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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wu, D., Zheng, D., Sheng, J., Wei, Z., Zhang, S., Xie, Z., Sun, X., Zheng, J., Song, Z., Zhang, J., & Chen, J. (2026). AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining. https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining
MLA 9
Wu, Di, et al. "AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining." https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining.
Chicago (author–date)
Wu, Di, Dongchen Zheng, Junhe Sheng, Zhongxing Wei, Songxin Zhang, Zejian Xie, Xiaoquan Sun, Junyang Zheng, Zhuoyang Song, Jiaxing Zhang, and Jiayu Chen. 2026. "AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining." https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining.
Harvard
Wu, D., Zheng, D., Sheng, J., Wei, Z., Zhang, S., Xie, Z., Sun, X., Zheng, J., Song, Z., Zhang, J. and Chen, J. (2026) 'AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining', Available at: https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining.
Vancouver
Wu D, Zheng D, Sheng J, Wei Z, Zhang S, Xie Z, et al. AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining. https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining
IEEE
D. Wu, D. Zheng, J. Sheng, Z. Wei, S. Zhang, Z. Xie, X. Sun, J. Zheng, Z. Song, J. Zhang, and J. Chen, "AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining," https://omanscience.com/en/articles/atomego-exploring-ego-robot-integration-for-embodied-foundation-model-pretraining.