Episodic Learning for Safe Bipedal Locomotion with Control Barrier\n Functions and Projection-to-State Safety

摘要

This paper combines episodic learning and control barrier functions in the\nsetting of bipedal locomotion. The safety guarantees that control barrier\nfunctions provide are only valid with perfect model knowledge; however, this\nassumption cannot be met on hardware platforms. To address this, we utilize the\nnotion of projection-to-state safety paired with a machine learning framework\nin an attempt to learn the model uncertainty as it affects the barrier\nfunctions. The proposed approach is demonstrated both in simulation and on\nhardware for the AMBER-3M bipedal robot in the context of the stepping-stone\nproblem, which requires precise foot placement while walking dynamically.\n