Hyunki Seong*1, David Hyunchul Shim1
1Korea Advanced Institute of Science and Technology (KAIST)
{hynkis,hcshim}@kaist.ac.kr
International Conference on Intelligent Robots and Systems (IROS) 2024
Abu Dhabi, UAE
Overview & Abstract
This paper focuses on the acquisition of mapless navigation skills within unknown environments. We introduce the Skill Q-Network (SQN), a novel reinforcement learning method featuring an adaptive skill ensemble mechanism. Unlike existing methods, our model concurrently learns a high-level skill decision process alongside multiple low-level navigation skills, all without the need for prior knowledge. Leveraging a tailored reward function for mapless navigation, the SQN is capable of learning adaptive maneuvers that incorporate both exploration and goal-directed skills, enabling effective navigation in new environments. Our experiments demonstrate that our SQN can effectively navigate complex environments, exhibiting a 40% higher performance compared to baseline models. Without explicit guidance, SQN discovers how to combine low-level skill policies, showcasing both goal-directed navigations to reach destinations and exploration maneuvers to escape from local minimum regions in challenging scenarios. Remarkably, our adaptive skill ensemble method enables zero-shot transfer to out-of-distribution domains, characterized by unseen observations from non-convex obstacles or uneven, subterranean-like environments.
Main Results
Trajectory results of evaluation policies in the evaluation environments, with distance fields visualizing the true distance cost from the goal point.
Skill trajectories of SQN across various environments. For brevity, a single trajectory is represented in SubT Cave.