发表机构
Yonsei University; Gwangju Institute of Science and Technology; University of California, Berkeley; Seoul National University（延世大学; 光州科学技术院; 加州大学伯克利分校; 首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CoHuB是一个面向多仿人机器人协作的仿真基准，提供10个任务和VR遥操作演示，揭示了协调感知与控制中的挑战，为协作策略开发奠定基础。
AI 中文摘要
人类环境中的许多物理任务需要协作，从协助伙伴到共同操纵物体。然而，现有的仿人机器人基准主要关注单仿人机器人技能，缺乏在自我中心视觉观察下对多仿人机器人协作的评估。我们提出了CoHuB（协作多仿人机器人基准），一个在自我中心视觉观察下进行多仿人机器人协作的仿真基准。CoHuB提供10个任务，其中8个由两个仿人机器人执行，2个由三个仿人机器人执行，涵盖了多样的协作模式。我们还提供了通过多操作员VR遥操作管道收集的同步演示，其中每个操作员从其自我中心视角控制一个仿人机器人。使用代表性视觉运动策略的实验揭示了在不同形式的协调感知和控制中的重大挑战。CoHuB为开发和评估多仿人机器人协作策略提供了基础。
英文摘要
Many physical tasks in human environments require collaboration, from assisting a partner to jointly manipulating an object. Yet, existing humanoid benchmarks largely focus on single-humanoid skills and lack evaluation of multi-humanoid collaboration under egocentric visual observations. We introduce CoHuB (Collaborative Multi-Humanoid Benchmark), a simulation benchmark for multi-humanoid collaboration under egocentric visual observations. CoHuB provides 10 tasks, eight with two humanoids and two with three humanoids, spanning diverse collaboration patterns. We also provide synchronized demonstrations collected through a multi-operator VR teleoperation pipeline, in which each operator controls one humanoid from its egocentric view. Experiments with representative visuomotor policies reveal substantial challenges across different forms of coordinated perception and control. CoHuB provides a foundation for developing and evaluating multi-humanoid collaboration policies.
CommentsProject page: https://meat124.github.io/CoHuB/
