别让你的机器人有害：通过安全即策略实现负责任的机器人操作
Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy
AI总结：
本文提出 Safety-as-policy 框架，结合世界模型与心智模型让机器人在操作中主动规避安全风险，并构建 SafeBox 合成数据集，在合成与真实实验中均显著优于基线方法。
摘要：
在机器人操作中不假思索地执行人类指令可能导致严重的安全风险，例如中毒、火灾甚至爆炸。在本文中，我们提出了负责任的机器人操作，要求机器人在完成指令并安全高效地执行复杂操作的同时，考虑现实世界环境中的潜在危险。然而，现实世界中的此类场景多变且对训练具有风险。为应对这一挑战，我们提出了 Safety-as-policy（安全即策略），它包括：(i) 一个世界模型，用于自动生成包含安全风险的场景并进行虚拟交互，以及 (ii) 一个心智模型，用于通过反思推断后果并逐步发展安全认知，使机器人能够在避免危险的同时完成任务。此外，我们创建了 SafeBox 合成数据集，其中包含一百个具有不同安全风险场景和指令的负责任机器人操作任务，有效降低了与现实世界实验相关的风险。实验表明，Safety-as-policy 在合成数据集和现实世界实验中都能避免风险并高效完成任务，显著优于基线方法。我们的 SafeBox 数据集显示出与现实世界场景一致的评估结果，可作为未来研究的安全有效基准。
英文摘要：
Unthinking execution of human instructions in robotic manipulation can lead to severe safety risks, such as poisonings, fires, and even explosions. In this paper, we present responsible robotic manipulation, which requires robots to consider potential hazards in the real-world environment while completing instructions and performing complex operations safely and efficiently. However, such scenarios in real world are variable and risky for training. To address this challenge, we propose Safety-as-policy, which includes (i) a world model to automatically generate scenarios containing safety risks and conduct virtual interactions, and (ii) a mental model to infer consequences with reflections and gradually develop the cognition of safety, allowing robots to accomplish tasks while avoiding dangers. Additionally, we create the SafeBox synthetic dataset, which includes one hundred responsible robotic manipulation tasks with different safety risk scenarios and instructions, effectively reducing the risks associated with real-world experiments. Experiments demonstrate that Safety-as-policy can avoid risks and efficiently complete tasks in both synthetic dataset and real-world experiments, significantly outperforming baseline methods. Our SafeBox dataset shows consistent evaluation results with real-world scenarios, serving as a safe and effective benchmark for future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
