Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery

arXiv:2404.00756v1 Announce Type: cross
Abstract: Recognizing failures during task execution and implementing recovery procedures is challenging in robotics. Traditional approaches rely on the availability of extensive data or a tight set of constraints, while more recent approaches leverage large language models (LLMs) to verify task steps and replan accordingly. However, these methods often operate offline, necessitating scene resets and incurring in high costs. This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating ontologies, logical …

abstract arxiv availability constraints cs.ai cs.lg cs.lo cs.ro data detection failure framework however language language models large language large language models llms neuro recovery robotics set type verify