MonoDuo: Using One Robot Arm to Learn Bimanual Policies

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bajamahal, Sandeep, Chen, Lawrence Yunliang, Lin, Toru, Ma, Zehan, Malik, Jitendra, Goldberg, Ken
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910268999598080
author Bajamahal, Sandeep
Chen, Lawrence Yunliang
Lin, Toru
Ma, Zehan
Malik, Jitendra
Goldberg, Ken
author_facet Bajamahal, Sandeep
Chen, Lawrence Yunliang
Lin, Toru
Ma, Zehan
Malik, Jitendra
Goldberg, Ken
contents Bimanual coordination is essential for many real-world manipulation tasks, yet learning bimanual robot policies is limited by the scarcity of bimanual robots and datasets. Single-arm robots, however, are widely available in research labs. Can we leverage them to train bimanual robot policies? We present MonoDuo, a framework for learning bimanual manipulation policies using single-arm robot demonstrations paired with human collaboration. MonoDuo collects data by teleoperating a single-arm robot to perform one side of a bimanual task while a human performs the other, then swapping roles to cover both sides. RGB-D observations from a wrist-mounted and fixed camera are augmented into synthetic demonstrations for target bimanual robots using state-of-the-art hand pose estimation, image and point cloud segmentation, and inpainting. These synthetic demonstrations, grounded in real robot kinematics, are used to train bimanual policies. We evaluate MonoDuo on five tasks: box lifting, backpack packing, cloth folding, jacket zipping, and plate handover. Compared to approaches relying solely on human bimanual videos, MonoDuo enables zero-shot deployment on unseen bimanual robot configurations, achieving success rates up to 70%. With only 25 target robot demonstrations, few-shot finetuning further boosts success rates by 65-70% over training from scratch, demonstrating MonoDuo's effectiveness in efficiently transferring knowledge from single-arm robot data to bimanual robot policies.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29298
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MonoDuo: Using One Robot Arm to Learn Bimanual Policies
Bajamahal, Sandeep
Chen, Lawrence Yunliang
Lin, Toru
Ma, Zehan
Malik, Jitendra
Goldberg, Ken
Robotics
Bimanual coordination is essential for many real-world manipulation tasks, yet learning bimanual robot policies is limited by the scarcity of bimanual robots and datasets. Single-arm robots, however, are widely available in research labs. Can we leverage them to train bimanual robot policies? We present MonoDuo, a framework for learning bimanual manipulation policies using single-arm robot demonstrations paired with human collaboration. MonoDuo collects data by teleoperating a single-arm robot to perform one side of a bimanual task while a human performs the other, then swapping roles to cover both sides. RGB-D observations from a wrist-mounted and fixed camera are augmented into synthetic demonstrations for target bimanual robots using state-of-the-art hand pose estimation, image and point cloud segmentation, and inpainting. These synthetic demonstrations, grounded in real robot kinematics, are used to train bimanual policies. We evaluate MonoDuo on five tasks: box lifting, backpack packing, cloth folding, jacket zipping, and plate handover. Compared to approaches relying solely on human bimanual videos, MonoDuo enables zero-shot deployment on unseen bimanual robot configurations, achieving success rates up to 70%. With only 25 target robot demonstrations, few-shot finetuning further boosts success rates by 65-70% over training from scratch, demonstrating MonoDuo's effectiveness in efficiently transferring knowledge from single-arm robot data to bimanual robot policies.
title MonoDuo: Using One Robot Arm to Learn Bimanual Policies
topic Robotics
url https://arxiv.org/abs/2605.29298