Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies
2026-06-15 • Robotics
Robotics
AI summaryⓘ
The authors address the challenge of two robots working together to move objects that connect them physically. They propose a training method called Sequential Asymmetric Imitation (SAI), which teaches one robot first with human help, then teaches the second robot to work with the first, and finally improves the first robot based on any mistakes during teamwork. This approach helps the robots coordinate better without needing both robots controlled at the same time or special communication. Their method improves success and coordination in real tasks compared to simpler training approaches.
collaborative mobile manipulationbimanual mobile manipulatorsimitation learningrobot coordinationmulti-robot systemsteleoperationcurriculum learningphase synchronizationphysical interactionrobot policy refinement
Authors
Yincong Chen, Ranpeng Qiu, Zihao Li, Yanan Zhou, Guoqiang Ren, Weiming Zhi
Abstract
Collaborative mobile manipulation requires robots to coordinate with a partially observed partner while physically interacting through shared objects. This is difficult because failures often arise not from poor local skills, but from mistimed waiting, yielding, pulling, releasing, or repositioning. We study this problem with two bimanual mobile manipulators coupled through rigid and deformable objects. We propose Sequential Asymmetric Imitation (SAI), a single-teleoperator curriculum for learning coupled multi-robot behaviors without synchronized dual-operator demonstrations or explicit inter-robot communication. SAI trains Robot A from unilateral demonstrations with a compliant human partner, trains Robot B against the deployed Robot A policy, and then refines Robot A using sparse interventions near coordination failures. This staged process exposes the policies to increasingly realistic partner behaviors, including delay, phase mismatch,insufficient yielding, and interaction conflict. Across real-world dual-robot manipulation tasks, SAI improves task success, phase synchronization, and partner-contingent yielding over independent imitation and curriculum-ablation baselines. These results suggest that physically coupled collaboration can be learned through the structure of the imitation curriculum, rather than through synchronized multi-operator demonstrations or explicit coordination mechanisms.Project page:http://cyc0429.github.io/sai-project-page/