Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos
Abstract
A mixture-of-transformers architecture jointly predicts future visual states and actions, leveraging pretrained vision-language representations and egocentric videos to improve robot policy learning without action supervision.
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.
Community
Can inexpensive, readily available human egocentric videos benefit embodied tasks without explicit action annotations? We design an architecture to uncover the implicit mutual information between actions and video, and explore its potential for generalization and scaling.
Project Page: https://llong-cs.github.io/EgoGuidance/
Get this paper in your agent:
hf papers read 2611.13685 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper