发表机构
ShanghaiTech University; Nanyang Technological University（上海科技大学; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出多智能体虚拟遥操作平台MATE，实现分布式操作员同时控制人形机器人协作数据采集，构建含24.1小时数据的数据集，并引入EAIS采样策略，支持零样本迁移至物理机器人。
AI 中文摘要
人形机器人需要多样化的具身经验，以习得复杂的移动操作与协作技能。然而，现有的人形机器人数据流水线主要聚焦于单一智能体，而物理多机器人协作因硬件成本高昂、需要专用空间以及反复重置而难以扩展。在本工作中，我们提出MATE，一个用于人形机器人协作数据采集的多智能体虚拟遥操作平台，该平台使多个地理上分散的操作员能够在共享的基于物理的仿真环境中同时控制全身人形机器人。MATE消除了对多台物理机器人及同地操作的需求，同时保留了人形机器人、物体与环境之间物理耦合的交互。利用MATE，我们构建了一个多智能体人形机器人协作数据集，包含2,500个联合回合中24.1小时的协调行为，覆盖五个长时程任务，包括物体交接、接力传递、环境交互以及协作搬运。为了从这些富含交互的演示中提升学习效果，我们提出了EAIS，一种执行对齐的交互采样策略，该策略在执行对齐的前缀内计算采样信号，并优先选择推进任务和关键交互的行为。我们使用具有代表性的模仿学习和视觉-语言-动作策略，在多种协作任务上对MATE进行评估。实验表明，MATE实现了高效的数据采集、有效的策略学习，以及从虚拟演示到物理人形机器人的零样本迁移，且无需真实世界微调。项目页面：此https URL
英文摘要
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/
