Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
日本語版は未提供のため、英語原文で表示しています。
要旨より
Recent vision-language-action (VLA) models have shown strong performance on local robot manipulation, yet their success does not readily translate to long-horizon mobile manipulation. In our experiments, a pretrained subtask VLA achieves 80% success rate on atomic manipulation tasks but only 19% when these skills are composed into mobile manipulation.
要旨より。当社による要約は作成中です。