Coordination of a Multi Robot System for Pick and Place Using Reinforcement Learning

Recent advances in deep reinforcement learning are enabling the creation and use of powerful agent systems in complex areas such as multi-robot coordination. These show great promise to help solve many of the difficult challenges of rapidly growing domains such as smart manufacturing. In this paper we describe our ongoing work on the use of single agent deep reinforcement learning to optimise coordination in a multi-robot pick and place (PnP) system. We describe the implementation of the DQN agent as well as a bespoke multi robot PnP simulator, implemented as an OpenAI Gym environment. We present our initial results and outline future work.