Ropedia Xperience 2 Provides a Dataset for Scaling Physical AI Environments and Behaviors

Written by

in

Ropedia Xperience 2 contains 1,589 metric-scale 3D scans and 4,230 first-person recordings across 74 tasks, totaling 131 hours. The collected data can be converted into interactive physics simulation environments, with human motions transferred to full-body robot trajectories and additional robot behaviors generated through virtual teleoperation and automated long-horizon trajectory generation. The paper presents joint environment and behavior collection as a baseline method for scaling physical AI data.

Source:Hugging Face 社区论文精选 · Read the original

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *