Autonomous Systems in the Internet of Vehicles
by Balamurugan Balusamy, Sandeep Kumar Mathivanan, Prabhu Jayagopal, S. K. B. Sangeetha, Ali Kashif Bashir
9Fusion-Enhanced Adaptive Learning for Robust Multisensor Integration in Autonomous IoV
A. Radha Krishna1, U.V. Ramesh2, S. Sathish Kumar3* and Aimin Li4
1Department of Computer Science and Engineering in Artificial Intelligence & Machine Learning, Pragati Engineering College, Surampalem, India
2Department of Computer Science and Engineering, Aditya University, Surampalem, India
3Department of Artificial Intelligence and Machine Learning, JB Institute of Engineering & Technology, Hyderabad, India
4School of Computer Science and Engineering, Xi’an University of Technology, Xian, China
Abstract
Multisensor fusion is indispensable for autonomous machines in the Internet of Vehicles (IoV) to enhance perception, localization, and decision-making. Current fusions are less adaptive in dynamic scenarios owing to static sensor weighting, heavy computational load, sensitivity to sensor failure, and limited spatiotemporal awareness. A fusion-enhanced adaptive learning (FEAL) approach is proposed in this study that combines LiDAR, radar, cameras, GPS, inertial measurement units, and vehicle-to-everything communication to mitigate these limitations. The self-evolving sensor weighting algorithm implemented in FEAL adjusts sensor importance dynamically with respect to current traffic conditions, environmental conditions, and sensor credibility. Additionally, a multiscale spatiotemporal fusion network enhances perception and decision-making by enhancing feature representation between sensor ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access