Abstract
Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions are embodiment-specific, their underlying motion intent can capture task-relevant structure that transfers across humans and robots. We introduce EgoLAP, a VLA pre-training framework that jointly learns from human and robot trajectories through a shared language-based action chain-of-thought. EgoLAP expresses motion intent as structured, temporally abstracted language actions and pairs them with motion-level reasoning grounded in scene geometry, physics, and object affordances. Across extensive real-world and simulated experiments, EgoLAP transfers human experience to robot control more effectively than alternative action representations and reaches 80.1% mean real-world task progress, a 2.3x performance gain over alternative action representations. Motion-level reasoning also outperforms a composite reasoning format that combines subtask, object-box, and visual-trace reasoning.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zha, L., Grover, S., Yin, T., Bateman, S. M., Pan, H., Zhang, M., Onol, A., Ren, A. Z., Shah, D., & Majumdar, A. (2026). EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning. https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning
MLA 9
Zha, Lihan, et al. "EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning." https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning.
Chicago (author–date)
Zha, Lihan, Shresth Grover, Tenny Yin, Samuel M. Bateman, Hengkai Pan, Mengchao Zhang, Aykut Onol, Allen Z. Ren, Dhruv Shah, and Anirudha Majumdar. 2026. "EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning." https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning.
Harvard
Zha, L., Grover, S., Yin, T., Bateman, S. M., Pan, H., Zhang, M., Onol, A., Ren, A. Z., Shah, D. and Majumdar, A. (2026) 'EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning', Available at: https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning.
Vancouver
Zha L, Grover S, Yin T, Bateman SM, Pan H, Zhang M, et al. EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning. https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning
IEEE
L. Zha, S. Grover, T. Yin, S. M. Bateman, H. Pan, M. Zhang, A. Onol, A. Z. Ren, D. Shah, and A. Majumdar, "EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning," https://omanscience.com/en/articles/egolap-learning-from-egocentric-human-data-through-language-action-reasoning.