30 results about "Pheromone matrix" patented technology

The invention relates to the technical field of autonomous navigation, in particular to an AUV (Autonomous Underwater Vehicle) multi-sensor fusion autonomous navigation system based on ant colony-particle swarm collaboration.The AUV multi-sensor fusion autonomous navigation system is characterized in that a sensor weight decision module constructs a pheromone matrix based on an ant colony algorithm, retrieves a mapping relation between historical errors and pheromone concentration in real time and dynamically generates a sensor priority sequence; adaptive weight distribution in a data conflict scene is realized; the dynamic path correction module is combined with a particle swarm algorithm and pheromone concentration gradient constraint to balance global path optimality and real-time obstacle avoidance requirements in optical camera obstacle deviation correction; and the closed-loop coupling module is used for converting sonar and geomagnetic residual errors into pheromone concentration correction values and confidence coefficient regulation factors by fusing residual error compensation and path tracking error feedback, so that an error traceability-weight calibration-path optimization closed loop is formed, sensor drift is inhibited, and the long-endurance navigation precision is improved.

The invention discloses a business processing method and device based on an ant colony algorithm, electronic equipment and a medium. The method comprises the following steps: acquiring a business service request, and analyzing the business service request to obtain a business task; determining each agent matched with the business task; wherein the intelligent agents are used for cooperative processing of business tasks; planning the cooperation path of each agent based on an ant colony algorithm to obtain a target path; and according to the cooperation sequence of the intelligent agents in the target path, executing the business task by using the intelligent agents in sequence. According to the technical scheme, efficient collaboration between agents is achieved through the improved ant colony algorithm. According to the system, a multi-dimensional pheromone matrix is adopted to record and transmit collaborative experience among departments, a knowledge verification mechanism based on swarm intelligence is established, and dynamic optimization and rapid convergence of a cross-department business process are realized.

The invention discloses a flexible job shop energy-saving scheduling optimization method considering a light storage condition and a load characteristic, and relates to the technical field of industrial scheduling, and the method comprises the steps: building a flexible job shop energy-saving scheduling problem model based on mixed integer programming, and setting an optimization target and a constraint condition; an ant colony algorithm is improved, an ant colony is divided into dynamic multi-level search, and a pheromone matrix is optimized; the updating effect of pheromones in the ant colony algorithm in the iteration process is optimized; optimizing the optimal solution of each generation of the ant colony algorithm by adopting a graph neural network off-line learning neighborhood search method; and stopping iteration when a preset termination condition is met, and outputting an optimal scheduling scheme. According to the method, a more efficient and flexible energy-saving scheduling strategy is developed to effectively coordinate the productivity and the energy efficiency, energy optimization and cost reduction in the production process are achieved, actual technical support is provided for energy-saving scheduling of the flexible job shop, and a method system for the workshop scheduling problem is enriched.

The invention provides an ant colony algorithm initialization method and system based on an ISIS protocol, and the method comprises the steps: collecting network topology information in real time based on the ISIS protocol, including a node set, a link set and cost parameters of each link, the cost parameters including transmission time delay, bandwidth utilization rate and packet loss rate; constructing a comprehensive cost evaluation model based on weighted summation of the cost parameters of the links; a pheromone matrix of the ant colony algorithm is initialized based on the result of the comprehensive cost evaluation model, and the link comprehensive cost is inversely proportional to the initial pheromone value; constructing a heuristic information model according to the network topology information, wherein the heuristic information model is the reciprocal of the comprehensive cost; and based on the pheromone matrix and the heuristic information model, initializing a node selection probability function of an ant colony algorithm, and executing the ant colony algorithm to iteratively solve an optimal routing path. According to the method, the real-time network information obtained by the ISIS protocol is used for the initialization of the ant colony algorithm, so that the initialization precision can be improved.

The invention discloses a path planning method, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a preset straight line between an initial position and a target position in a space grid, determining the vertical distance between each space node in the space grid and the preset straight line, the space grid being a discrete unit structure generated based on a preset space, and the preset straight line being a preset straight line; the space nodes are discrete points in the space grid; constructing an initial pheromone matrix of the space grid according to the vertical distance, wherein the initial pheromone matrix at least comprises the initial pheromone concentration of each space node in the space grid; and iteratively generating a planned path between the initial position and the target position in the space grid according to an ant colony algorithm based on the initial pheromone matrix. Therefore, according to the technical scheme of the invention, the initial pheromone concentration of each space node in the space grid is optimized based on the preset straight line, and ants are guided to preferentially search the region close to the ideal path, so that the iterative convergence speed is accelerated, and the precision and efficiency of path planning are improved.

The invention discloses a multi-SoC cooperative task allocation method based on quantum ant colony optimization. The method comprises the following steps: acquiring a node resource portrait set and a task attribute set for each system-on-chip node in a multi-SoC system; constructing a task-resource mapping graph; obtaining a quantum coding task set; loading the quantum coding task set to a search state space of quantum ant individuals, setting a pheromone matrix and a quantum rotation angle matrix, and obtaining an initial population of a quantum ant colony; obtaining an updated quantum state population; calculating a delay index, a power consumption index and a reliability index of each deterministic task allocation result according to the node resource portrait set, and screening out a candidate feasible solution set meeting real-time constraint; and obtaining a global scheduling scheme. According to the method, the modeling granularity and the distribution precision of task distribution under multi-domain heterogeneous resources are remarkably improved, the problems of bandwidth contention and delay mutation in cross-node and cross-domain migration are effectively avoided, and the real-time performance and the high adaptability of task distribution are achieved.

The invention discloses a parking lot recommendation method based on an improved ant colony algorithm, and the method comprises the steps: S1, setting the number of ants and a pheromone matrix, and determining a weight parameter of a heuristic function; s2, in the current iteration, each ant starts from a starting point, a next node is selected by adopting a roulette strategy according to the pheromone concentration between the nodes and a heuristic function value until the next node reaches an end point, a complete path is formed, and in the path construction process, part of ants execute a random walking strategy to perform global exploration; s3, after all the ants complete path construction, a pheromone matrix is updated uniformly according to the path advantages and disadvantages of all the ants, and the updating process does not include a pheromone volatilization step; and S4, the steps S2 to S3 are executed repeatedly until the iteration termination condition is met, the global optimal path in all iterations is output as a recommendation result, and the recommendation result at least comprises the target parking lot, the distance and the passing time information. The method is suitable for parking lot recommendation.

The application discloses a PLC program automatic debugging method based on an ant colony optimization algorithm, parses information and constructs a multi-PLC controller debugging action collaborative work graph and a constraint set; generates a discrete debugging action sequence; generates a first candidate parallel debugging scheme; performs a debugging action exchange, a debugging port rearrangement and a network bandwidth redistribution operation based on a time axis; inputs a second candidate parallel debugging scheme into a consistency and safety checker for checking, deploys a shadow breakpoint and a shadow forced write in a corresponding controller to construct a minimum disturbance debugging environment; updates a pheromone matrix and a tabu attribute table according to collected debugging data to form an adaptively adjusted third candidate parallel debugging scheme; and a debugging terminal condition is satisfied and a final parallel PLC controller collaborative debugging scheme is output. The application greatly improves the ability of the scheme to jump out of a local optimum and cope with multiple constraint field disturbances.

The application provides a ship steel plate yard storage operation planning method considering pretreatment time, which comprises the following steps: collecting the storage sequence of the steel plate, the pretreatment time of the storage steel plate, grouping according to the manufacturing date of the section where the steel plate is located, determining the parameters of the yard, and determining the moving time of the travelling crane between different stacking positions; determining the initial storage sequence of the steel plate and the plate turning result through a heuristic algorithm; setting the pheromone matrix value of the ant colony and the weight of the pheromone value and the heuristic value, adopting the ant colony algorithm, and iteratively obtaining the steel plate storage operation scheme of each stage; determining the plate turning result of the storage operation scheme obtained at each iteration, and updating the optimal storage operation scheme, the pheromone matrix and the weight of the pheromone value and the heuristic value; and judging whether the stopping condition of the method is reached. The method fully considers the pretreatment time information of the steel plate, reasonably plans the storage stacking position of the steel plate, and reduces the plate turning times when the steel plate is discharged.

The application provides a method and system for optimizing SNP interaction selection precision based on an ant colony algorithm, and the method comprises the following steps: each artificial ant selects an SNP interaction in a search space, all artificial ants are divided into several populations, and an adaptive function is allocated to each population, and the adaptive function is used to evaluate the correlation between the SNP interaction and a disease phenotype; an information matrix is updated by using any pheromone updating strategy; in each iteration process of the ant colony algorithm, a self-learning mechanism is set by taking the maximum cumulative reward of the ants as a target, and the pheromone updating strategy is changed through the self-learning mechanism. Based on the method, a system for optimizing SNP interaction selection precision based on the ant colony algorithm is also provided. The application is used for accurately selecting SNP interactions related to a disease phenotype, several different path selection strategies are designed, and the path selection strategy which can bring the maximum selection ability to the algorithm is adaptively selected in the search process of the algorithm based on reinforcement learning.

This invention discloses a scheduling and control method and system for the co-production of bioproteins and ethanol from syngas, relating to the field of scheduling and control technology. The method includes: calculating the relative biomass bias of ethanol based on the operating data of the syngas co-production fermentation system; calculating a comprehensive evaluation quantity based on the relative biomass bias of ethanol; constructing a set of gas injection path rearrangement actions based on the configuration data of the controllable actuators of the fermentation reactor, and obtaining a structural intervention action library based on the set of gas injection path rearrangement actions; obtaining an updated pheromone matrix based on the comprehensive evaluation quantity and the structural intervention action library, and obtaining a target action sequence based on the updated pheromone matrix. This invention improves the ability to regulate complex gas-liquid distribution states.

The invention discloses a path planning method and system based on an improved self-adaptive ant colony algorithm, and the method comprises the following steps: initializing, loading traveling salesman problem instance data of a plurality of places based on basic parameters and dynamic parameters of the improved self-adaptive ant colony algorithm, constructing a distance matrix between the places based on Euclidean distance, and performing path planning on the distance matrix. Initializing a symmetric pheromone matrix; iterative optimization is carried out, each ant starts from a randomly selected initial site, a complete path is constructed step by step through an improved state transition probability rule, the path length of each ant is calculated, and the current iterative optimal path and the length thereof are recorded; iteration is terminated, and when the number of iterations reaches the preset value, the algorithm stops running; according to the method, statistics is carried out on results of multiple rounds of operation, the average optimal distance of the multiple rounds of operation and the minimum distance in the multiple rounds of operation are obtained, namely, the optimal planning path is obtained, a self-adaptive volatilization mechanism is introduced, the pheromone volatilization rate is dynamically adjusted according to the number of iterations, and the local optimum problem is solved.

The present invention relates to the field of software engineering, and specifically to an experimental implementation method for chaos engineering application scenarios based on an ant colony algorithm; performing structured processing and time series modeling on the collected complex raw data; importing the processed information into the ant colony algorithm, determining parameters such as the number of ant colonies, pheromone concentration, evaporation rate, and initializing the pheromone matrix during initialization, and utilizing resource usage and relevant business information to assist in decision-making. During the execution of the algorithm, ants select paths based on a probability formula, determine the weights of pheromones and heuristic indicators based on the fault history and business information, and adjust the pheromone matrix according to the volatilization, addition, and update rules after traversal, and repeat until the conditions are met. The algorithm outputs an adjacency matrix containing pheromone, node, and edge information, which is used to analyze fault paths, impacts, propagation, and generate visual charts. This method can improve experimental efficiency, accuracy, and dynamic adaptability, and enhance system reliability and resilience.

The invention provides a test case dynamic scheduling method and system based on an ant colony algorithm, and relates to the technical field of software test optimization. The method comprises the steps that core variables and parameters are initialized; analyzing the dependency relationship of the test cases; estimating the execution time of the test case according to the dependency relationship of the test case; selecting a to-be-executed test node according to the test case execution time; selecting a test case to be executed according to the task-node distribution table; according to the to-be-executed test case, updating a node operation state; according to the task execution result, the total completion time and the pheromone matrix, updating a test case execution state and the pheromone matrix; and obtaining an optimal scheduling scheme according to the current number of iterations or the total completion time fluctuation of continuous multiple iterations. According to the method, a load balancing problem is converted into an integer programming problem through mathematical modeling, optimal task allocation is realized by utilizing a heuristic search mechanism of the ant colony algorithm, and the efficiency and stability of a test system facing uncertain factors are remarkably improved.

The application discloses a cold-chain low-carbon transport vehicle scheduling method under fuzzy driving time, which comprises the following steps: main and auxiliary population initialization; fusing the main population and the auxiliary population into a temporary population; performing niche reservation operation on individuals in the temporary population according to multiple optimization target values in a scheduling model, replacing individuals in the main population with the reserved ps elite individuals in the temporary population, and obtaining an updated main population; determining a non-inferior solution set of the updated main population according to the multiple optimization target values in the scheduling model by using a Pareto non-dominated relationship; updating a pheromone matrix by using individuals in the non-inferior solution set of the updated main population, sampling the pheromone matrix to update an auxiliary population; interacting individuals in the updated main and auxiliary populations; performing local search on individuals in the non-inferior solution set of the main and auxiliary populations after the interaction; and judging a termination condition. By the method, a high-quality non-inferior solution set of the cold-chain low-carbon transport vehicle scheduling problem under fuzzy driving time can be obtained in a short time.

This application provides a trajectory planning method and system for defect detection robots, relating to the field of equipment planning technology. The method includes: constructing a digital twin of a production line based on various digital models; determining the starting measurement point and the robot to be visited by the ant in the current iteration from a set of measurement points arranged for the body-in-white model; calculating the selection probability of all possible decisions based on the current pheromone matrix and heuristic information matrix; the elements in the heuristic information matrix are obtained based on the simulation results of the digital twin of the production line; selecting the target decision from these decisions and updating the heuristic information matrix in the current iteration accordingly; constructing the corresponding solution when all measurement points have been visited; evaluating each solution through an objective function to obtain the current optimal solution, and updating the pheromone matrix elements based on this and the global optimal solution; and determining the latest global optimal solution as the optimal trajectory for defect detection when the iteration meets the termination condition. The aim is to improve the efficiency of defect detection trajectory planning.

The invention provides a mobile robot path planning method based on an improved ant colony algorithm, and belongs to the field of mobile robot autonomous navigation. Comprising the following steps: S1, initializing a pheromone matrix by using an ant colony algorithm; s2, ant colony algorithm pheromones are dynamically updated; s3, after the maximum number of iterations of the ant colony algorithm is reached, a genetic algorithm is carried out to initialize a population; s4, designing a fitness function; s5, crossover, variation and path smoothing are carried out; and S6, performing final smoothing processing on the optimal path output by the genetic algorithm, and storing and outputting the optimal path. According to the method, the global optimal solution solving capability of the ant colony algorithm is reserved, meanwhile, the convergence speed and the path smoothness are high, and the navigation requirement for the mobile robot in the real environment is better met.

This invention discloses a method and apparatus for optimizing multi-logistics vehicle service scheduling based on a multi-pheromone matrix ant colony system, belonging to the field of logistics scheduling optimization technology. It includes: a path construction strategy based on a multi-pheromone matrix, a local optimization strategy based on logistics task deletion and insertion, a pheromone matrix matching strategy based on path similarity, and a global update strategy for the multi-pheromone matrix. The method iteratively optimizes the multi-logistics vehicle service scheduling scheme using an ant colony system algorithm until the iteration termination condition is met, outputting the final globally optimal service scheduling scheme. This invention maintains a pheromone matrix for each logistics vehicle, selects logistics tasks based on the multi-pheromone matrix, and efficiently and accurately constructs a multi-logistics vehicle service scheduling scheme by minimizing the maximum value of the service cost of all logistics vehicles.

The invention discloses a PLC program automatic debugging method based on an ant colony optimization algorithm. The method comprises the steps that information is analyzed, and a multi-PLC debugging action collaborative operation diagram and a constraint set are constructed; generating a discrete debugging action sequence; generating a first candidate parallel debugging scheme; executing debugging action switching, debugging port rearrangement and network bandwidth redistribution operation based on a time axis; inputting the second candidate parallel debugging scheme into a consistency and security checker for checking, and deploying a shadow breakpoint and shadow mandatory writing in a corresponding controller to construct a minimum disturbance debugging environment; updating the pheromone matrix and the tabu attribute table according to the acquired debugging data to form a third candidate parallel debugging scheme for adaptive adjustment; and the debugging terminal meets the conditions and outputs a final parallel PLC collaborative debugging scheme. According to the method, the capability of jumping out of local optimum and coping with multi-constraint field disturbance of the scheme is greatly improved.

The invention discloses a multi-device master-slave type intelligent cooperative control and adjustment system, and relates to the technical field of artificial intelligence, and the system comprises a data collection unit, a data calculation unit, and a cooperative control unit. Wherein the data acquisition unit is used for acquiring multi-source heterogeneous data of the heat supply system in real time and defining a cooperative control instruction set based on the multi-source heterogeneous data; the data calculation unit is used for constructing an intelligent cooperative control model based on the obtained hierarchical pheromone structure between the devices through a state transition probability inspired by thermodynamics; according to the invention, thermodynamic coupling and pipe network delay between the devices are combined, control is carried out through a dynamic pheromone matrix based on an optimized ant colony algorithm, device level difference and collaborative requirements are effectively expressed, optimization effect limitation is avoided, and the method is suitable for large-scale popularization and application. And the overall performance of the system is comprehensively improved.

The application discloses a logistics vehicle multi-service scheme planning method based on a ranking ant colony algorithm, which maintains multiple pheromone matrices through the ranking ant colony optimization algorithm, iteratively finds multiple optimal service schemes, and proposes an optimal service scheme saving strategy based on service scheme similarity; a key service sequence mining mechanism based on the optimal service scheme is designed, a service scheme local optimization method fusing the key service sequence and 2-opt is proposed; a sub-ant colony division mechanism based on service scheme similarity is further designed, a matching rule based on the optimal service scheme of the sub-ant colony and a representative scheme of the pheromone matrix is proposed; a multiple pheromone matrix updating mechanism based on optimal matching is designed, the dispersion search of the ant colony to multiple regions of a solution space is realized, and the purpose of locating multiple optimal service schemes in different regions is achieved. The application can provide multiple optimal service schemes for logistics vehicles, provide multiple decision supports for logistics companies, and improve the flexibility of logistics vehicles serving logistics tasks.

The invention provides a ship selection method for a semi-submerged ship / heavy lift ship industrial module joint stowage ant colony optimization algorithm. The method comprises the following steps: initializing a ship score and a pheromone matrix of each alternative ship; according to the ship score and the pheromone matrix, selecting a ship which is most suitable for stowage through an ant colony optimization algorithm; carrying out cargo stowage according to the ship most suitable for stowage, carrying out space utilization rate and filling rate evaluation on stowage results, generating an evaluation result of each ship, and updating a corresponding ship score according to the evaluation result; according to the updated ship score, space utilization rate and filling rate evaluation, splitting the cargo into a plurality of modules, and allocating the modules to different voyage numbers; and the generated voyage number and module splitting scheme is converted into final actual stowage operation, a stowage optimization model is constructed to optimize the actual stowage operation, and a final ship selection method is generated.

The invention provides an unmanned aerial vehicle coverage path planning method based on deep reinforcement learning, and belongs to the technical field of unmanned aerial vehicles. Comprising the following steps: dividing a terrace coverage area into a plurality of honeycomb units, and defining attributes of the honeycomb units and calculation functions and parameters of energy consumption of the unmanned aerial vehicle; modeling the decision process of the unmanned aerial vehicle in the incomplete information environment by adopting a partially observable Markov decision process POMDP, and formalizing the decision process of the unmanned aerial vehicle in the incomplete information environment into a quintuple POMDP model; designing a pheromone system of a dual-channel pheromone guiding mechanism, performing adaptive weight fusion on static pheromones and dynamic pheromones, and updating a pheromone matrix; and S4, designing a DRQN reinforcement learning network, designing a PPRL algorithm based on a pheromone adaptive fusion mechanism and the DRQN reinforcement learning network, solving a partially observable Markov decision problem, and obtaining an unmanned aerial vehicle coverage path. According to the invention, coverage path planning can be effectively carried out in the terrace environment.

The invention relates to the technical field of ship navigation and autonomous collision avoidance, and discloses an inland river bidirectional channel ship driving route autonomous collision avoidance optimization method based on a BAS algorithm, and the method comprises the following steps: S1, judging the relative speed and course angle state of a ship, and determining the dynamic driving risk degree; s2, searching in continuous space coordinates, and determining an updating position of a target function value by combining a fitness function; s3, comparing fitness states by using a BAS algorithm, updating the pheromone matrix, and determining a historical optimal target value; s4, generating a reference point set according to ship conflict positions, and performing decision search by using an Ackley / Rosenbrock function; and S5, dynamic scene transition is completed under a finite-state machine, an autonomous collision avoidance decision constraint formula is generated, and the route uncertainty deviation parameter is corrected. According to the method, the global optimization capability of the BAS algorithm is introduced, and dynamic risk assessment and a continuous space efficient search mechanism are combined, so that accurate autonomous collision avoidance optimization of the inland river bidirectional channel ship driving route is realized.

The application discloses a kind of distributed energy resource intelligent scheduling methods based on Internet of Things, it is related to Internet of Things technical field, including, the operating data of distributed energy equipment is collected and pretreated, obtain equipment operating dataset, and the group intelligence initialization of equipment operating dataset is carried out, generates initial pheromone matrix;Equipment operating dataset and initial pheromone matrix are locally optimized, generate updated pheromone matrix and equipment candidate scheduling scheme, and obtain local optimal scheduling scheme by screening and verification;Quantum computing node receives local optimal scheduling scheme, and local optimal scheduling scheme is used as initial solution, constructs global optimization problem, outputs global optimal scheduling scheme, while converting into global scheduling instruction;The application captures equipment interaction, economic factors and multidimensional constraints within network range by formulating global optimization problem, realizes coordination between equipment and constraint compliance, prevents the problem of unstable power grid.

The invention belongs to the technical field of system engineering and meta-model design, and particularly relates to a rescue system meta-model design method based on ant colony evolution comprehensive optimization, the method is carried out in a macroscopic cycle of intergenerational evolution, and each generation of cycle comprises the following steps: step 1, population construction based on ant colonies; 2, population evaluation based on an advanced theory; 3, global pheromones are updated, the comprehensive fitness score of each rescue system meta-model scheme output in the second stage is input, and an updated pheromone matrix is output; the method comprises the following steps: repeatedly executing the three stages until a preset maximum number of iterations or optimal solution convergence is reached; and finally, recording a rescue system meta-model scheme with the highest fitness in the whole evolution history as the output of the method. According to the method, a recombination process of an evolutionary algorithm is replaced by a construction process of an ant colony, and each generated candidate scheme meets grammar and structural constraints of a meta-model.

The application discloses a multi-SoC cooperative task allocation method based on quantum ant colony optimization, and collects node resource portrait set and task attribute set of each system-on-a-chip node in a multi-SoC system; a task-resource mapping diagram is constructed; a quantum encoding task set is obtained; the quantum encoding task set is loaded to a search state space of a quantum ant individual, an information element matrix is set, a quantum rotation angle matrix is set, an initial population of quantum ant colony is obtained; an updated quantum state population is obtained; delay indexes, power consumption indexes and reliability indexes of each deterministic task allocation result are calculated according to the node resource portrait set, a candidate feasible solution set meeting real-time constraints is screened out; and a global scheduling scheme is obtained. The application significantly improves modeling granularity and allocation accuracy of task allocation under multi-domain heterogeneous resources, effectively avoids bandwidth contention and delay mutation problems in cross-node and cross-domain migration, and realizes real-time and high adaptability of task allocation.

The application provides a path planning method based on a multi-target optimization smooth ant colony algorithm, comprising: establishing a grid map, determining a starting point and a target point, and initializing ant colony algorithm parameters; initializing a pheromone matrix according to guide path information generated by a Floyd algorithm and initializing a taboo table; constructing a candidate solution according to the taboo table and an optimized state transition function, and selecting a next node according to a roulette wheel principle; updating the taboo table according to the next node, recording path nodes and path lengths of ants, judging whether the ants reach the target node, and judging whether a preset maximum number of ants is reached, if yes, performing global updating according to an optimized pheromone updating mode, and performing smoothing processing on the path; and performing iteration according to a preset maximum iteration number, and obtaining an optimal path. The application optimizes and improves a traditional ant colony algorithm, so as to achieve the effects of accelerating the convergence speed of the algorithm, avoiding a local optimal solution and smoothing a path.

The invention provides a decentralized swarm intelligence cooperative control method and system of a robot system, belongs to the technical field of multi-robot cooperative control, and can at least partially solve the problems that an existing robot system is high in communication overhead; role distribution depends on central planning or assumes that global information is available; the formation model lacks a weighting mechanism for role behavior differences; in order to solve the problem of lack of a local robust strategy for failure recovery in the prior art, each robot constructs a neighbor table through local communication, calculates local fitness of different roles based on own state and environment information, and maintains a virtual pheromone matrix. And according to the pheromone matrix and the local fitness, roles are autonomously selected according to a probability transfer rule, and an expected motion control quantity is generated in combination with aggregation, separation and alignment rules so as to realize group formation control. Meanwhile, the pheromones are updated according to the task execution effect, role redistribution is triggered when the key role fails, and self-adaptive cooperative control over the robot group is achieved.