Multi-robot Formation Control Using Reinforcement Learning Method

Formation is a good example of the research for multi-robot cooperation. Many different ways can be used to accomplish this task, but the main drawbacks of most of these methods are that robots can’t self-learn. In Brooks’ behavioral opinion, this paper is to verify that the reinforcement learning method can be used for robots to select different behaviors in various different situations. Experiments are performed to illustrate the team robots’ capability of self-learning and autonomy. The results show that the robots can get a self-formation in a barrier environment after learning.