A multi-robot task assignment method for intelligent storage system

Abstract

The invention discloses a multi-robot task assignment method for an intelligent storage system. According to the intelligent storage task assignment problem, a multi-objective task assignment model is established, and a time cost function and an energy consumption cost function are designed; A multi-objective genetic algorithm for non-dominated sorting; and a new iterative process is added to the framework of the above-mentioned genetic algorithm to ensure that it can further converge to a better non-dominated solution. The invention obtains a better non-dominated solution by sorting the dominance levels of each optimization component, and improves the probability that the algorithm converges to a better non-dominated solution through population restart and an elite pool mechanism. And at the same time, the present invention takes into account the time cost and energy consumption cost of the multi-robot system in the task allocation problem of the multi-robot system, can solve the task allocation problem in the multi-robot system more systematically, and improve the scientificity and rationality of the task allocation results.

Description

technical field [0001] The invention relates to a multi-robot task assignment method for an intelligent storage system, which belongs to the field of intelligent storage robot control. Background technique [0002] The sorting and transportation of goods is an important part of the intelligent storage system and an important part of the future social Internet of Things system. For the future intelligent warehousing system, the multi-robot system can effectively improve the efficiency of goods sorting and reduce the time of package handling through collaboration. However, multi-robot systems working in the same space are prone to task interference and conflicts, which can lead to problems such as deadlocks. Therefore, the task distribution of multi-robot system is an important part of intelligent storage system. [0003] At present, most of the multi-robot system task allocation algorithms take the minimization of the total path of the multi-robot system as the primary goal...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the multi-robot system task allocation algorithms take the minimization of the total path of the multi-robot system as the primary goal, which leads to the unbalanced task allocation of each robot, and finally leads to some robots waiting for a long time for a robot to return during sorting. In the case of the actual low efficiency

There is also a Single-Function-Optimization (SFO) algorithm whose primary goal is to minimize the linear combination of the variance of the multi-robot system and the total path of the multi-robot system. As a result, the shortcomings of time cost and energy cost cannot be taken into account at the same time

Images