检查机器人:评估具身AI的能力与安全性
Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI
浏览论文内容
中文总结 AI 辅助
本文介绍Inspect Robots,一个模块化开源框架,用于评估具身智能体的能力与安全性,并通过评估六种基于前沿语言模型的策略展示其功能,发布三个月内下载量近10万。
中文摘要 AI 辅助
通用语言模型越来越能够控制机器人硬件。因此,理解这些模型在具身化时的能力与安全性,对于理解其社会影响和风险日益重要。为此,我们推出了检查机器人(Inspect Robots),一个模块化的开源框架,用于开发和运行具身智能体的评估。检查机器人将可定制、可重用的抽象概念(用于指定物理评估和分析其结果)与自动化评估设置、执行和终止的基础设施相结合。我们通过使用检查机器人评估基于前沿语言模型的六种策略的能力与安全性来展示其功能。检查机器人自发布以来已获得显著的早期采用,在发布后的三个月内下载量接近10万次。
英文摘要
General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodied is therefore increasingly important for understanding their societal impact and risks. To this end, we introduce Inspect Robots, a modular, open-source framework for developing and running evaluations of embodied agents. Inspect Robots pairs customizable, reusable abstractions for specifying physical evaluations and analyzing their results with infrastructure that automates evaluation setup, execution and termination. We demonstrate Inspect Robots by using it to evaluate the capabilities and safety of six policies based on frontier language models. Inspect Robots has seen significant early uptake, receiving nearly 100,000 downloads in the three months since its release.
发表机构
- Robocurve
- University of Southern California(南加州大学)
- San Jose State University(圣何塞州立大学)
- Indian Institute of Technology Bhilai(印度理工学院比莱校区)
- University of Maryland(马里兰大学)
- Stony Brook University(石溪大学)
- Arizona State University(亚利桑那州立大学)
- Brown University(布朗大学)
机构由 AI 辅助整理,请以论文原文为准。