← 研踪 PaperTrailarXiv:2611.13685 · v1
Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos
首次提交 2026-11-10 15:33
版本更新 2026-11-10 15:33
雷达观测 2026-11-11 11:04
摘要
In this paper, we investigate how human egocentric videos can benefit robot policy learning without action supervision. Building on a pretrained VLM, we propose Shared Prediction on Action and Representation (SPAR), an MoT architecture in which future visual state prediction can provide independent and complementary learning signals alongside action prediction. We find that representations learned from egocentric videos improve downstream performance on out-of-distribution robot tasks, with further gains as video data scales. We also study the effects of objective choices and data curation, providing insights into how to leverage action-free videos for scalable robot learning.
作者备注：Project Page: https://llong-cs.github.io/EgoGuidance
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-10 15:33 · 最新观测版本
Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos
In this paper, we investigate how human egocentric videos can benefit robot policy learning without action supervision. Building on a pretrained VLM, we propose Shared Prediction on Action and Representation (SPAR), an MoT architecture in which future visual state prediction can provide independent and complementary learning signals alongside action prediction. We find that representations learned from egocentric videos improve downstream performance on out-of-distribution robot tasks, with further gains as video data scales. We also study the effects of objective choices and data curation, providing insights into how to leverage action-free videos for scalable robot learning.
查看此版本解读 →查看此版本原文 ↗