loading page

A novel approach to compensate delay in communication by predicting teleoperator behaviour using deep learning and reinforcement learning to control telepresence robot
  • +1
  • Fawad Naseer,
  • Muhammad Nasir Khan,
  • Akhtar Rasool,
  • Nafees Ayub
Fawad Naseer
The University of Lahore

Corresponding Author:fawadn.84@gmail.com

Author Profile
Muhammad Nasir Khan
The University of Lahore
Author Profile
Akhtar Rasool
Beijing Institute of Technology
Author Profile
Nafees Ayub
Government College University Faisalabad
Author Profile

Abstract

Robots with telepresence capabilities are typically employed for tasks where human presence is not feasible due to geography, safety risks like fire or radiation exposure, or other factors like any epidemic disease. Time delay is a significant consideration in controlling a telepresence robot. This study proposes a deep learning-based approach to compensate for the delay by predicting the behaviour of the teleoperator. We integrate a recurrent neural network (RNN) based on the Long Short-Term Memory (LSTM) architecture with the reinforcement learning-based Deep Deterministic Policy Gradient (DDPG) algorithm. The proposed method predicts the teleoperator’s angular and linear controlling commands by using data gathered by embedded sensors on the specially designed and built telepresence robot. Simulations and experiments assess the operation of the proposed technique in Gazebo simulation and MATLAB with ROS integration, which shows 2.3% better response in the presence of static and dynamic obstacles.
01 Jan 2023Submitted to Electronics Letters
02 Jan 2023Submission Checks Completed
02 Jan 2023Assigned to Editor
08 Jan 2023Reviewer(s) Assigned
27 Mar 2023Review(s) Completed, Editorial Evaluation Pending
28 Mar 2023Editorial Decision: Revise Minor
12 Apr 20231st Revision Received
12 Apr 2023Submission Checks Completed
12 Apr 2023Assigned to Editor
12 Apr 2023Review(s) Completed, Editorial Evaluation Pending
15 Apr 2023Editorial Decision: Accept