatically triggered. For example, in complex warehousing tasks, the robot can dynamically adjust the allocation plan based on factors such as the urgency of the task and the status of resources, significantly reducing the time to complete the task. This resource-aware task allocation method has significant adaptability in a dynamic environment.

[0059] Specifically, when the planning module 3 is executed, the preset navigation objective function not only focuses on the optimality of the path length, but also introduces the obstacle avoidance cost and energy consumption. Through the preset navigation objective function, the robot that receives the task to be assigned is path planned to obtain the task path information. The preset navigation objective function is specifically: ; in, is the navigation objective function value; L(t) is the path length, which represents the time cost for the robot to complete the task; C obstacle (t) is the obstacle avoidance cost, which can be determined by the robot obtaining a safe path generated by the dynamic obstacle distribution (for example, it can be calculated using a preset obstacle avoidance calculation formula based on the local obstacle avoidance route and the corresponding additional energy consumption); E(t) is the energy consumption; α, β and γ are path weight parameters, obstacle avoidance weight parameters and energy weight parameters, respectively; [t0, t f ] is the time integration interval, t0 is the minimum value of the time integration interval (i.e. the task start time), t f is the maximum value of the time integration interval (i.e., task completion time).

[0060] When the planning module 3 is executed, it first generates multiple operation paths through algorithms such as the A* algorithm, the Dijkstra algorithm or the ant algorithm (the A* algorithm, the Dijkstra algorithm or the ant algorithm are existing technologies and are not described in detail here), and then considers the path length, obstacle avoidance cost and energy consumption, inputs the data corresponding to each operation path into the preset navigation objective function, calculates the navigation objective function value of each operation path, and extracts the operation path corresponding to the minimum value from the navigation objective function values ​​of each operation path to obtain the task path information.

[0061] Specifically, when the moving module 4 is executed, it controls the robot that has received the task to be assigned to move according to the task path information, so as to move to the corresponding task location to perform the task to be assigned.

[0062] Specifically, when the collaboration module 5 moves to the corresponding task location, it controls the group robots to collaborate to avoid collision according to the preset conflict prediction model and the preset state update model, and executes: In the process of moving to the corresponding task location, the relative distance between each robot in the swarm robot is periodically obtained; According to the preset conflict prediction model and the preset state update model, conflict analysis is performed on robots whose relative distance is less than the preset conflict distance, and the conflict risk value is calculated; The path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted to obtain an adjusted conflict path; Based on the adjusted conflict path, the corresponding robots in the swarm robot are controlled to move to avoid collision among the swarm robots.

[0063] Specifically, the coordination module 5 is executed when periodically acquiring the relative distance between each robot in the swarm robot; Periodically obtain the real-time position of each robot in the swarm robot; According to the real-time position, the relative distance between each robot is calculated.

[0064] When the collaborative module 5 is executed, the real-time position of each robot in the group robot is obtained at intervals of a preset period (the preset period can be set according to actual needs), and the relative distance between each robot is calculated based on the real-time position. Among them, each robot is equipped with a multimodal sensor (such as a laser radar, a camera, etc.), through which each robot can obtain information such as the position of surrounding obstacles, the coordinates of the target area, and the status of neighboring robots.

[0065] Specifically, the collaboration module 5 performs conflict analysis on robots whose relative distance is less than the preset conflict distance according to the preset conflict prediction model and the preset state update model (i.e., after updating the state of the robots whose relative distance is less than the preset conflict distance according to the preset state update model, based on the preset conflict prediction model, calculates the conflict risk value between the robots whose relative distance after the state update is less than the preset conflict distance), and when the conflict risk value is calculated, executes: Determine whether the relative distance between the robots is less than the preset conflict distance; If so, after updating the states of the robots whose relative distances are less than the preset conflict distance according to the preset state update model, the conflict risk values ​​between the robots whose relative distances after the state update are less than the preset conflict distance are calculated based on the preset conflict prediction model; If not, the robots whose relative distance is greater than or equal to the preset conflict distance are controlled to move according to the task path information.

[0066] When the collaborative module 5 is executed, it determines whether the relative distance between the robots is less than the preset conflict distance (the preset conflict distance can be set according to actual needs, and the preset conflict distance is used as the radius and the robot itself is used as the origin to draw a circle to construct the neighborhood of the corresponding robot). When there is a relative distance between any robot and other robots that is less than the preset conflict distance (that is, there are other robots in the neighborhood of any robot), according to the preset state update model, the state of the robot whose relative distance is less than the preset conflict distance is updated (that is, the state vector of the robot in the neighborhood is updated and synchronized, and the state vector includes the position vector (x, y, z) and velocity vector (v) of the robot in the three-dimensional space x , v y , v z ), where x, y, and z are the horizontal, vertical, and vertical coordinates of the robot, respectively, and v x 、v y 、v z are the speeds of the robots in the horizontal, vertical and vertical directions respectively), then based on the preset conflict prediction model, the conflict risk value between the robots whose relative distance after state update is less than the preset conflict distance is calculated, wherein the preset state update model is specifically: ; Among them, x i (t+1) is the state vector of robot i at time t+1; x i (t) is the state vector of robot i at time t; ϵ is the learning rate, that is, the amplitude of the robot state update; is the communication weight between robot i and robot j; N i is the set of robots within the preset conflict distance of robot i (i.e., the set of robots in the neighborhood of robot i); x j (t) is the state vector of robot j at time t.

[0067] Through the preset state update model, information is exchanged, the states of the robots in the neighborhood are updated and synchronized, so that the state vectors of each robot obtained by the robots in the neighborhood gradually converge, thereby optimizing the collaborative behavior of the entire group. Through the state update mechanism, each robot gradually coordinates with the robots in its neighborhood on path selection and task priority until the entire group of robots reaches consistency. For example, during the execution of a task, when multiple robots need to cooperate to pass through a narrow passage, after the state is updated and synchronized, (the control system or between multiple robots) will dynamically adjust their passing order and speed, thereby significantly improving the efficiency of task completion.

[0068] The preset conflict prediction model is as follows: ; Among them, R ij (t) is the conflict risk value between robot i and robot j at time t; is an exponential function with the natural constant e as base, The natural constant e power; p i (t) is the current position of robot i at time t; p j (t) is the current position of robot j at time t; is the norm symbol; is the conflict range parameter.

[0069] Through the preset conflict prediction model, the corresponding conflict risk value can be calculated according to the position of the robot. When there is no data of the relative distance between any robot and other robots being less than the preset conflict distance, the robots whose relative distance is greater than or equal to the preset conflict distance are controlled to move according to the task path information.

[0070] Specifically, when the coordination module 5 adjusts the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance and obtains the adjusted conflict path, it executes: Determine whether the conflict risk value between the robots is greater than the preset safety threshold; If yes, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted through the preset speed adjustment model to obtain an adjusted conflict path; If not, the robot whose conflict risk value is less than or equal to the preset safety threshold is controlled to move according to the task path information.

[0071] When the collaborative module 5 is executed, it determines whether the conflict risk value between the robots is greater than the preset safety threshold. When there is a conflict risk value greater than the preset safety threshold between the robots, the speed of the robot during movement can be adjusted through the preset speed adjustment model (wherein, speed refers to the speed vector, and adjusting the speed of the robot during movement includes numerical adjustment and directional adjustment. According to actual needs, the movement speed of a single robot or two robots can be adjusted to obtain the corresponding collision integral through the preset speed adjustment model, and then the corresponding adjustment measures can be determined according to the minimum value of the collision integral) to adjust the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance to obtain the adjusted conflict path. The adjusted conflict paths of the robots are coordinated with each other to avoid collisions between the robots. Among them, the preset speed adjustment model is specifically: ; in, is the collision integral; v i (t) is the speed of robot i at time t; v j (t) is the speed of robot j at time t. The robot's movement speed is adjusted so that the collision integral reaches the minimum value after adjustment. The adjusted collision path is determined by determining the robot's movement speed corresponding to the minimum value.

[0072] In some optional embodiments, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance can be adjusted by using methods such as A* algorithm, Dijkstra algorithm or ant algorithm to obtain an adjusted conflict path. Among them, methods such as A* algorithm, Dijkstra algorithm or ant algorithm are prior arts and will not be described in detail here.

[0073] When there is no conflict risk value greater than a preset safety threshold between the robots, the robots whose conflict risk values ​​are less than or equal to the preset safety threshold are controlled to move according to the task path information.

[0074] When the cooperation module 5 is executed, it controls the corresponding robots in the swarm robots to move according to the adjusted conflict path to avoid collision among the swarm robots.

[0075] As can be seen from the above, the swarm robot collaboration device obtains the task information of the task to be assigned and the robot information of the swarm robots, and through the preset task allocation model, divides the task to be assigned to the robot with the smallest cost function value in the swarm robots according to the task information and the robot information, and according to the preset navigation objective function, performs path planning for the robot that receives the task to be assigned to obtain the task path information, and based on the task path information, controls the robot that receives the task to be assigned to move to the corresponding task location to perform the task to be assigned, and in the process of moving to the corresponding task location, controls the swarm robots to cooperate to avoid collision according to the preset conflict prediction model and the preset state update model; thus, the swarm robots are controlled to perform the task to be assigned through the preset task allocation model and the preset navigation objective function, and in the process of moving to the corresponding task location, controls the swarm robots to cooperate to avoid collision according to the preset conflict prediction model and the preset state update model, thereby solving the problem that the existing swarm robot control method ignores the coordination of the swarm robots in terms of navigation and path planning, and cannot effectively cope with the task changes in the dynamic environment in terms of task allocation and collaboration, and optimizes the path conflict problem, task allocation problem and collaborative cooperation problem of the swarm robots in the real-time environment through the dynamic control method, thereby improving the collaborative efficiency of the swarm robots.

[0076] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The present application provides an electronic device, including: a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other through a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301. When the electronic device is running, the processor 301 executes the computer program to execute the group robot collaboration method in any optional implementation of the above embodiment to achieve the following functions: obtaining task information of a task to be assigned and robot information of a group robot, dividing the task to be assigned to a robot with a minimum cost function value in the group robot according to the task information and the robot information through a preset task assignment model, planning a path for the robot that receives the task to be assigned according to a preset navigation objective function to obtain task path information, and controlling the robot that receives the task to be assigned to move to a corresponding task location to perform the task to be assigned based on the task path information. In the process of moving to the corresponding task location, controlling the group robots to collaborate to avoid collision according to a preset conflict prediction model and a preset state update model.

[0077] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the swarm robot collaboration method in any optional implementation of the above-mentioned embodiment is executed to achieve the following functions: obtaining task information of the task to be assigned and robot information of the swarm robot, dividing the task to be assigned to the robot with the smallest cost function value in the swarm robot according to the task information and the robot information through a preset task assignment model, performing path planning for the robot that receives the task to be assigned according to a preset navigation objective function to obtain task path information, and based on the task path information, controlling the robot that receives the task to be assigned to move to a corresponding task location to perform the task to be assigned; in the process of moving to the corresponding task location, controlling the swarm robots to collaborate to avoid collisions according to a preset conflict prediction model and a preset state update model. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0078] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0079] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0081] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0082] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A swarm robot collaboration method for controlling swarm robots, characterized in that: Includes steps: Obtaining task information of the task to be assigned and robot information of the swarm robot; By using a preset task allocation model, according to the task information and the robot information, the task to be allocated is allocated to the robot with the smallest cost function value in the group of robots; According to a preset navigation objective function, a path planning is performed on the robot that receives the task to be assigned to obtain task path information; Based on the task path information, control the robot that has received the task to be assigned to move to the corresponding task location to perform the task to be assigned; In the process of moving to the corresponding task location, the group robots are controlled to cooperate in a coordinated manner according to a preset conflict prediction model and a preset state update model to avoid collision.

2. The group robot collaboration method according to claim 1, characterized in that: By using a preset task allocation model, according to the task information and the robot information, the task to be allocated is allocated to the robot with the smallest cost function value in the group of robots, including: By using a preset task allocation model, according to the task information and the robot information, a cost function value of dividing the task to be allocated to each robot in the group of robots is calculated; Extracting the minimum value among the cost function values; The task to be assigned is divided into the robot corresponding to the minimum value of the cost function value.

3. The group robot collaboration method according to claim 1, characterized in that: In the process of moving to the corresponding task location, according to a preset conflict prediction model and a preset state update model, the group robots are controlled to cooperate to avoid collision, including: In the process of moving to the corresponding task location, periodically obtaining the relative distance between each robot in the group of robots; According to a preset conflict prediction model and a preset state update model, a conflict analysis is performed on the robots whose relative distance is less than a preset conflict distance, and a conflict risk value is calculated; Adjusting the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance to obtain an adjusted conflict path; Based on the adjusted conflict path, corresponding robots in the swarm of robots are controlled to move to avoid collision among the swarm of robots.

4. The group robot collaboration method according to claim 3, characterized in that: Periodically obtaining the relative distance between each robot in the group of robots, including: Periodically obtaining the real-time position of each robot in the swarm of robots; The relative distances between the robots are calculated based on the real-time positions.

5. The group robot collaboration method according to claim 3, characterized in that: According to a preset conflict prediction model and a preset state update model, a conflict analysis is performed on the robot whose relative distance is less than the preset conflict distance, and a conflict risk value is calculated, including: Determine whether the relative distance between the robots is less than the preset conflict distance; If so, after updating the states of the robots whose relative distances are less than the preset conflict distance according to the preset state update model, the conflict risk values ​​between the robots whose relative distances are less than the preset conflict distance after the state update are calculated based on the preset conflict prediction model; If not, the robot whose relative distance is greater than or equal to the preset conflict distance is controlled to move according to the task path information.

6. The group robot collaboration method according to claim 3, characterized in that: The path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted to obtain an adjusted conflict path, including: Determine whether the conflict risk value between the robots is greater than a preset safety threshold; If yes, the path of the robot whose conflict risk value is greater than the preset safety threshold within the preset conflict distance is adjusted through a preset speed adjustment model to obtain an adjusted conflict path; If not, the robot whose conflict risk value is less than or equal to the preset safety threshold is controlled to move according to the task path information.

7. The group robot collaboration method according to claim 3, characterized in that: The preset state update model is specifically: ； The preset conflict prediction model is specifically: ； Among them, x i (t+1) is the state vector of robot i at time t+1; x i (t) is the state vector of robot i at time t; ϵ is the learning rate, that is, the amplitude of the robot state update; is the communication weight between robot i and robot j; N i is the set of robots within the preset conflict distance of robot i; x j (t) is the state vector of robot j at time t; R ij (t) is the conflict risk value between robot i and robot j at time t; is an exponential function with the natural constant e as base, The natural constant e power; p i (t) is the current position of robot i at time t; p j (t) is the current position of robot j at time t; is the norm symbol; is the conflict range parameter.

8. A swarm robot collaboration device for controlling swarm robots, characterized in that: include: An acquisition module, used to acquire task information of the task to be assigned and robot information of the swarm robot; A division module, used for dividing the to-be-assigned task to the robot with the smallest cost function value in the group of robots according to the task information and the robot information through a preset task allocation model; A planning module, used to plan a path for the robot that has received the task to be assigned according to a preset navigation objective function, and obtain task path information; A moving module, used for controlling the robot that has received the task to be assigned to move to a corresponding task location to perform the task to be assigned based on the task path information; The collaboration module is used to control the group robots to collaborate to avoid collisions according to a preset conflict prediction model and a preset state update model during the process of moving to the corresponding task location.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, it runs the steps in the group robot collaboration method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the group robot collaboration method as described in any one of claims 1-7 are performed.

Images