CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration

arXiv:2609.34782 · cs.RO, cs.AI, cs.CV, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.RO, cs.AI, cs.CV, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Comments: Project page: https://meat124.github.io/CoHuB/

Code: https://github.com/pink-kinematics/pink

Project page: https://nvlabs.github.io/GR00T-WholeBodyControl

License: http://creativecommons.org/licenses/by/4.0/

The gist: Many physical tasks in human environments require collaboration, from assisting a partner to jointly manipulating an object.

Terminology

Abstract

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.

Sources

Related papers