Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
This research investigates the limitations of vision-language-action (VLA) models in long-horizon mobile manipulation. By diagnosing failure regimes in task planning, navigation, and local manipulation, the authors develop an agentic intervention system that improves success rates from 19% to 49% on RoboCasa365, and from 14% to 37% on BEHAVIOR-1K. The system incorporates demonstration-based planning, adaptive memory, and base adjustment, demonstrating the value of targeted interventions over uniform policy scaling.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
- code: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.19600v1 Announce Type: new Abstract: 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. We argue that this
Open source S2
VLA with demonstration-based planning guidance, adaptive visual memory, accessibility-aware base adjustment, and local end-effector adjustment. On RoboCasa365, these interventions progressively improve task success from 19% to 47%, with the finalized system reaching 49% on held-out episode seeds, compared with 18% for the baseline. The same design improves performance from 14% to 37% on BEHAVIOR-1K and from 5/20 to
Open source S4
13/20 on real-robot tasks. These results suggest that reliable mobile manipulation can be advanced by diagnosing and intervening on the current bottleneck, rather than uniformly scaling the underlying policy. Our code will be released at https://github.com/PKU-VaLuE-Lab/Cracking-Mobile-Manipulation.git.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org