Short Title: Int. J. Mech. Eng. Robot. Res.
Frequency: Bimonthly
Professor of School of Engineering, Design and Built Environment, Western Sydney University, Australia. His research interests cover Industry 4.0, Additive Manufacturing, Advanced Engineering Materials and Structures (Metals and Composites), Multi-scale Modelling of Materials and Structures, Metal Forming and Metal Surface Treatment.
2024-10-25
2024-09-24
Abstract—In this study, the focus is on close proximity Timeto- Collision (TTC) prediction from an Autonomous Robot (AR)’s perception system, which is built with an X-band Doppler radar for relative speed estimation and infrared proximity sensors for direction and distance sensing from a moving obstacle. To compensate for the possibility of poor ranging performance, an Artificial Neural Network (ANN) approach is introduced to enhance prediction accuracy. A comparative performance analysis against conventional and Linear Regression (LR) methods was also conducted and results demonstrated that the predicted TTC with the ANN model trained with the Levenberg-Marquardt algorithm successfully reduced the average error to 0.155s, which was a considerable 50% reduction from the conventional method. Index Terms—artificial neural network, time-to-collision, doppler radar, autonomous robot Cite: Imane Arrouch, Junita Mohamad Saleh, Patrick Goh, and Nur Syazreen Ahmad, "A Comparative Study of Artificial Neural Network Approach for Autonomous Robot’s TTC Prediction," International Journal of Mechanical Engineering and Robotics Research, Vol. 11, No. 5, pp. 345-350, May 2022. DOI: 10.18178/ijmerr.11.5.345-350 Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.