A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU

TL;DR

This paper introduces a multimodal mobile teleoperation system combining vision-based hand pose estimation and IMU-based arm tracking, enabling stable and efficient control of a robot hand-arm system in complex tasks.

Contribution

The paper presents a novel vision-based hand pose regression network and an IMU-based arm tracking method for mobile robot teleoperation, enhancing mobility and control accuracy.

Findings

Efficient and stable hand-arm control demonstrated on complex manipulation tasks.

The system enables real-time, mobile teleoperation with high accuracy.

The proposed network improves hand pose estimation accuracy.

Abstract

In this paper, we present a multimodal mobile teleoperation system that consists of a novel vision-based hand pose regression network (Transteleop) and an IMU-based arm tracking method. Transteleop observes the human hand through a low-cost depth camera and generates not only joint angles but also depth images of paired robot hand poses through an image-to-image translation process. A keypoint-based reconstruction loss explores the resemblance in appearance and anatomy between human and robotic hands and enriches the local features of reconstructed images. A wearable camera holder enables simultaneous hand-arm control and facilitates the mobility of the whole teleoperation system. Network evaluation results on a test dataset and a variety of complex manipulation tasks that go beyond simple pick-and-place operations show the efficiency and stability of our multimodal teleoperation system.