Applications
EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning
arXiv:2610.08726v1 Announce Type: cross Abstract: Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a
arXiv:2610.08726v1 Announce Type: cross 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.
Related
- From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
- FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model
- Towards VLA-Dreamer: Refining VLA Behavior Using World Models
- Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
- TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
Source: arXiv cs.AI | 2026-10-07