Learning Force Control for Legged Manipulation

arXiv:2405.01402v1 Announce Type: cross
Abstract: Controlling contact forces during interactions is critical for locomotion and manipulation tasks. While sim-to-real reinforcement learning (RL) has succeeded in many contact-rich problems, current RL methods achieve forceful interactions implicitly without explicitly regulating forces. We propose a method for training RL policies for direct force control without requiring access to force sensing. We showcase our method on a whole-body control platform of a quadruped robot with an arm. Such force control enables us to perform …

abstract access arxiv control cs.ai cs.lg cs.ro cs.sy current eess.sy interactions manipulation policies reinforcement reinforcement learning sim tasks training type while