IJMO 2025 Vol.15(1): 1-8
DOI: 10.7763/IJMO.2025.V15.865
An Analysis of Disengagements in Autonomous Vehicles
Md L. Ali*, Nicholas Castro, and Michael Varchetto
Department of Computer Science and Physics, Rider University, NJ 08648 USA
Email: mdali@rider.edu (M.L.A.); dweib@squ.edu.om (N.C.); mdweib@qou.edu (M.V.)
*Corresponding author
Manuscript received May 11, 2024; revised December 1, 2024; accepted January 9, 2025.
Abstract—Autonomous vehicles represent one of the most interesting applications of artificial intelligence. However, the current technology still has room for improvement, as it is still in beta. There are situations in which the autonomous system must be disengaged for safety concerns. This study aims to analyze a dataset regarding disengagements in autonomous vehicles and to attempt to predict the reasons for disengagement using machine learning algorithms. First, background information will be provided regarding autonomous vehicles and disengagements. Next, related research in the field of autonomous vehicle disengagements will be discussed. An overview of the experiment will be supplied, including a review of the dataset and extracted features, preprocessing, model architecture, training procedure, and evaluation metrics used. Finally, the results of the experiment are discussed and interpreted.
Keywords—disengagements, autonomous vehicles, machine learning, prediction
[PDF]
Cite: Md L. Ali, Nicholas Castro, and Michael Varchetto, "An Analysis of Disengagements in Autonomous Vehicles," International Journal of Modeling and Optimization, vol. 15, no. 1, pp. 1-8, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
(CC BY 4.0).
