Latest breakthroughs, research results, and challenges in intelligent control of autonomous vehicles
- 2 May 2025
- journal article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
- Vol. 240 (4) , 1564-1591
Abstract
Major companies like Google, Tesla, and Uber have invested heavily in autonomous technology, testing them in countries like the US, China, and Germany. Autonomous vehicle (AV) technology has advanced significantly, with deep learning algorithms, high-definition mapping systems, and vehicle-to-everything (V2X) communication. Sensor technology like lidar, radar, and cameras has also been developed for safe navigation. Recent advancements in intelligent control technology have improved performance and capabilities, with artificial intelligence (AI) and machine learning (ML) playing a crucial role in developing intelligent control systems. Researchers are developing algorithms for safe navigation, sensor fusion techniques, predictive modeling, and advanced planning algorithms to enhance navigation, lane changes, and intersection handling. Safety in AV control requires rigorous testing, cybersecurity, redundancy, and failsafe mechanisms. This review synthesizes a wide range of methodologies, such as statistical analysis, simulation-based approaches, deep learning models, reinforcement learning algorithms, and genetic algorithms, that have been used throughout many studies on Autonomous Vehicles (AVs). These techniques have greatly improved the performance of AVs, especially in terms of maximizing mixed traffic flow, strengthening sensor integration, and honing decision-making in challenging situations. Research findings show significant advancements; for instance, deep learning improves vehicle control and pedestrian recognition in difficult situations, while simulation-based models emphasize the benefits of autonomous vehicles on traffic efficiency. The optimization of AV routing and traffic management has been demonstrated by the successful combination of genetic algorithms and reinforcement learning. Despite these developments, a number of significant challenges still need to be overcome, including the requirement for flexible and scalable infrastructure as well as policy frameworks, sensor susceptibilities to inclement weather, and security and privacy concerns. The necessity for more reliable fixes for these vulnerabilities and the incorporation of AVs into the current transportation infrastructure are too prominent research needs. Numerous studies also stress how important it is to have sophisticated governance frameworks in place to handle the moral, legal, and security issues related to the use of AVs. The review identifies that AV research predominantly focuses on improving communication technologies, AI-enabled decision-making, and sensor integration. Future research directions should explore AV interactions with urban infrastructure, develop equitable policy adaptations, and implement advanced safety measures in the absence of connectivity. Overall, this review provides comprehensive insights into the current state, challenges, and future potential of AV technologies, guiding researchers and policymakers in addressing critical gaps to accelerate the global development and adoption of AV systems.Keywords
This publication has 157 references indexed in Scilit:
- Advances, Opportunities and Challenges in AI-enabled Technologies for Autonomous and Connected Vehicles2022
- Machine Learning: An Introduction to Reinforcement Learning2022
- Role of AI and IoT Techniques in Autonomous Transport Vehicles2022
- Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications2022
- Deep Learning for Unmanned Autonomous Vehicles: A Comprehensive Review2021
- Grounding the case for a European approach to the regulation of automated driving: the technology-selection effect of liability rulesEuropean Journal of Law and Economics, 2020
- Self-driving Cars: An Overview of Various Autonomous Driving Systems2020
- Large-Scale Machine Learning with Stochastic Gradient Descent2010
- Optimal State Estimation2006
- A note on two problems in connexion with graphsNumerische Mathematik, 1959