外观
论文arXiv 2610.1960014 天前
破解移动操作：从失败诊断到智能体式机器人系统
原文链接：Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System（arXiv 2610.19600 · 发布日期：2026-10-14）
Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System
针对VLA在长程移动操作中组合成功率低的问题，论文通过失败诊断设计智能体干预，并在RoboCasa365、BEHAVIOR-1K和真机任务上验证。
核心要点
- 问题源于长程移动操作执行过程中的多类失败，而非仅局部操作能力不足。
- 系统诊断出任务规划、导航与底盘定位、局部操作三类主要失败机制。
- 在固定子任务VLA上加入示范规划、视觉记忆、底盘和末端自适应调整。
- RoboCasa365、BEHAVIOR-1K和真机任务均提升成功率，代码将开源。
验证范围与局限：验证范围为RoboCasa365、BEHAVIOR-1K及真实机器人任务。
英文摘要 (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 gap stems from failures across the execution process rather than from local manipulation capability alone. To uncover these bottlenecks, we systematically diagnose failures in long-horizon mobile manipulation and identify three dominant regimes: task planning, navigation and base positioning, and local manipulation. Based on this diagnosis, we develop failure-guided agentic intervention that augments a fixed subtask 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 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.
作者：Zixuan Wang, Jia-Ning Li, Yinzhou Tang, Yanzhao Yu, Biao Wu, Meng Fang, Xin Li, Yiwu Zhong
来源
本页事实对应的公开页面，以原文为准。