Intelligent robot division cooperation method and system

Abstract

The invention discloses a work division cooperation method and system of an intelligent robot, and relates to the technical field of robot control, and the method comprises the steps: obtaining a work task demand and robot group information, executing path planning, calculating path energy consumption distribution, and constructing a work task graph; generating an operation cooperation constraint set based on the atlas, and dividing the robot group into an operation body and an energy complementation guarantee body in combination with the constraint to form an initial work division scheme set; simulating division cooperation in a virtual simulation environment, and evaluating a cooperation adaptation degree; and selecting the division scheme with the highest cooperative fitness as a final execution scheme, and issuing the final execution scheme to the robot group to execute job scheduling. Therefore, the technical effects of improving the task execution efficiency, enhancing the adaptability and the operation radius, and optimizing the labor division adaptability and the energy efficiency ratio in a complex environment are achieved.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a labor division and cooperation method and system for intelligent robots. Background Art

[0002] In the field of intelligent robotics, robot swarms are increasingly being used for a variety of complex tasks. However, current approaches to robot collaboration mostly employ a homogeneous operation model, where all robots perform the same or similar tasks, lacking a differentiated division of labor among robot roles. Furthermore, existing path planning techniques typically only consider geographic path information, ignoring the impact of energy consumption distribution on task execution. This results in inadequate task allocation and a failure to fully consider the relationship between robot energy consumption and task adaptation, which in turn impacts the task accessibility, task adaptability, and overall performance of the robot swarm. Summary of the Invention

[0003] The present invention provides a method and system for division of labor and cooperation of intelligent robots to solve the technical problems in the existing technology, such as a single division of labor and cooperation mechanism, disconnection between path planning and energy consumption management, and insufficient adaptability to complex tasks, so as to achieve the technical effects of improving task execution efficiency, enhancing adaptability and operating radius, and optimizing the division of labor adaptability and energy efficiency ratio in complex environments.

[0004] In a first aspect, the present invention provides a method for division of labor and cooperation among intelligent robots, wherein the method for division of labor and cooperation among intelligent robots comprises:

[0005] Obtain task requirement information and robot group information of the target task, and perform task path planning based on the task requirement information and the robot group information.

[0006] The path energy consumption distribution of the corresponding operation path planning result is calculated, and the operation task map is constructed by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information.

[0007] According to the operation task map, intuitive operation collaboration constraints and indirect operation collaboration constraints are generated and output as an operation collaboration constraint set. In combination with the operation collaboration constraint set, the robot group is iteratively randomly divided into operation bodies and energy replenishment guarantee bodies to obtain an initial division of labor plan set.

[0008] A virtual simulation environment is established based on the job task map, the job collaboration constraints and the initial division of labor scheme set, a division of labor and collaboration simulation is performed accordingly, and a collaboration adaptability evaluation is performed based on the division of labor and collaboration simulation results.

[0009] The division of labor plan with the highest collaborative adaptability is selected as the target execution plan and sent to the robot group for job scheduling.

[0010] In a feasible implementation, the task requirement information includes at least task area information, work object information and task timeliness information, and the robot group information includes at least the number of robots, robot intrinsic parameters and corresponding robot energy consumption model.

[0011] In one feasible implementation, the path energy consumption distribution corresponding to the operation path planning result is calculated, and the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information are combined to construct the operation task map, including:

[0012] A path point sequence is generated based on the operation path planning result.

[0013] The energy consumption function model of each robot is extracted from the robot group information.

[0014] The energy consumption characteristic value of each waypoint in the waypoint sequence is calculated by combining the geospatial data, the robot energy consumption model and the task requirement information.

[0015] The path energy consumption distribution is obtained based on the energy consumption characteristic value fitting, and the path energy consumption distribution is associated with the operation path planning result, and the operation task map is constructed by combining the task requirement information and the robot group information.

[0016] In a feasible implementation, intuitive operation collaboration constraints and indirect operation collaboration constraints are generated according to the operation task map, and output as an operation collaboration constraint set, including:

[0017] The task requirement information and the robot group information are regularized to form intuitive operation collaboration constraints.

[0018] Based on the operation task map and the intuitive operation collaboration constraints, indirect operation collaboration constraints are calculated, wherein the indirect operation collaboration constraints at least include: task guarantee constraints, endurance safety constraints, time window constraints and service capacity constraints.

[0019] The intuitive operation collaboration constraint and the indirect operation collaboration constraint are integrated and output as the operation collaboration constraint set.

[0020] In a feasible implementation, a virtual simulation environment is established based on the operation task map, the operation collaboration constraints, and the initial division of labor solution set, and a corresponding division of labor and collaboration simulation is performed, including:

[0021] The virtual simulation environment is established using the job task map as a simulation target input parameter and the job collaboration constraint set as an optimization restriction condition.

[0022] Each initial division of labor scheme is configured differently according to the operation speed range extracted from the operation task map to obtain a set of alternative division of labor schemes.

[0023] The alternative division of labor scheme set is input into the virtual simulation environment for preliminary screening of division of labor strategies and effectiveness evaluation, the alternative division of labor scheme set is cleaned accordingly, and division of labor and cooperation simulation is performed on the cleaned alternative division of labor scheme set.

[0024] In a feasible implementation, the division of labor scheme with the highest collaborative adaptability is selected as the target execution scheme and sent to the robot group for job scheduling. The execution steps of the job body include:

[0025] Monitor its own remaining endurance, and when it is lower than the preset threshold α, automatically generate and broadcast energy replenishment request information, which includes the current location coordinates and energy replenishment demand.

[0026] Continue to execute the current task until the energy supply support body arrives.

[0027] Connect with the energy replenishment guarantee body to complete the energy replenishment process, and send an energy replenishment confirmation signal after the energy replenishment is completed.

[0028] Continue the current task execution process and simultaneously monitor its own remaining battery life.

[0029] In a feasible implementation, the division of labor scheme with the highest collaborative adaptability is selected as the target execution scheme and sent to the robot group for job scheduling. The execution steps of the energy replenishment guarantee body include:

[0030] Continuously monitor the energy replenishment request information of the operation body.

[0031] Perform the nearest match based on the energy replenishment request information, generate an energy replenishment task and execute path planning to the target work body.

[0032] Arriving at the work object according to the path planning result and performing energy replenishment operation, wherein the energy replenishment method includes contact energy replenishment or non-contact energy replenishment.

[0033] After charging is completed, check the remaining endurance.

[0034] When the remaining endurance is lower than a preset threshold, the return route is planned first; otherwise, the energy replenishment request monitoring state is restored.

[0035] In a feasible implementation, the initial division of labor plan is centralized, and the initial division of labor plan includes the number and ratio of the operating units and the energy replenishment guarantee units, wherein:

[0036] The operation body is used to execute the target operation task.

[0037] The energy replenishment guarantee body is equipped with an energy supply component for providing energy replenishment for the working body during the operation process.

[0038] In a feasible implementation, the collaborative adaptability is obtained by integrating preset multidimensional evaluation factors, and the multidimensional evaluation factors include at least: total energy consumption, total path length, unit path energy consumption, division of labor and collaboration cost, and effective operation energy consumption ratio.

[0039] In a second aspect, the present invention further provides a division of labor and cooperation system for intelligent robots, wherein the division of labor and cooperation system for intelligent robots comprises:

[0040] The operation information acquisition module is used to obtain task requirement information and robot group information of the target operation task, and perform operation path planning based on the task requirement information and the robot group information.

[0041] The operation task map construction module is used to calculate the path energy consumption distribution of the operation path planning results, and to construct the operation task map by combining the path energy consumption distribution, operation path planning results, task requirement information and robot group information.

[0042] The division of labor scheme acquisition module is used to generate intuitive operation collaboration constraints and indirect operation collaboration constraints according to the operation task map, output them as an operation collaboration constraint set, and randomly divide the robot group into operation bodies and energy replenishment guarantee bodies in combination with the operation collaboration constraint set to obtain an initial division of labor scheme set.

[0043] The simulation and evaluation module is used to establish a virtual simulation environment based on the job task map, the job collaboration constraints and the initial division of labor plan set, execute the division of labor and collaboration simulation accordingly, and evaluate the collaboration suitability based on the division of labor and collaboration simulation results.

[0044] The solution screening and execution module is used to select the division of labor solution with the highest collaborative adaptability as the target execution solution and send it to the robot group for job scheduling.

[0045] The present invention discloses a method and system for division of labor and cooperation of intelligent robots, comprising: obtaining task requirement data of a target operation task and corresponding robot group information, and executing operation path planning based on the task requirement data and group information; calculating the path energy consumption distribution of the operation path planning result, and constructing an operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement data and the robot group information; generating direct collaboration constraints and indirect collaboration constraints for describing the collaborative relationship based on the operation task map to form an operation collaboration constraint set, and iteratively and randomly dividing the robot group based on the collaboration constraint set to construct an operation body and an energy replenishment guarantee body to obtain an initial division of labor scheme set; constructing a virtual simulation environment based on the operation task map, the operation collaboration constraint set and the initial division of labor scheme set, carrying out division of labor and cooperation simulation, and evaluating the collaboration fitness based on the simulation results; selecting the division of labor scheme with the highest fitness from the initial division of labor scheme set as the target scheduling scheme, and issuing the target scheduling scheme to the robot group to execute the operation task scheduling. The present invention discloses a method and system for the division of labor and cooperation of intelligent robots, which solves the technical problems of a single division of labor and cooperation mechanism, a disconnect between path planning and energy consumption management, and insufficient adaptability to complex tasks. It achieves the technical effects of improving task execution efficiency, enhancing adaptability and operating radius, and optimizing the adaptability and energy efficiency ratio of division of labor in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The figure is a flow chart of a method for division of labor and cooperation among intelligent robots according to the present invention.

[0047] Figure 2 The figure is a structural diagram of a division of labor and cooperation system of intelligent robots according to the present invention.

[0048] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0049] Job information acquisition module 11, job task map construction module 12, division of labor plan acquisition module 13, simulation and evaluation module 14, plan screening and execution module 15. DETAILED DESCRIPTION

[0050] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention, rather than all, are shown in the drawings.

[0051] Example 1, as Figure 1 The figure is a flow chart of a method for division of labor and cooperation among intelligent robots according to the present invention, wherein the method for division of labor and cooperation among intelligent robots includes:

[0052] S100: Obtain task requirement information and robot group information of a target task, and perform task path planning according to the task requirement information and the robot group information.

[0053] Specifically, a target task refers to a specific operational task to be completed by the intelligent robot. Optionally, the target task may include different types of tasks, such as handling, inspection, spraying, and cleaning. This target task is typically issued by a task management module or a higher-level scheduling system. Task requirement information refers to the detailed parameters describing the target task. Examples include task type, operating area, time requirements, payload requirements, and accuracy requirements, which guide the robot in executing the task.

[0054] Specifically, robot group information refers to the capabilities, status, and location of the individual robots currently collaborating. It reflects the status of the robots in the group, illustratively including each robot's load capacity, endurance, current mission status, navigation accuracy, and reachable area. Based on known mission requirements and robot capabilities, specific tasks can be assigned to the robot group and optimal movement and operation paths can be generated. This is known as operation path planning, which optimizes overall mission completion efficiency, maximizes resource utilization, and satisfies mission constraints.

[0055] Specifically, first, the target operation task issued by the task management module or the upper scheduling system is received, and its task requirement information is parsed. For example, the task type is warehouse transportation, the target area is from area A to area B, and it is required to be completed within 30 minutes, and the single transportation weight does not exceed 10 kg. At the same time, the robot group information of the current robot group is obtained, such as the position, load capacity, passability, power status and congestion of the five robots. Then, based on the task requirements and robot group information, an obstacle avoidance path is generated for the current robot group. For example, if robot R1 is currently in area A, has sufficient power and a load capacity of 15 kg, it can be assigned to a shorter heavy-load path, and the shortest path from area A to area B that bypasses obstacles is planned.

[0056] Through the above process, an efficient operation path (i.e., the operation path planning result) can be generated based on the task requirements and robot capabilities in combination with the path planning algorithm. The determined operation path provides feasible and accurate path information for subsequent analysis and simulation, facilitating the efficient execution of division of labor and collaborative decision-making.

[0057] In some embodiments, the task requirement information includes at least task area information, work object information and task timeliness information, and the robot group information includes at least the number of robots, robot intrinsic parameters and corresponding robot energy consumption model.

[0058] Specifically, task requirement information refers to a data set used to describe the specific content and constraints of the task to be performed, including three key elements: task area information, that is, the geographical or spatial location range where the task occurs, such as two-dimensional map coordinates, three-dimensional spatial areas or specific functional blocks, which are used to guide robot path planning and scheduling; operation object information, which refers to the operational objectives involved in the task, such as moving objects, inspecting areas, cleaning the ground, etc., usually including the type, quantity, location and operation requirements of the objects; task timeliness information, which refers to the time constraints of the task, such as the earliest start time, the latest completion time or the execution duration, etc., which are used to achieve timeliness scheduling or priority sorting.

[0059] Specifically, robot group information is a data set that describes the capabilities and status of currently dispatchable robots, including: the number of robots, that is, the total number of individual robots currently available to perform tasks; robot intrinsic parameters, which refer to the robot's inherent performance parameters, such as maximum speed, load capacity, battery capacity, sensor type, etc.; robot energy consumption model, which refers to a mathematical model that describes the energy consumption pattern of the robot when performing different tasks, usually based on variables such as speed, load, and path length.

[0060] S200: Calculate the path energy consumption distribution corresponding to the operation path planning result, and construct an operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information.

[0061] Specifically, based on the path information obtained from path planning and data such as the energy consumption model of the robot group, the energy consumption of each section of the path during the execution of the task can be calculated, and then the path energy consumption distribution can be generated. The path energy consumption distribution reflects the specific energy consumption of the robot group based on the operation path planning results, and is used to quickly realize the call of energy consumption characteristic parameters in subsequent simulation analysis, thereby improving efficiency.

[0062] Specifically, constructing an operation task map is to combine the calculated path energy consumption distribution with the operation path planning results, task requirement information and robot group information to form a structured model that comprehensively reflects the various key elements and their interrelationships in the task execution process. It is used to clearly and intuitively express the task information, robot-related information and path constraint information involved in the division of labor and cooperation, and facilitate rapid search and call in subsequent simulations.

[0063] Through the above process, it is possible to achieve refined modeling of the energy consumption of the robot's operation path. At the same time, by constructing an operation task map, the scattered task information, robot capabilities and path performance data can be structured and integrated, thereby improving the global understanding and management capabilities of the task execution process for subsequent simulation.

[0064] In some embodiments, a path energy consumption distribution corresponding to the operation path planning result is calculated, and the path energy consumption distribution, the operation path planning result, the task requirement information, and the robot group information are combined to construct an operation task map, including:

[0065] A path point sequence is generated based on the operation path planning result; an energy consumption function model of each robot is extracted from the robot group information; the energy consumption characteristic value of each path point in the path point sequence is calculated by combining geographic space data, the robot energy consumption model and the task requirement information; a path energy consumption distribution is obtained based on the energy consumption characteristic value fitting, and the path energy consumption distribution is associated with the operation path planning result, and an operation task map is constructed by combining the task requirement information and the robot group information.

[0066] Specifically, a waypoint sequence is a series of ordered waypoints based on the results of task path planning. Each waypoint contains location information (such as 2D or 3D coordinates), timestamp, velocity, or posture, and is used to discretize the robot's trajectory along the path, facilitating subsequent analysis and calculation. An energy consumption function model is a mathematical model that describes the relationship between the robot's energy consumption per unit time or per unit distance under different operating conditions (such as speed, load, terrain, etc.). It is usually an empirical formula or a function fitted based on experimental data.

[0067] Specifically, geospatial data is used to reflect the actual three-dimensional information of the operation path planning results. For example, it includes information such as the terrain type, slope, obstacle distribution, surface material, etc. of the area where the path points are located. The factors contained in the geospatial data will significantly affect the energy consumption performance of the robot on the path.

[0068] Specifically, the energy consumption characteristic value refers to the estimated energy consumption at a specific path point, calculated by combining the robot's motion state and environmental information. For example, it is expressed in joules / meter. The path energy consumption distribution is a continuous energy consumption curve formed by fitting the energy consumption characteristic values ​​of all path points. It is used to approximately describe the energy consumption trend of the robot as it operates along the planned path.

[0069] Specifically, the operation task graph is a task knowledge graph represented by a graph structure, which integrates the path energy consumption distribution, operation path planning results, task requirement information and robot group information. It is used to provide a structured information basis for subsequent steps.

[0070] Specifically, first, a path point sequence is generated based on the path planning results. For example, according to the preset division granularity of 0.5m, the path from starting point A to end point B in the path planning result is divided into a path point every 0.5 meters, resulting in a path point sequence P = {p1, p2, ..., pn}. Each path point contains its spatial coordinates and expected speed. Subsequently, the energy consumption function model of each robot is extracted from the robot group information. For example, assuming that all robots in the group are of the same model R1, its energy consumption model can be expressed as:

[0071] E(v,w,θ)=αv 2 +βw+γsin(θ);

[0072] Where v is the speed, w is the load, θ is the slope angle, and α, β, and γ are empirical parameters (which can be determined based on experiments).

[0073] Specifically, the energy consumption characteristic value is then calculated for each point in the pathpoint sequence, combining geospatial data with mission requirements. For example, at pathpoint p3, with a slope of 10°, a speed of 1.2 m / s, and a load of 8 kg, substituting this into the corresponding energy consumption model yields an energy consumption characteristic value of 9.45 J / km. Similarly, the resulting pathpoint energy consumption sequence E = {0.3, 0.35, 0.45, ..., 0.25} is obtained.

[0074] Furthermore, the acquired path point energy consumption sequence is fitted using curve fitting methods such as spline interpolation or Gaussian fitting to generate a path energy consumption distribution curve. This energy consumption distribution is then structured and integrated with the path point sequence, task requirement information, and robot group information to construct a task graph. For example, nodes in the graph may include entities such as path segments, robots, task objects, and energy consumption values, while edges represent semantic relationships such as execution, transit, and consumption.

[0075] Through the above process, the energy consumption distribution of the robot during the task execution can be accurately obtained, and combined with other key information in the task execution process, an operation task map can be generated, providing detailed and accurate data support and calling basis for subsequent steps such as job collaboration constraint generation, division of labor plan formulation, and simulation, which helps to improve overall efficiency and task execution results.

[0076] S300: Generate intuitive operation collaboration constraints and indirect operation collaboration constraints according to the operation task map, output them as an operation collaboration constraint set, and randomly divide the robot group into operation bodies and energy replenishment guarantee bodies in combination with the operation collaboration constraint set to obtain an initial division of labor plan set.

[0077] Specifically, intuitive collaborative constraints refer to explicit constraints derived directly from task requirements and robot group information. Examples include: "Heavy-load tasks can only be performed by robots with a payload capacity greater than 10 kg" and "Tasks must be completed within 10 minutes." Regularization involves uniformly encoding and standardizing task and robot information from different sources and formats to make them comparable and computable. For example, task deadlines can be uniformly converted into acceptable time windows and robot capability attributes can be converted into standard capability vectors.

[0078] Specifically, indirect work collaboration constraints are implicit collaboration restrictions obtained by analyzing the association relationships between various entities in the work task graph and reasoning with intuitive work collaboration constraints, including but not limited to:

[0079] Task assurance constraints, such as requiring a task to be completed by a robot with specific capabilities or historical experience; endurance safety constraints, such as ensuring the robot's remaining battery life is above a certain threshold during the task path to prevent failure; time window constraints, such as requiring the robot to arrive within a specific time window; and service capacity constraints, such as requiring a robot to serve a maximum of N targets or transport M units of material in a single task. The resulting set of collaborative constraints integrates these intuitive and indirect constraints and serves as the input condition set for task scheduling and path optimization.

[0080] In some embodiments, the initial division of labor plan is centralized, and the initial division of labor plan includes the number and ratio of the operating units and the energy replenishment guarantee units, wherein:

[0081] The working body is used to perform the target working task; the energy replenishment guarantee body is equipped with an energy supply component for providing energy replenishment for the working body during the working process.

[0082] Specifically, the working body and the energy replenishment support body are two subsets of the robot group determined according to the collaborative role and energy support function. Among them, the working body is responsible for directly performing the working tasks, such as inspection, transportation, collection, etc.; the energy replenishment support body is used to provide energy support for the working body, such as power supply, fuel supply, task succession, etc. Through the coordinated cooperation of these two roles, the service radius and operation stability of the robot group can be improved efficiently and at low cost without improving the performance of individual robots.

[0083] Specifically, under the premise of satisfying some of the collaborative constraints in the acquired task collaboration constraint set, a heuristic or probabilistic method is used to randomly divide the robot group initially to explore various possible collaborative strategies and generate an initial set of work division schemes. These schemes, i.e., the multiple combinations of work units and energy support units generated through this division process, serve as candidate solution spaces for subsequent optimization and scheduling. For example, a work unit to energy support unit ratio of 2:1 can be configured, with a total of 30 units.

[0084] Through the above process, based on the collaborative constraints, a diverse set of initial division of labor schemes can be generated, providing rich candidate solutions for subsequent task scheduling optimization and strategy selection.

[0085] In some embodiments, intuitive operation collaboration constraints and indirect operation collaboration constraints are generated according to the operation task map and output as an operation collaboration constraint set, including:

[0086] Regularize the task requirement information and the robot group information to form intuitive operation collaboration constraints; calculate indirect operation collaboration constraints based on the operation task map and the intuitive operation collaboration constraints, wherein the indirect operation collaboration constraints include at least: task guarantee constraints, endurance safety constraints, time window constraints and service capacity constraints; integrate the intuitive operation collaboration constraints and the indirect operation collaboration constraints, and output them as the operation collaboration constraint set.

[0087] Specifically, first, the task requirement information and robot group information are regularized. For example, if task T1 requires "complete inspection of three target points within 15 minutes", it can be regularized into a vector [task type: inspection; time window: 0, 15; service capacity: 3] to generate intuitive work collaboration constraints. Then, based on the aforementioned work task graph, indirect collaboration constraints are further inferred. For example, the graph shows that the energy consumption of the T1 path is 25J and the remaining power of R1 is 30J, then the endurance safety constraint "R1 should safely complete T1 and return to the base station" can be derived. Ultimately, all intuitive and indirect constraints can be integrated to form a work collaboration constraint set as input for subsequent steps.

[0088] Through the above process, we can generate directly applicable collaborative constraints while also inferring a variety of implicit constraints through the structured representation and semantic association of the task graph, enriching our understanding of the collaborative relationships between tasks and robots. This in turn improves the rationality and adaptability of scheduling strategies and avoids problems such as task conflicts, resource waste, or robot failures caused by ignoring implicit constraints.

[0089] S400: establishing a virtual simulation environment based on the job task map, the job collaboration constraints and the initial division of labor scheme set, executing a division of labor and collaboration simulation, and performing a collaboration adaptability evaluation based on the division of labor and collaboration simulation results.

[0090] Specifically, a virtual simulation environment is a digital platform built within a digital environment, such as a computer or edge computing platform, to simulate the collaborative work of a group of robots in a real-world task environment. By leveraging data such as geographic information, task nodes, path structures, and energy consumption models contained in the task map, this virtual simulation environment can reconstruct real or near-realistic task scenarios, enabling digital simulation and evaluation of robot behavior, path planning, and energy consumption changes.

[0091] Specifically, in the above-mentioned virtual simulation environment, the initial division of labor scheme (i.e., the scheme in which the robots are divided into working bodies and energy replenishment guarantee bodies) can be simulated separately to simulate the collaborative behavior of each robot during the task execution process, including task allocation, path execution, energy replenishment scheduling, etc., and then by analyzing various indicators such as task completion rate, energy consumption efficiency, task conflict rate, energy replenishment success rate, etc. during the simulation process, the adaptation effect of multiple initial division of labor schemes under specific task maps and collaborative constraints can be quantitatively evaluated to provide a basis for subsequent optimization.

[0092] Through this process, the collaborative effectiveness of differentiated division of labor strategies can be quickly evaluated without actually deploying robots, thereby reducing the trial-and-error costs before actual deployment. The virtual simulation environment provides a highly controllable and repeatable testing platform, while the collaborative fitness assessment results provide quantitative feedback for subsequent optimization algorithms. Focusing on achieving a closed loop of simulation-assessment-optimization will improve the collaborative efficiency, task completion rate, and stability of the robot group.

[0093] In some embodiments, a virtual simulation environment is established based on the job task map, the job collaboration constraints, and the initial division of labor solution set, and a corresponding division of labor and collaboration simulation is performed, including:

[0094] The virtual simulation environment is established using the job task map as a simulation target input parameter and the job collaboration constraint set as an optimization restriction condition; each initial division of labor scheme is differentially configured according to the job speed range extracted from the job task map to obtain a set of alternative division of labor schemes; the set of alternative division of labor schemes is input into the virtual simulation environment for preliminary screening and effectiveness evaluation of the division of labor strategy, the set of alternative division of labor schemes is cleaned accordingly, and a division of labor and collaboration simulation is performed on the cleaned set of alternative division of labor schemes.

[0095] Specifically, the operating speed range refers to the preset robot execution speed range for different task nodes or path segments in the task map. This operating speed range is limited by factors such as terrain type, task complexity, and task urgency. For example, in rough terrain or narrow passages, the robot must perform tasks at a lower speed to ensure safety; while in flat areas or emergency tasks, the robot can operate at a higher speed.

[0096] Specifically, differentiated configuration involves individually adjusting the robot behavior parameters in the initial division of labor plan based on the aforementioned operating speed ranges, thereby obtaining a variety of alternative division of labor plans. Preliminary division of labor strategy screening and effectiveness evaluation involves a quick pre-simulation screening of alternative division of labor plans, eliminating those that clearly do not meet the constraints or have low performance indicators, thereby reducing simulation computational overhead.

[0097] Specifically, the task map is first used as the simulation target input parameter to extract information such as task nodes, path structure, energy consumption model, and operation speed range. The task collaboration constraint set is then used as the optimization constraint to construct a virtual simulation environment. For example, given a task map containing 20 task points, five types of terrain, and 10 robots (R1–R10), the allowed operating speed ranges for the ten robots on different terrains can be extracted, such as 0.5–1.0 m / s on grass, 1.0–1.5 m / s on concrete roads, and 0.3–0.8 m / s on slopes.

[0098] Specifically, a random number generator and the obtained operating speed range are then used to differentially configure the robot's task execution speed for each of the initial division of labor solutions. This generates multiple variants, forming a set of alternative division of labor solutions. This set of alternative division of labor solutions is then input into a virtual simulation environment. Using rapid evaluation metrics configured based on the task map, such as estimated task completion time, estimated total energy consumption, and task coverage, the division of labor strategies are initially screened. Solutions that clearly do not meet the constraints, such as those with an estimated task completion rate below 80% or energy consumption exceeding the power limit, are eliminated.

[0099] Furthermore, the high-potential solutions retained after cleaning are further input into the virtual simulation environment for fine-grained division of labor and cooperation simulation, simulating the collaborative operation process of robots under different speed configurations, recording and analyzing key indicators such as their total energy consumption, total mileage of the robot group, actual energy consumption per unit path, number of path conflicts, and stability, and generating division of labor and cooperation simulation results.

[0100] This process improves simulation efficiency, avoids redundant simulations of numerous inefficient division-of-work solutions, and makes each alternative more realistic and feasible. Differentiated configurations enhance adaptability to complex, heterogeneous task environments, facilitating the acquisition of more realistic solutions and providing more targeted and effective collaborative strategies for robot swarms.

[0101] In some embodiments, the collaborative fitness is obtained by integrating preset multidimensional evaluation factors, and the multidimensional evaluation factors include at least: total energy consumption, total path length, unit path energy consumption, division of labor and collaboration cost, and effective operation energy consumption ratio.

[0102] Specifically, collaborative fitness is a dimensionless numerical indicator used to quantitatively measure the overall collaborative effect and execution efficiency of alternative division of labor schemes under specific task maps and collaborative constraints. It can reflect the rationality of collaboration between robots and the efficiency of task completion. Multidimensional evaluation factors are the basic evaluation parameters that constitute collaborative fitness, covering multiple angles to comprehensively quantify the pros and cons of division of labor schemes. Specifically, they include:

[0103] Total energy consumption, that is, the total energy consumed by all robots in the process of completing the task, reflects the overall energy consumption; total path length, that is, the cumulative length of the paths traveled by all robots in performing the task, is used to evaluate the efficiency of path planning; unit path energy consumption, that is, the average energy consumed per unit path length, measures the coordination between energy consumption and path planning; division of labor and cooperation cost refers to the resource consumption cost caused by task division, collaborative scheduling, communication coordination, etc.; effective operation energy consumption ratio, that is, the proportion of energy consumption used by robots for actual effective operations such as resource handling to total energy consumption, is used to evaluate the efficiency of energy use.

[0104] S500: Select the division of labor plan with the highest collaborative adaptability as the target execution plan and send it to the robot group for job scheduling.

[0105] Specifically, the target execution plan is the plan with the highest score in the comprehensive collaborative adaptability index among all alternative plans after simulation evaluation and cleaning. The task target execution plan has the best comprehensive performance in terms of task completion efficiency, energy consumption control, path optimization and collaborative coordination, which meets the target manufacturer's preferences and requirements for multi-dimensional evaluation factors and can be used for division of labor and scheduling configuration in actual deployment.

[0106] Specifically, the target execution plan includes specific parameters such as task allocation, path planning, time scheduling, etc. for each robot. The target execution plan can be sent to each robot terminal in the form of instructions or task packages through the communication module, so that the robot group can start and execute the work tasks synchronously according to the target execution plan.

[0107] Through the above process, it can be ensured that the final deployed division of labor plan is optimal under multi-dimensional performance indicators, thereby realizing efficient collaborative operation of robot groups in complex task environments, improving the stability and energy efficiency of task completion, reducing resource waste and task failure risks caused by unreasonable division of labor, and enhancing the application value and intelligent decision-making capabilities of robot groups in actual scenarios.

[0108] In some embodiments, the division of labor scheme with the highest collaborative adaptability is selected as the target execution scheme and sent to the robot group for job scheduling. The execution steps of the job body include:

[0109] Monitor its own remaining battery life. When it falls below a preset threshold α, it automatically generates and broadcasts a recharge request message, which includes the current location coordinates and the required amount of recharge. Continue to execute the current task until the recharge support body arrives. Connect with the recharge support body to complete the recharge process and send a recharge confirmation signal after the recharge is completed. Continue the current task execution process and simultaneously monitor its own remaining battery life.

[0110] Specifically, an operating body refers to a robot individual that performs specific production, service or task behaviors. It has the capabilities of movement, perception, and execution, and is the main role that undertakes actual operations.

[0111] Specifically, during the execution of the operation, the operating body will monitor its remaining endurance in real time, such as obtaining data such as the current power percentage and drivable distance through the battery management system (BMS). When it is detected that the remaining endurance is lower than the set threshold α, a recharge request information will be automatically generated. For example, the current position coordinates are (x=120, y=85), and the recharge demand is 800Wh. This information will be broadcast through a wireless communication module (such as Wi-Fi, 5G or V2X). This ensures that the nearest available recharge guarantee body can be dispatched to the location of the operating body (ie, the current location coordinates). During this period, the operation will continue to execute the current task and update the position of the operating body until the recharge guarantee body arrives to ensure that the task is not interrupted.

[0112] Furthermore, after the energy supply support unit arrives, the energy transfer process is completed through positioning and docking mechanisms. After energy supply is complete, the operator will proactively send a confirmation signal for logging and scheduling optimization, continue the current task process, and continuously monitor the endurance status to enter the next round of energy supply judgment logic.

[0113] Through the above process, the working body can achieve dynamic energy replenishment without interrupting task execution, avoiding the risk of passive shutdown due to robot energy exhaustion, and enhancing stability and autonomy in long-term, large-scale task execution.

[0114] In some embodiments, the division of labor scheme with the highest collaborative adaptability is selected as the target execution scheme and sent to the robot group for job scheduling. The execution steps of the energy replenishment guarantee body include:

[0115] Continuously monitor the energy replenishment request information of the work body; perform the nearest match based on the energy replenishment request information, generate the energy replenishment task and execute the path planning to the target work body; arrive at the work body according to the path planning result to perform the energy replenishment operation, wherein the energy replenishment method includes contact energy replenishment or non-contact energy replenishment; after the energy replenishment is completed, detect its own remaining endurance; when its own remaining endurance is lower than the preset threshold, give priority to planning the return path, otherwise, resume the energy replenishment request monitoring state.

[0116] Specifically, the energy replenishment guarantee body is a mobile energy support unit specially used to provide energy replenishment for the working body. It has functions such as autonomous navigation, path planning, energy transmission and task communication. It can select the most appropriate energy replenishment guarantee body to respond based on factors such as the spatial distance between the energy replenishment guarantee body and the working body that issues the request, the path cost, the current task load, etc.

[0117] Specifically, contact-based energy replenishment includes fuel gun connection, cable connection, energy pack replacement, etc., while contactless energy replenishment includes inductive wireless charging, etc.; the preset threshold is the set lower limit of power, which is used to trigger safety behaviors such as energy replenishment or return.

[0118] Specifically, when the energy replenishment guarantee body is in standby mode, it is set to continuously monitor the energy replenishment request information broadcast in the network. Once a request is received from an operating body, the shortest path priority algorithm is used to perform a nearby match based on the current energy replenishment guarantee body's location, remaining energy, task status and other parameters, and the optimal energy replenishment guarantee body is assigned a response task. After a successful match, an energy replenishment task is generated for the energy replenishment guarantee body, and a corresponding path planning component is started to plan the optimal path from the current position of the energy replenishment guarantee body to the target operating body. The energy replenishment task is then navigated along the path to the operating body, and the contact or contactless energy replenishment method is selected according to the interface type of the operating body to complete the energy transmission.

[0119] Furthermore, after recharging is complete, the recharging assurance body will detect its own remaining battery life. If it is below a set threshold, it will prioritize planning a return route back to the recharging station or charging pile. If there is still sufficient power, it will re-enter the monitoring state and prepare to respond to the next recharging request. Preferably, the above-mentioned preset threshold can be set based on the dynamic battery life evaluation model and the current distance from the base station (i.e., the starting point of the robot group or the path to the mother station). For example, 1.2 times the remaining battery life value obtained by the dynamic battery life evaluation model can be configured as the preset threshold.

[0120] Through the above process, the energy replenishment guarantee body can provide dynamic, precise and low-latency energy support to the working body, enhance the operation continuity and adaptability of the robot group, avoid task interruption caused by energy depletion of the working body, and improve the adaptability and coordination capabilities of the entire robot group in complex task environments.

[0121] In summary, the intelligent robot division of labor and cooperation method provided by the present invention has the following technical effects:

[0122] By obtaining the task requirement data of the target task and the corresponding robot group information, and performing task path planning based on the task requirement data and group information; calculating the path energy consumption distribution of the task path planning results, and combining the path energy consumption distribution, the task path planning results, the task requirement data and the robot group information to construct a task map; generating direct collaboration constraints and indirect collaboration constraints for describing the collaborative relationship based on the task map to form a task collaboration constraint set, and iteratively randomly dividing the robot group based on the collaboration constraint set to construct the work body and the energy replenishment guarantee body to obtain an initial division of labor plan set; constructing a virtual simulation environment based on the task map, the task collaboration constraint set and the initial division of labor plan set, carrying out division of labor and collaboration simulation, and evaluating the collaboration adaptability based on the simulation results; selecting the division of labor plan with the highest adaptability from the initial division of labor plan set as the target scheduling plan, and sending the target scheduling plan to the robot group to execute task scheduling, thereby achieving the technical effects of improving task execution efficiency, enhancing adaptability and operation radius, and optimizing the division of labor adaptability and energy efficiency ratio in complex environments.

[0123] Example 2, as Figure 2 This is a structural diagram of a division of labor and cooperation system of intelligent robots in the present invention. For example, Figure 1 The flowchart of the division of labor and cooperation method of an intelligent robot in the present invention can be shown as follows: Figure 2 The structure shown is implemented.

[0124] Based on the same concept as the division of labor and cooperation method of an intelligent robot in the embodiment, the present invention also provides a division of labor and cooperation system of an intelligent robot, including:

[0125] The operation information acquisition module 11 is used to obtain task requirement information and robot group information of the target operation task, and perform operation path planning according to the task requirement information and the robot group information.

[0126] The operation task map construction module 12 is used to calculate the path energy consumption distribution corresponding to the operation path planning result, and to construct the operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information.

[0127] The division of labor scheme acquisition module 13 is used to generate intuitive operation collaboration constraints and indirect operation collaboration constraints according to the operation task map, output them as an operation collaboration constraint set, and randomly divide the robot group into operation bodies and energy replenishment guarantee bodies in combination with the operation collaboration constraint set to obtain an initial division of labor scheme set.

[0128] The simulation and evaluation module 14 is used to establish a virtual simulation environment based on the job task map, the job collaboration constraints and the initial division of labor plan set, execute the division of labor and collaboration simulation accordingly, and perform collaboration fitness evaluation based on the division of labor and collaboration simulation results.

[0129] The solution screening and execution module 15 is used to select the division of labor solution with the highest collaborative adaptability as the target execution solution and send it to the robot group for job scheduling.

[0130] In some embodiments, the task map construction module 12 includes:

[0131] The operation path planning unit is used to obtain task requirement information and robot group information of the target operation task, and perform operation path planning according to the task requirement information and the robot group information.

[0132] The operation task map construction unit is used to calculate the path energy consumption distribution of the operation path planning result, and to construct the operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information.

[0133] The initial division of labor scheme set acquisition unit is used to generate intuitive operation collaboration constraints and indirect operation collaboration constraints according to the operation task map, output them as an operation collaboration constraint set, and randomly divide the robot group into operation bodies and energy replenishment guarantee bodies in combination with the operation collaboration constraint set to obtain the initial division of labor scheme set.

[0134] The division of labor and collaboration simulation and evaluation unit is used to establish a virtual simulation environment based on the job task map, the job collaboration constraints and the initial division of labor plan set, execute the division of labor and collaboration simulation accordingly, and evaluate the collaboration adaptability based on the division of labor and collaboration simulation results.

[0135] The target execution plan determination and scheduling unit is used to select the division of labor plan with the highest collaborative adaptability as the target execution plan and send it to the robot group for job scheduling.

[0136] In some embodiments, the division of labor scheme acquisition module 13 includes:

[0137] The intuitive operation collaboration constraint generation unit is used to regularize the task requirement information and the robot group information to form intuitive operation collaboration constraints.

[0138] The indirect operation collaboration constraint calculation unit is used to calculate the indirect operation collaboration constraints based on the operation task map and the intuitive operation collaboration constraints, wherein the indirect operation collaboration constraints include at least: task guarantee constraints, endurance safety constraints, time window constraints and service capacity constraints.

[0139] The operation collaboration constraint set output unit is used to integrate the intuitive operation collaboration constraint and the indirect operation collaboration constraint, and output the result as the operation collaboration constraint set.

[0140] In some embodiments, the simulation and evaluation module 14 includes:

[0141] The virtual simulation environment establishing unit is used to establish the virtual simulation environment using the job task map as a simulation target input parameter and the job collaboration constraint set as an optimization restriction condition.

[0142] The alternative division of labor scheme set configuration unit is used to differentially configure each initial division of labor scheme according to the operation speed range extracted from the operation task map to obtain the alternative division of labor scheme set.

[0143] The division of labor strategy simulation and evaluation unit is used to input the alternative division of labor scheme set into the virtual simulation environment for preliminary screening and effectiveness evaluation of the division of labor strategy, clean the alternative division of labor scheme set accordingly, and perform division of labor and cooperation simulation on the cleaned alternative division of labor scheme set.

[0144] In some embodiments, the execution steps of the task body in the solution screening and execution module 15 include:

[0145] Monitor its remaining battery life. When it falls below a preset threshold α, it automatically generates and broadcasts a recharge request message, including its current location and the required amount of energy. Continue executing the current mission until the recharge provider arrives. Connect with the provider, complete the recharge process, and send a recharge confirmation signal upon completion. Continue executing the current mission while simultaneously monitoring its remaining battery life.

[0146] In some embodiments, the execution steps of the energy replenishment guarantee body in the solution screening and execution module 15 include:

[0147] Continuously monitor the energy replenishment request information of the operating body. Perform the nearest match based on the energy replenishment request information, generate the energy replenishment task, and execute the path planning to the target operating body. Arrive at the operating body according to the path planning result and perform the energy replenishment operation, wherein the energy replenishment method includes contact energy replenishment or non-contact energy replenishment. After the energy replenishment is completed, detect the remaining endurance of the vehicle. When the remaining endurance of the vehicle is lower than the preset threshold, prioritize planning the return path; otherwise, resume the energy replenishment request monitoring state.

[0148] In some implementations, the task requirement information includes at least task area information, work object information, and task timeliness information, and the robot group information includes at least the number of robots, robot intrinsic parameters, and corresponding robot energy consumption models.

[0149] In some implementations, the initial division of labor plan is centralized, and the initial division of labor plan includes the number and ratio of the operating units and the energy replenishment guarantee units, wherein:

[0150] The working body is used to perform the target working task; the energy replenishment guarantee body is equipped with an energy supply component for providing energy replenishment for the working body during the working process.

[0151] In some implementations, the collaborative fitness is obtained by integrating preset multidimensional evaluation factors, and the multidimensional evaluation factors include at least: total energy consumption, total path length, unit path energy consumption, division of labor and collaboration cost, and effective operation energy consumption ratio.

[0152] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the division of labor and cooperation system of intelligent robots described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.

[0153] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the embodiments mentioned above. It should be understood that those skilled in the art can still modify the technical solutions described in the above embodiments or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention and are all included in the scope of protection of the present invention.

Claims

1. A method for division of labor and cooperation among intelligent robots, characterized in that: include: Obtaining task requirement information and robot group information of a target task, and executing task path planning based on the task requirement information and the robot group information; Calculate the path energy consumption distribution of the operation path planning result, and construct an operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information; According to the task map, intuitive and indirect work collaboration constraints are generated and output as a work collaboration constraint set. The robot group is randomly divided into work bodies and energy replenishment guarantee bodies in an iterative manner based on the work collaboration constraint set to obtain an initial division of labor solution set. Establishing a virtual simulation environment based on the work task map, the work collaboration constraints, and the initial work division plan set, executing a work division and collaboration simulation, and performing a collaboration fitness evaluation based on the work division and collaboration simulation results; The division of labor plan with the highest collaborative adaptability is selected as the target execution plan and sent to the robot group for job scheduling.

2. The method for division of labor and cooperation of intelligent robots according to claim 1, characterized in that: The task requirement information includes at least task area information, work object information and task timeliness information, and the robot group information includes at least the number of robots, robot intrinsic parameters and corresponding robot energy consumption model.

3. The method for division of labor and cooperation of intelligent robots according to claim 2, wherein: Calculate the path energy consumption distribution of the operation path planning result, and combine the path energy consumption distribution, operation path planning result, task requirement information and robot group information to build an operation task map, including: generating a path point sequence based on the operation path planning result; Extracting an energy consumption function model of each robot from the robot group information; Calculating the energy consumption characteristic value of each waypoint in the waypoint sequence by combining the geospatial data, the robot energy consumption model, and the task requirement information; The path energy consumption distribution is obtained based on the energy consumption characteristic value fitting, and the path energy consumption distribution is associated with the operation path planning result, and the operation task map is constructed by combining the task requirement information and the robot group information.

4. The method for division of labor and cooperation of intelligent robots according to claim 3, characterized in that: According to the job task graph, intuitive job collaboration constraints and indirect job collaboration constraints are generated and output as a job collaboration constraint set, including: Regularizing the task requirement information and the robot group information to form intuitive operation collaboration constraints; Based on the operation task map and the intuitive operation collaboration constraints, indirect operation collaboration constraints are calculated, wherein the indirect operation collaboration constraints include at least: task guarantee constraints, endurance safety constraints, time window constraints and service capacity constraints; The intuitive operation collaboration constraint and the indirect operation collaboration constraint are integrated and output as the operation collaboration constraint set.

5. The method for division of labor and cooperation of intelligent robots according to claim 4, characterized in that: A virtual simulation environment is established based on the operation task map, the operation collaboration constraints, and the initial division of labor solution set, and a corresponding division of labor and collaboration simulation is performed, including: The virtual simulation environment is established using the operation task map as a simulation target input parameter and the operation collaboration constraint set as an optimization constraint condition; Differentiating each initial division of labor scheme based on the operation speed range extracted from the operation task map to obtain a set of alternative division of labor schemes; The alternative division of labor scheme set is input into the virtual simulation environment for preliminary screening of division of labor strategies and effectiveness evaluation, the alternative division of labor scheme set is cleaned accordingly, and division of labor and cooperation simulation is performed on the cleaned alternative division of labor scheme set.

6. The method for division of labor and cooperation of intelligent robots according to claim 1, characterized in that: The division of labor plan with the highest collaborative adaptability is selected as the target execution plan and sent to the robot group for job scheduling. The execution steps of the job body include: Monitor its remaining battery life. When it falls below a preset threshold α, it automatically generates and broadcasts a request for energy replenishment, which includes the current location coordinates and the amount of energy required. Continue to execute the current task until the energy supply support body arrives; Connecting with the energy replenishment support body to complete the energy replenishment process and sending an energy replenishment confirmation signal after the energy replenishment is completed; Continue the current task execution process and simultaneously monitor its own remaining battery life.

7. The method for division of labor and cooperation of intelligent robots according to claim 6, characterized in that: The division of labor plan with the highest collaborative adaptability is selected as the target execution plan and sent to the robot group for job scheduling. The execution steps of the energy replenishment guarantee body include: Continuously monitoring the energy replenishment request information of the operating body; Performing a nearby match based on the energy replenishment request information, generating an energy replenishment task, and executing path planning to the target work body; Arriving at the working body according to the path planning result and performing energy replenishment operation, wherein the energy replenishment method includes contact energy replenishment or non-contact energy replenishment; After the energy is replenished, check the remaining battery life; When the remaining endurance is lower than a preset threshold, the return route is planned first; otherwise, the energy replenishment request monitoring state is restored.

8. The method for division of labor and cooperation of intelligent robots according to claim 1, wherein: The initial division of labor plan is centralized, and the initial division of labor plan includes the number and ratio of the operating units and the energy replenishment guarantee units, wherein: The operation body is used to perform the target operation task; The energy replenishment guarantee body is equipped with an energy supply component for providing energy replenishment for the working body during the operation process.

9. The method for division of labor and cooperation of intelligent robots according to claim 1, wherein: The collaborative fitness is obtained by integrating preset multi-dimensional evaluation factors, and the multi-dimensional evaluation factors include at least: total energy consumption, total path length, unit path energy consumption, division of labor and collaboration cost, and effective operation energy consumption ratio.

10. A division of labor and cooperation system of intelligent robots, characterized in that: A method for implementing the division of labor and cooperation of intelligent robots according to any one of claims 1 to 9, comprising: An operation information acquisition module is used to obtain task requirement information and robot group information of a target operation task, and perform operation path planning based on the task requirement information and the robot group information; An operation task map construction module is used to calculate the path energy consumption distribution corresponding to the operation path planning result, and to construct an operation task map by combining the path energy consumption distribution, the operation path planning result, the task requirement information and the robot group information; A labor division scheme acquisition module is used to generate intuitive and indirect labor cooperation constraints based on the work task map, output them as a set of labor cooperation constraints, and randomly divide the robot group into work bodies and energy replenishment guarantee bodies in combination with the set of labor cooperation constraints to obtain an initial labor division scheme set; A simulation and evaluation module is used to establish a virtual simulation environment based on the work task map, the work collaboration constraints and the initial division of labor scheme set, execute a division of labor and collaboration simulation accordingly, and perform a collaboration fitness evaluation based on the division of labor and collaboration simulation results; The solution screening and execution module is used to select the division of labor solution with the highest collaborative adaptability as the target execution solution and send it to the robot group for job scheduling.

Images