Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations

arXiv:2111.09971v3 Announce Type: replace-cross
Abstract: This paper addresses learning safe output feedback control laws from partial observations of expert demonstrations. We assume that a model of the system dynamics and a state estimator are available along with corresponding error bounds, e.g., estimated from data in practice. We first propose robust output control barrier functions (ROCBFs) as a means to guarantee safety, as defined through controlled forward invariance of a safe set. We then formulate an optimization problem to learn ROCBFs …

abstract arxiv control cs.lg cs.sy data dynamics eess.sy error estimator expert feedback functions laws paper practice robust safe state type