Ropedia releases Xperience 2 physical-AI dataset
Ropedia released Xperience 2, a physical-AI dataset combining 1,589 metric-scale 3D scans with 4,230 egocentric recordings covering 74 tasks and 131 hours. The data aligns environments with human movements and can be converted into interactive simulations, robot trajectories, teleoperation demonstrations, and automated long-horizon trajectories. Its accompanying paper also introduces spatial reconstruction, object localization, and spatial question-answering benchmarks.
Xperience 2 offers a released, unified resource for training and evaluating robots across aligned real-world environments, human behaviors, and reusable simulated interactions.
Computer Science > Computer Vision and Pattern Recognition
arXiv:2611.17060 (cs)
[Submitted on 12 Nov 2026]
Title:Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors
Authors:Hao Li, Fangzhou Hong, Zhaoxi Chen, Hui En Pang, Kairui Hu, Mingze Sun, Runmao Yao, Xinhao Ji, Xiyuan Zheng, Xuanli Chen, Yalun Dai, Yap Kim Hui, Dingwen Zhang, Yuanyuan Gao, Ziang Cao, Cheng Huang Yean, Jackson Peng, Rui Duan, Yaobo Liu, Zetong Wang, Ziwei Liu
View a PDF of the paper titled Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors, by Hao Li and 20 other authors
#Ropedia#Ropedia Xperience 2#HOMIE Headset 2#GPT-6 Astra#Claude Fable 5.1#Gemini 3.8 Flash