安全防护会同时抑制机器人的有害与有益行为，引发伦理与功能的矛盾。
On the Dual-Use Dilemma in Physical Reasoning and Force
- 通过案例研究发现防护机制会削弱机器人接触人体时的力控能力
- 安全策略使有害与有益动作均减少，尤其影响身体接触型操作
- 适合关注机器人安全与能力平衡的研究者和开发者
人类通过复杂的生理与心理学习过程掌握如何在世界中施加力。试图在视觉语言模型（VLMs）中复现这一能力面临双重挑战：VLM可能产生有害行为，这对与现实世界交互的VLM控制机器人尤为危险；但强制实施行为安全措施又会限制其功能与伦理潜力。我们对生成有力机器人动作的VLM进行了两项案例研究，发现安全防护机制会同时降低涉及人体接触的有害与有益行为。由此揭示的关键启示是：价值对齐可能阻碍机器人实现理想能力，这对模型评估与机器人学习具有重要意义。
原文摘要 · Abstract (English)
Humans learn how and when to apply forces in the world via a complex physiological and psychological learning process. Attempting to replicate this in vision-language models (VLMs) presents two challenges: VLMs can produce harmful behavior, which is particularly dangerous for VLM-controlled robots which interact with the world, but imposing behavioral safeguards can limit their functional and ethical extents. We conduct two case studies on safeguarding VLMs which generate forceful robotic motion, finding that safeguards reduce both harmful and helpful behavior involving contact-rich manipulation of human body parts. Then, we discuss the key implication of this result--that value alignment may impede desirable robot capabilities--for model evaluation and robot learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。