---
title: "Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.37533v1"
permalink: "https://feed.astralor.com/items/itm_383e6541a2de89daa34c34cb"
published: "2026-10-27T16:53:18.000Z"
score: 53
channel: "ai"
tags: ["多模态","Which Hand Was","Late","Diagnosis","Robot Failure Recovery","Bimanual Tool Use","Failure","VLMs"]
---

# Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use

## 速览

Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures …

## 关键点

- Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration.
- Bimanual tool use adds failures of other kinds: a tool that slips out of its socket while still held, two correct gestures made at different times, and attempts that fail for two reasons at once.
- On a simulated bimanual tool-use task whose failure causes are read from the recorded trace, we measure what each sensing channel lets a diagnoser tell.

## 全文

Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures of other kinds: a tool that slips out of its socket while still held, two correct gestures made at different times, and attempts that fail for two reasons at once. On a simulated bimanual tool-use task whose failure causes are read from the recorded trace, we measure what each sensing channel lets a diagnoser tell. The tool's slip is read on the tool hand; which hand was late is read on both arms, while a sensor on one hand reads its own hand's delay and at most part of the other's; and whether a late attempt was also pushed too weakly is not identifiable from passive sensing when the tool hand is late. Within two attempts, a repair policy that escalates when the cause is not identifiable repairs as many failures as one told the true cause. A VLM's internal state carries the late hand almost perfectly, along a direction no closer to the one its answer reads than a random one; whether the answer reports it depends on the wording of the question.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_383e6541a2de89daa34c34cb