Anmin Zhu and Simon X. Yang
Task assignment, self-organizing map, multi-robots, neural network
In this paper, an improved approach which integrates a SOM- based path planner and a neuro-dynamics-based path tracker is proposed for multi-robot systems to tackle the task assignment problem. This approach 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. 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 earlier studies [1]–[3], the current direction of every robot is considered during the robot motion. The addition of a path tracker guarantees the tracking paths of the robots being smooth and easily applied in real robots. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.
Important Links:
Go Back
