Asymmetric Self-Play-Enabled Intelligent Heterogeneous Multirobot Catching System Using Deep Multiagent Reinforcement Learning

Aiming to develop a more robust and intelligent heterogeneous system for adversarial catching in security and rescue tasks, in this article, we discuss the specialities of applying asymmetric self-play and curriculum learning techniques to deal with the increasing heterogeneity and number of different robots in modern heterogeneous multirobot systems (HMRS). Our method, based on actor-critic multiagent reinforcement learning, provides a framework that can enable cooperative behaviors among heterogeneous multirobot teams. This leads to the development of an HMRS for complex catching scenarios that involve several robot teams and real-world constraints. We conduct simulated experiments to evaluate different mechanisms' influence on our method's performance, and real-world experiments to assess our system's performance in complex real-world catching problems. In addition, a bridging study is conducted to compare our method with a state-of-the-art method called S2M2 in heterogeneous catching problems, and our method performs better in adversarial settings. As a result, we show that the proposed framework, through fusing asymmetric self-play and curriculum learning during training, is able to successfully complete the HMRS catching task under realistic constraints in both simulation and the real world, thus providing a direction for future large-scale intelligent security & rescue HMRS.