Hand-Eye Autonomous Delivery: Learning Humanoid Navigation, Locomotion and Reaching
Chen, Sirui, Ye, Yufei, Cao, Zi-Ang, Lew, Jennifer, Xu, Pei, Liu, C. Karen
–arXiv.org Artificial Intelligence
We propose Hand-Eye Autonomous Delivery (HEAD), a framework that learns navigation, locomotion, and reaching skills for humanoids, directly from human motion and vision perception data. We take a modular approach where the high-level planner commands the target position and orientation of the hands and eyes of the humanoid, delivered by the low-level policy that controls the whole-body movements. Specifically, the low-level whole-body controller learns to track the three points (eyes, left hand, and right hand) from existing large-scale human motion capture data while high-level policy learns from human data collected by Aria glasses. Our modular approach decouples the ego-centric vision perception from physical actions, promoting efficient learning and scalability to novel scenes. We evaluate our method both in simulation and in the real-world, demonstrating humanoid's capabilities to navigate and reach in complex environments designed for humans.
arXiv.org Artificial Intelligence
Aug-11-2025
- Country:
- Asia (0.04)
- North America > United States
- California > Santa Clara County
- Palo Alto (0.05)
- Florida > Hillsborough County
- University (0.05)
- California > Santa Clara County
- Genre:
- Research Report (0.40)
- Technology: