Toward the development of adaptive intelligence for dynamic legged robots

Deploying legged robots in real-world applications will require fast adaptation to unknown terrain and model uncertainty. Model uncertainty could come from unknown robot dynamics, external disturbances, interaction with other humans or robots, or unknown parameters of contact models or terrain properties. In this talk, I will first present our recent works on adaptive control and deep reinforcement learning for legged locomotion under substantial model uncertainty. In these results, we focus on the application of quadruped robots walking and running on rough terrain while carrying a heavy load. From our observation, while adaptive control can allow fast adaptation in control action, reinforcement learning can introduce adaptive behaviors in response to different terrains or scenarios. Therefore, I will also discuss some thoughts on the combination of adaptive control and reinforcement learning toward achieving long-term adaptive intelligence for dynamic legged robots.

Dr. Quan Nguyen