UniBiDex: A Unified Teleoperation Framework for Robotic Bimanual Dexterous Manipulation

Zhongxuan Li^1,* Zeliang Guo^2,* Jun Hu² David Navarro-Alarcon³ Jia Pan¹ Hongmin Wu^4,† Peng Zhou^2,†

¹ Department of Computer and Data Science, The University of Hong Kong

² Dongguan Key Laboratory of Intelligent Equipment and Smart Industry, School of Advanced Engineering, The Great Bay University

³ Department of Mechanical Engineering, The Hong Kong Polytechnic University

⁴ Guangdong Academy of Sciences

* Equal contribution, † Corresponding author

Paper Code

Abstract

We present UniBiDex, a unified teleoperation framework for robotic bimanual dexterous manipulation that supports both VR-based and leader–follower input modalities. UniBiDex enables real-time, contact-rich dual-arm teleoperation by integrating heterogeneous input devices into a shared control stack with consistent kinematic treatment and safety guarantees.

The framework employs null-space control to optimize bimanual configurations, ensuring smooth, collision-free and singularity-aware motion across tasks. We validate UniBiDex on a long-horizon kitchen-tidying task involving five sequential manipulation subtasks, demonstrating higher task success rates, smoother trajectories, and improved robustness compared to strong baselines.

By releasing all hardware and software components as open-source, we aim to lower the barrier to collecting large-scale, high-quality human demonstration datasets and accelerate progress in robot learning.

System Overview

The proposed system supports two teleoperation input modalities: VR headsets and leader–follower arms. For the VR mode, we use the Meta Quest 3, while the leader–follower mode is based on the hardware design of the GELLO system. A unified dual-arm control layer minimizes collisions and inverse-kinematics failures in both modes, enabling precise and reliable bimanual manipulation.

Framework Architecture

The framework integrates heterogeneous input devices into a shared control stack with consistent kinematic treatment. The name "UniBiDex" reflects two core principles: universal device support (any input modality can be integrated) and unified constraint handling (all safety and task-related constraints are enforced through a single bimanual control module). The overall architecture consists of four decoupled modules: input preprocessing, motion retargeting, bimanual motion control, and haptic feedback.

Human commands are first smooth-filtered and converted to robot end-effector motions under the robot's base frame. During teleoperation, null-space control utilizes predefined optimal poses to maintain safe bimanual configurations. The system guides the robot towards biomechanically favorable poses, avoiding joint limits, singularities, and inter-arm collisions, while tracking complex end-effector trajectories. Haptic feedback enhances user experience and safety by providing force feedback when the robot nears workspace boundaries or encounters resistance.

Optimal Configurations for Null Space Control

Experimental Results

Kitchen-Tidying Task

We conducted a comprehensive user study with four participants performing a long-horizon bimanual manipulation task simulating a household kitchen-tidying routine. The task involves five sequential, contact-rich sub-tasks requiring dexterous coordination:

Item Unpacking: Pick up assorted items from a cloth bag and place them on the table
Shelf Organization: Sort and place items into designated positions in a multi-level kitchen shelf
Towel Folding: Fold the towel neatly along a marked midline using both grippers
Towel Placement: Place the folded towel onto the rack section of the shelf
Clamp Attachment: Attach the clamp onto the rack to secure the towel in place

Performance Comparison

Method	Overall Success Rate	Completion Time (s)	Improvement
UniBiDex (VR)	60% (24/40)	672 ± 20	+15% success, -18% time
Naive VR Baseline	45% (18/40)	816 ± 24	-
UniBiDex (Leader-Follower)	75% (30/40)	319 ± 8	+18% success, -5% time
Naive LF Baseline	57% (24/40)	335 ± 9	-

Citation

@article{li2025unibidex,
    title   = {UniBiDex: A Unified Teleoperation Framework for Robotic Bimanual Dexterous Manipulation},
    author  = {Zhongxuan Li, Zeliang Guo, Jun Hu, David Navarro-Alarcon, Jia Pan, Hongmin Wu, and Peng Zhou},
    year    = {2025},
    journal = {IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO)},
    note    = {Under Review},
    url     = {https://github.com/Dieselmarble/UniBiDex}
}