English(EN) VLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression

机器人VLA策略在无指令的情况下意外执行任务

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 05:00

arXiv上的一篇新研究论文探讨了机器人视觉-语言-动作（VLA）策略的安全问题，特别是它们在未收到指令时执行意外任务的倾向。该研究在LIBERO-Goal模拟环境中对六个模型检查点应用了各种指令，包括空指令和无意义指令。结果显示，即使使用空提示，机器人也经常启动运动并完成指令未指定的任务。研究人员测试了三种抑制这些意外行为的方法，其中门控机制在防止对非任务输入做出反应方面最有效，但并非万无一失。 AI

影响强调了VLA策略中关键的安全问题，可能影响未来自主机器人系统的开发和部署。

排序理由该集群包含一篇详细介绍AI模型行为研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 8 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI模型行为研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Minsu Jang, Jae-Woo Choi, Youngwoo Yoon, Dohyung Kim · 2026-11-03 05:00

VLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression

arXiv:2610.41609v1 Announce Type: cross Abstract: A robot should act only on an instruction from a person or on an intent that the robot explicitly represents and generates. Unintended actions taken without such an instruction can cause risk or inconvenience to people and the env…

本文如何被排名

报道来源 [1]

VLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression

相关实体

相关话题