一作ACL 2026Poster· Natural Language Processing
R obo F ail R ing: Retrieval-Augmented and Language Grounding Failure Detection for VLM -enabled Robotic Manipulation
Chenduo Ying · Linkang Du · Yuanchao Shu · Peng Cheng
摘要
Reliable failure detection and causal reasoning are critical in robotic manipulation, as their absence risks robot damage and endangers human safety.Although recent Vision–Language Models (VLMs) are employed to attempt failure detection and causality reasoning, they typically make retrospective a...