The Role of Artificial Intelligence in Shaping Intelligent Motorways: Opportunities, Challenges, and Real-World Implementations

The incorporation of Artificial Intelligence (AI) into transportation infrastructure has drastically reshaped the conception and functioning of motorways worldwide. This paper conducts an in-depth examination of the role and impact of AI-based technologies in intelligent motorways, detailing their mechanisms, data utilisation, and the advantages and disadvantages stemming from their implementation. This review highlights prevalent AI technologies, including Automated Incident Detection Systems (AIDs), Automated Number Plate Recognition (ANPR), and Traffic Prediction and Management Systems, elucidating the unique AI algorithms that drive these systems and the distinct data types they harness. The paper also underscores real-world examples of these technologies in operation, offering practical insights into their application. It also explores the potential issues surrounding AI integration, focusing on adversarial machine learning attacks and concept drift that pose significant challenges to the robustness and security of AI systems in transportation. Subsequently, the overarching aim of this paper is to facilitate a comprehensive understanding of the current state of AI implementation in motorways and to stimulate further research and dialogue on the rapidly evolving intersection of AI and transportation. As such, this comprehensive review serves as a valuable resource for policymakers, industry practitioners, and researchers, fostering a well-rounded understanding of AI’s transformative role in modern motorways while highlighting areas that demand further exploration. The integration of AI into transportation infrastructure has significantly reshaped the operation of motorways worldwide. This paper provides a comprehensive review of AI applications in intelligent motorways, focusing on technologies such as Automated Incident Detection Systems (AIDs), Traffic Prediction Models, and Digital Twins. It examines real-world implementations and highlights challenges, including adversarial attacks, concept drift, and data privacy concerns. To address these challenges, we propose a structured evaluation framework emphasising explainability, robustness, and fairness. By identifying key research and policy gaps—spanning ethics, transparency, and public trust—the paper outlines actionable insights and future research priorities. Case studies offer practical examples, making this work a valuable resource for policymakers, industry practitioners, and researchers aiming to advance the safe and effective deployment of AI in transportation systems.