Abstract: Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targets remains difficult to address. With recent advances in deep learning, intelligent control techniques such as reinforcement learning have enabled agents to learn autonomously from environment interactions with little to no prior knowledge. Such methods can address the exploration-exploitation tradeoff of planning over unknown targets in a data-driven manner, streamlining the decision-making pipeline with end-to-end training. In this paper, we propose a multi-agent reinforcement learning technique (MARL) with target map building based on distributed Gaussian process (GP). We leverage the distributed GP to encode belief over the target locations in a scalable manner and incorporate it into centralized training with decentralized execution MARL framework to efficiently plan over unknown targets. We evaluate the performance and transferability of the trained policy in simulation and demonstrate the method on a swarm of micro unmanned aerial vehicles with hardware experiments.
(accepted for publication in the International Journal of Control, Automation and Systems (IJCAS))