Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot

arXiv:2404.15096v1 Announce Type: cross
Abstract: Replicating the remarkable athleticism seen in animals has long been a challenge in robotics control. Although Reinforcement Learning (RL) has demonstrated significant progress in dynamic legged locomotion control, the substantial sim-to-real gap often hinders the real-world demonstration of truly dynamic movements. We propose a new framework to mitigate this gap through frequency-domain analysis-based impedance matching between simulated and real robots. Our framework offers a structured guideline for parameter selection and the range for dynamics randomization …

abstract animals arxiv challenge control cs.lg cs.ro dynamic enabling gap movements progress reinforcement reinforcement learning robot robotics running sim type world