As robotic systems grow to be more capable and ubiquitous, their increasing scale and complexity necessitate a shift toward robust, scalable controllers and automated synthesis methods. My research group has approached this challenge by turning to distributed (multi-agent) reinforcement learning (MARL) approaches, with an emphasis on understanding and eliciting emergent coordination/cooperation in multi-robot systems and articulated robots (where agents are individual joints). Our focus lies in improving information representations and neural architectures, as well as devising learning techniques that can help them explore their high-dimensional joint policy space, to identify and reinforce high-quality policies that naturally fit together towards team-level cooperation.

In this seminar, I will discuss the three main areas that my research group has been investigating: imitation learning, modularized/hierarchical neural structures, and learning scaffolding. I will describe these techniques within a wide variety of robotic applications, such as multi-agent pathfinding, autonomous exploration/search, traffic signal control, collaborative manipulation, and legged loco manipulation.

I will also briefly share on some of our research group’s ongoing and future work. Throughout this journey, the goal would be to highlight the key challenges surrounding learning representation, policy space exploration, and scalability/robustness of learned policies, and outline some of the open avenues for research in this exciting area of robotics.