Task Allocation For Swarm Robots Used In Intelligent Warehouse Scheduling

The massive orders on the e-commerce platform puts forward high requirements for the logistics industry.As the starting point of logistics,the improvement of work efficiency of warehouse center is realistic.The application of swarm robots in the field of intelligent warehouse can change the warehouse center from the traditional “picker-to-rack” picking mode to the intelligent“rack-to-picker” picking mode.Therefore,the research on task allocation of swarm robots has both theoretical significance and application value.The main research contents of this thesis are as follows:(1)Aiming at the problem of task allocation in static environment,the fitness function is constructed according to the path cost and time cost of swarm robots to complete the task.The static task assignment model is established,and the ant colony-genetic fusion framework algorithm is proposed.First of all,the ant colony algorithm is used to optimize the initial population to get a better solution set.Then,the excellent solution set is taken as the initial population of the genetic algorithm,and the selection operator of the genetic algorithm is improved.The inversion operator is added to the genetic operation to improve the algorithm convergence ability of the population.Finally,the experimental design is carried out for small-scale and medium-to-large-scale tasks,and the proposed algorithm is compared with the task allocation scheme obtained by the ant colony algorithm and the genetic algorithm alone.The results show that the ant colony-genetic fusion framework can give full play to the advantages of the ant colony algorithm and the genetic algorithm,and obtain a more reasonable task allocation scheme.(2)Aiming at the problem of task allocation in dynamic environment,the fitness function is constructed based on the walking distance,time spent and task balance of the swarm robots to complete the task.The dynamic task allocation model is established by setting the task priority and using the event-driven mechanism and taking the power threshold of the robot as the constraint.The Cauchy migration fireworks algorithm is proposed.First of all,the Cauchy migration strategy is formulated,and use its sparks instead of Gaussian mutation sparks to solve the problem that Gaussian mutation sparks can not effectively improve the population diversity in the basic fireworks algorithm.Then,the selection strategy based on fitness function is adopted to reduce the computational overhead of the algorithm.Finally,the performance of the algorithm is verified on 6 datasets of different sizes and compared with the other three optimization algorithms.The results show that the Cauchy migration fireworks algorithm can effectively improve the task allocation efficiency of swarm robots in large-scale intelligent warehousing.