跳到正文
RadarAI· X:星海图 Galaxea (@GalaxeaDynamics)·· 4 小时前AI 评分38

星海图赵行 CoRL 2026 主题演讲:按时间尺度拆分机器人智能

AI 导读

星海图联合创始人兼首席科学家、清华助理教授赵行在 CoRL 2026 早期职业主题演讲中提出,机器人智能应按时间尺度而非感知/规划/控制划分:从以秒计的 System 2 推理,到数十赫兹的 System 1 策略,再到数百赫兹负责接触的 System 0。

正文 · 原文

Galaxea Dynamics· @GalaxeaDynamics · X·2026-11-12 18:29· 45 分钟前AI 评分43

AI 导读

星海图联合创始人兼首席科学家、清华助理教授赵行在 CoRL 2026 早期职业主题演讲中提出,机器人智能应按时间尺度而非感知/规划/控制划分:从以秒计的 System 2 推理,到数十赫兹的 System 1 策略,再到数百赫兹负责接触的 System 0。

正文 · 原文

🎓At CoRL 2026, Hang Zhao — Assistant Professor at Tsinghua and co-founder & chief scientist of Galaxea — gave one of this year's Early Career Keynotes.

His argument: the physical world does not pause while a robot computes. Headline numbers look strong, but the bottleneck sits elsewhere: inference latency, not the controller, sets the pace.

So he splits robot intelligence by timescale, not by perception / planning / control: from System 2 reasoning over seconds, to System 1 policies at tens of hertz, down to System 0 for contact at hundreds of hertz. Galaxea fields one model per timescale — Fast-WAM, G0.5, ActionCodec2.

Fast-WAM alone cuts single-step inference from ~800ms to 190ms, a 4x+ speedup. Slides below 👇
Keynote: 2026.corl.org · Paper: arxiv.org/abs/2608.11739

来源:Galaxea Dynamics · x.com

来源:RadarAI · aihot.news