|国家预印本平台
首页|Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning

Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning

Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning

来源:Arxiv_logoArxiv
英文摘要

Learning effective visual representations for robotic manipulation remains a fundamental challenge due to the complex body dynamics involved in action execution. In this paper, we study how visual representations that carry body-relevant cues can enable efficient policy learning for downstream robotic manipulation tasks. We present $\textbf{I}$nter-token $\textbf{Con}$trast ($\textbf{ICon}$), a contrastive learning method applied to the token-level representations of Vision Transformers (ViTs). ICon enforces a separation in the feature space between agent-specific and environment-specific tokens, resulting in agent-centric visual representations that embed body-specific inductive biases. This framework can be seamlessly integrated into end-to-end policy learning by incorporating the contrastive loss as an auxiliary objective. Our experiments show that ICon not only improves policy performance across various manipulation tasks but also facilitates policy transfer across different robots. The project website: https://github.com/HenryWJL/icon

Junlin Wang、Zhiyun Lin

计算技术、计算机技术

Junlin Wang,Zhiyun Lin.Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning[EB/OL].(2025-05-23)[2025-06-05].https://arxiv.org/abs/2505.18487.点此复制

评论