Collaborative approach for swarm robot systems based on distributed DRL

Abstract

Navigation and task allocation for swarm robot systems are more difficult than for a single robot. In swarm robot systems, navigation and task allocation difficulties are compounded by challenges such as a dynamic environment, exponentially increasing complexity, and collaboration. In this study, a deep reinforcement learning (DRL) based collaborative approach for navigation and task allocation is proposed, which can be trained at the same time as the training time of a single robot and achieve a high success rate. The proposed approach implements DRL as a distributed architecture. Furthermore, the proposed approach uses adaptive reward mechanisms, a leaderless control approach for environment control, and a simultaneous learning approach for learning. The proposed approach is evaluated by the success rate of reaching the target, the success rate of reaching the target by the shortest path, the success rate of selecting a task, and the success rate of selecting the nearest task. In addition, the costs of the non-collaborative approach are compared with the costs of the collaborative approach. The evaluations show that the success rate of navigation and collaboration of the robots increased and the cost decreased. Thus, the performance of the proposed approach is verified.