Safe Bimanual Teleoperation with Language-Guided Collision Avoidance

TL;DR

This paper presents a VR-based bimanual teleoperation system that uses voice commands and visual grounding to prevent collisions in cluttered environments, enhancing safety without reducing efficiency.

Contribution

It introduces a novel integration of voice-activated collision avoidance with immersive VR teleoperation for bimanual robots in cluttered spaces.

Findings

Significantly improves safety during teleoperation

Maintains task efficiency in cluttered environments

Effective collision prevention through visual grounding

Abstract

Teleoperating precise bimanual manipulations in cluttered environments is challenging for operators, who often struggle with limited spatial perception and difficulty estimating distances between target objects, the robot's body, obstacles, and the surrounding environment. To address these challenges, local robot perception and control should assist the operator during teleoperation. In this work, we introduce a safe teleoperation system that enhances operator control by preventing collisions in cluttered environments through the combination of immersive VR control and voice-activated collision avoidance. Using HTC Vive controllers, operators directly control a bimanual mobile manipulator, while spoken commands such as "avoid the yellow tool" trigger visual grounding and segmentation to build 3D obstacle meshes. These meshes are integrated into a whole-body controller to actively prevent collisions during teleoperation. Experiments in static, cluttered scenes demonstrate that our system significantly improves operational safety without compromising task efficiency.