Abstract
Humanoid robots require diverse embodied experiences to acquire complex loco-manipulation and collaborative skills. However, existing humanoid data pipelines primarily focus on individual agents, while physical multi-robot collaboration remains difficult to scale due to costly hardware, dedicated spaces, and repeated resets. In this work, we introduce MATE, a Multi-Agent virtual TEleoperation platform for humanoid collaboration data collection that enables multiple geographically distributed operators to simultaneously control whole-body humanoids in a shared physics-based environment. MATE removes the need for multiple physical robots and co-located operation while preserving physically coupled interactions among humanoids, objects, and environments. Using MATE, we construct a multi-humanoid collaboration dataset comprising 24.1 hours of coordinated behavior across 2,500 joint episodes and five long-horizon tasks, including object handover, relay delivery, environment interaction, and cooperative transport. To improve learning from these interaction-rich demonstrations, we introduce EAIS, an Execution-Aligned Interaction Sampling strategy that computes sampling signals within an execution-aligned prefix and prioritizes task-progressing and interaction-critical behaviors. We evaluate MATE with representative imitation learning and vision-language-action policies across diverse collaboration tasks. Experiments demonstrate efficient data collection, effective policy learning, and zero-shot transfer from virtual demonstrations to a physical humanoid without real-world fine-tuning. Project page: https://yerik-yu.github.io/MATE/
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yu, Y., Wang, Y., Ren, Y., Feng, D., Yang, Y., Yang, B., Gong, S., Sun, Y., & Ma, Y. (2026). MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection. https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection
MLA 9
Yu, Yichuan, et al. "MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection." https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection.
Chicago (author–date)
Yu, Yichuan, Youzhuo Wang, Yiming Ren, Di Feng, Yexuan Yang, Bingxi Yang, Shengxiao Gong, Yujing Sun, and Yuexin Ma. 2026. "MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection." https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection.
Harvard
Yu, Y., Wang, Y., Ren, Y., Feng, D., Yang, Y., Yang, B., Gong, S., Sun, Y. and Ma, Y. (2026) 'MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection', Available at: https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection.
Vancouver
Yu Y, Wang Y, Ren Y, Feng D, Yang Y, Yang B, et al. MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection. https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection
IEEE
Y. Yu, Y. Wang, Y. Ren, D. Feng, Y. Yang, B. Yang, S. Gong, Y. Sun, and Y. Ma, "MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection," https://omanscience.com/en/articles/mate-multi-agent-virtual-teleoperation-platform-for-humanoid-collaboration-data-collection.