Preprint
Oct 2026
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
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 c...
Zi-Xu Wang, Jia-Ning Li, Yin-Zhou Tang et al.
· 0 citations