Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist

arXiv:2402.18002v1 Announce Type: cross
Abstract: This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. …

abstract arxiv assembly control cs.ai cs.lg cs.ro observability observable reinforcement reinforcement learning robotic studies study symmetry type