Jim Fan(@DrJimFan)
Teleop is so 2025. Ever since we unveiled EgoScale and the dexterity scaling law, it's been clear to...
7.5内容质量
TL;DR · AI 摘要
Jim Fan提出2026年机器人学习将转向无需实体机器人的行为克隆，依托EgoScale和灵巧性扩展定律突破遥操作瓶颈。
核心要点
- 遥操作（Teleop）正被行为克隆取代，成为机器人学习新范式
- EgoScale与灵巧性扩展定律为人类数据驱动的机器人训练提供基础
- 2026年重点是通过人类中心视角数据实现机器人学习规模化
#机器人学习#行为克隆#EgoScale#AI#NVIDIA
打开原文Jim Fan on X: "Teleop is so 2025. Ever since we unveiled EgoScale and the dexterity scaling law, it's been clear to us and the ecosystem that behavior cloning directly from humans is the way to break the curse of teleop. 2026 is all about scaling robot learning without robots." / X
Don’t miss what’s happening
Teleop is so 2025. Ever since we unveiled EgoScale and the dexterity scaling law, it's been clear to us and the ecosystem that behavior cloning directly from humans is the way to break the curse of teleop. 2026 is all about scaling robot learning without robots.
Quote
Danfei Xu
@danfei_xu
·
Mar 23
Introducing EgoVerse: an ecosystem for robot learning from egocentric human data. Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling 1300+ hrs, 240 scenes, 2000+ tasks, and growing Dataset design, findings, and ecosystem 
·
58
83
593
309
Read 58 replies