Model Mediated Teleoperation with a Hand-Arm Exoskeleton in Long Time Delays Using Reinforcement Learning

TL;DR

This paper introduces a model mediated teleoperation system combining reinforcement learning and dynamic movement primitives to improve control under long delays, tested on a hand-arm exoskeleton with promising adaptability.

Contribution

It presents a novel integration of RL with model mediated teleoperation and DMPs, enhancing adaptability in long-delay teleoperation scenarios.

Findings

RL finds different solutions after object position changes

DMPs effectively adapt to new conditions without uncertainty

System improves transparency and responsiveness in delayed feedback environments

Abstract

Telerobotic systems must adapt to new environmental conditions and deal with high uncertainty caused by long-time delays. As one of the best alternatives to human-level intelligence, Reinforcement Learning (RL) may offer a solution to cope with these issues. This paper proposes to integrate RL with the Model Mediated Teleoperation (MMT) concept. The teleoperator interacts with a simulated virtual environment, which provides instant feedback. Whereas feedback from the real environment is delayed, feedback from the model is instantaneous, leading to high transparency. The MMT is realized in combination with an intelligent system with two layers. The first layer utilizes Dynamic Movement Primitives (DMP) which accounts for certain changes in the avatar environment. And, the second layer addresses the problems caused by uncertainty in the model using RL methods. Augmented reality was also provided to fuse the avatar device and virtual environment models for the teleoperator. Implemented on DLR's Exodex Adam hand-arm haptic exoskeleton, the results show RL methods are able to find different solutions when changes are applied to the object position after the demonstration. The results also show DMPs to be effective at adapting to new conditions where there is no uncertainty involved.