Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation

Jialong Li, Zhenguo Wang, Tianci Wang, Maj Stenmark, Volker Krueger

TL;DR

Quest2ROS2 addresses the challenge of scalable bi-manual VR teleoperation for data collection in robotics. It extends Quest2ROS into a ROS 2 middleware with relative-motion-based end-effector control, visualization, and dual-arm support to enhance ergonomics and task feasibility. Key contributions include the relative-motion control scheme that decouples end-effector motion from the initial controller pose, RViz-based target pose visualization, and dual-arm modes (Side-by-Side and Mirror) with straightforward gripper and pose-stream controls. The framework is modular via a BaseArmController and includes debugging tools and safety guidelines, all released as open-source to facilitate adoption and replication in robotics research.

Abstract

Quest2ROS2 is an open-source ROS2 framework for bi-manual teleoperation designed to scale robot data collection. Extending Quest2ROS, it overcomes workspace limitations via relative motion-based control, calculating robot movement from VR controller pose changes to enable intuitive, pose-independent operation. The framework integrates essential usability and safety features, including real-time RViz visualization, streamlined gripper control, and a pause-and-reset function for smooth transitions. We detail a modular architecture that supports "Side-by-Side" and "Mirror" control modes to optimize operator experience across diverse platforms. Code is available at: https://github.com/Taokt/Quest2ROS2.

Quest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation

TL;DR

Quest2ROS2 addresses the challenge of scalable bi-manual VR teleoperation for data collection in robotics. It extends Quest2ROS into a ROS 2 middleware with relative-motion-based end-effector control, visualization, and dual-arm support to enhance ergonomics and task feasibility. Key contributions include the relative-motion control scheme that decouples end-effector motion from the initial controller pose, RViz-based target pose visualization, and dual-arm modes (Side-by-Side and Mirror) with straightforward gripper and pose-stream controls. The framework is modular via a BaseArmController and includes debugging tools and safety guidelines, all released as open-source to facilitate adoption and replication in robotics research.

Abstract

Quest2ROS2 is an open-source ROS2 framework for bi-manual teleoperation designed to scale robot data collection. Extending Quest2ROS, it overcomes workspace limitations via relative motion-based control, calculating robot movement from VR controller pose changes to enable intuitive, pose-independent operation. The framework integrates essential usability and safety features, including real-time RViz visualization, streamlined gripper control, and a pause-and-reset function for smooth transitions. We detail a modular architecture that supports "Side-by-Side" and "Mirror" control modes to optimize operator experience across diverse platforms. Code is available at: https://github.com/Taokt/Quest2ROS2.
Paper Structure (9 sections, 3 figures)

This paper contains 9 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Quest2ROS2
  3. Relative-motion-based End-Effector control
  4. Visualization in Simulation
  5. Button Functionality
  6. Usage Note
  7. Features
  8. Safety Guidelines
  9. Future Work

Figures (3)

  • Figure 1: Example implementation of Quest2ROS2 framework on a bi-manual Kuka iiwa7 system. Top Left: Potential pose of the operator while teleoperating, the controllers can be grasped in any arbitrary pose. Top Right: Visualization of the commands being streamed from the controllers to the robot. Bottom: The block-stacking task being performed via teleoperation by the operator using the system.
  • Figure 2: Conceptual demonstration of relative motion based control. Under this control logic, Movement 1 and Movement 2 produce equivalent effects on the End-Effector (EE), causing the EE to translate the same distance in the same direction, and Movement 3 will push the EE to move twice the distance in the same direction.
  • Figure 3: Demonstration of Control Methods Affected by Orientation and Position. The circle represents the operator, the square represents the robot, and the arrows indicate their respective orientations (facing directions). The colors on the controllers and robotic arms identify the one-to-one correspondence between them. In the "Side-by-Side" stance, the chirality (handedness) of the operator and the robotic arms is consistent, whereas in the "Mirror" scenario, the chirality between the controller and the robotic arm is symmetrical.