Simulation platform enables teamwork for multiple humanoid robots
CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration
RoboticsArtificial IntelligenceComputer Vision and Pattern RecognitionMachine Learning
Summary
Many tasks done by humans require two or more people working closely together, but robots often work alone. The authors created CoHuB, a computer simulation that lets multiple humanoid robots practice working together while seeing only from their own perspective. They set up 10 different tasks involving two or three robots and collected real human-controlled examples to guide robot learning. Their tests show that coordinating vision and movements among multiple robots is still very challenging. CoHuB provides a way to develop and test new methods for robot teamwork.
What this means in practice
- •For robotics engineers: Test and improve control algorithms for coordinated tasks with multiple humanoid robots using realistic visual perspectives.
- •For virtual reality developers: Develop training tools that use multi-person VR setups to create coordinated humanoid robot demonstrations.
Authors
Hyunjin Park, Jebeom Chae, Minwoo Park, Sunghyun Park, Hanjun Yoo, Seoyeon Choi, Soochul Yoo, Joohwan Seo, Sarmad Idrees, Jae-Sang Hyun, Jongmin Lee, Roberto Horowitz, Youngwoon Lee, Jongeun Choi
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.