An improved SOM-based approach to dynamic task assignment of multi-robots

Abstract

In this paper, an improved self organizing map (SOM)-based approach is proposed for multi-robot systems to tackle the task assignment problem which focuses on the self-organization issue with a large number of robots and a large number of task locations in dynamic environments subject to uncertainties. It is capable of dynamically controlling a group of mobile robots to achieve different task locations from arbitrary initial locations and directions. In the proposed approach, the robot motion planning is integrated with the task assignment, thus the robots start to move once the overall task is given. The group of mobile robots can automatically arrange the total task, and dynamically adjust their motion whenever the environment is changed, such as when some robots break down, some robots and/or some tasks are added, or the situation accruing when some tasks are changed. Different from our early study, the current direction of every robot is considered during the robot motion planning. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.