# Aether AI and UC San Diego propose RobotAgentBench to evaluate robots' open-world autonomy

- Source: 机器之心 · 微信公众号
- Published: 2026-10-29T02:04:33.000Z
- RoboHot: https://robohot.news/en/items/yavraa9h9i7bbvid0fwz81im9
- Original: https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2651070836&idx=3&sn=d4e1d5c5053ff2726f6eb66e7016dce2&chksm=85e082ce6d6409aef556153937fd9624fec43392a96163a3cec9bda6eeb3fb36f3a66a2b6aa9&scene=126&sessionid=1793284300#rd

## Summary

A research team from Aether AI and UC San Diego has proposed RobotAgentBench (RAB), a comprehensive benchmark for open-world robot autonomy, building 50 household layouts, 90 atomic tasks, 18 short-horizon tasks, 8 long-horizon tasks, and 4 types of open-ended scenarios.