外观
论文arXiv 2609.214611 个月前
AtomEgo：探索用于具身基础模型预训练的 Ego-Robot 融合
原文链接：AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining（arXiv 2609.21461 · 发布日期：2026-09-18）
AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining
针对机器人示范规模与多样性受限，AtomEgo通过自我中心数据与机器人协同预训练，在多任务真机和跨具身表征分析中验证。
核心要点
- 动机是利用大规模自我中心人类交互数据，缓解机器人示范规模和多样性不足。
- 提出AtomEgo系统研究，基于约2,659小时整理语料和可扩展数据处理流水线。
- 考察三类范式：联合协同训练、从自我中心到机器人渐进迁移、联合视频-动作建模。
- 结果显示自我中心数据可提升泛化，但收益取决于对齐质量和利用方式。
验证范围与局限：验证范围为多任务真机实验与语言条件跨具身表征分析。
英文摘要 (Abstract)
Embodied foundation models are constrained by the limited scale and diversity of robot demonstrations, motivating the use of large-scale egocentric human interaction data. However, how to effectively incorporate such data into embodied-model pre-training remains unclear because of substantial embodiment and action-space gaps between humans and robots. We present AtomEgo, a systematic study of ego--robot co-training supported by a curated corpus of approximately 2,659 hours and a scalable data processing pipeline. Across vision--language--action and world--action model architectures, we investigate three representative paradigms: joint co-training with domain-specific action heads, progressive ego-to-robot transfer through embodiment alignment, and joint video--action modeling. We evaluate these paradigms through multi-task real-robot experiments and language-conditioned cross-embodiment representation analysis. Our results reveal a simple principle: Data Scale * Alignment Quality --> Capability Gain; egocentric data can improve generalization, but their value depends on how effectively they are aligned and utilized. This principle can provide practical guidance for scalable ego--robot pre-training.
作者：Wu, Di, Dongchen Zheng, Junhe Sheng, Zhongxing Wei, Songxin Zhang, Zejian Xie, Xiaoquan Sun, Junyang Zheng, Zhuoyang Song, Jiaxing Zhang
来源
本页事实对应的公开页面，以原文为准。