Single RGB-D Camera Teleoperation for General Robotic Manipulation

TL;DR

This paper introduces a versatile teleoperation system using a single RGB-D camera capable of performing various manipulation tasks, aiming to lower entry barriers and facilitate data collection for machine learning in robotics.

Contribution

The system employs innovative techniques like non-Cartesian coordinate frames and dynamic motion scaling to enhance flexibility and generality in robotic teleoperation.

Findings

Successfully performs diverse manipulation tasks including cloth folding and peg insertion.

Increases teleoperation flexibility through coordinate frame and motion scaling innovations.

Enables data collection to support machine learning in robotic manipulation.

Abstract

We propose a teleoperation system that uses a single RGB-D camera as the human motion capture device. Our system can perform general manipulation tasks such as cloth folding, hammering and 3mm clearance peg in hole. We propose the use of non-Cartesian oblique coordinate frame, dynamic motion scaling and reposition of operator frames to increase the flexibility of our teleoperation system. We hypothesize that lowering the barrier of entry to teleoperation will allow for wider deployment of supervised autonomy system, which will in turn generates realistic datasets that unlock the potential of machine learning for robotic manipulation. Demo of our systems are available online https://sites.google.com/view/manipulation-teleop-with-rgbd