Artificial Intelligence (AI) simulates human intelligence in a machine to make the machine intelligent in solving real world problems. AI is comprised of approaches such as machine learning, data engineering and knowledge discovery, natural language processing, meta-heuristic algorithms, expert systems, fuzzy systems, intelligent data mining, etc. These approaches have been used for solving real world problems in society with great success.

Recently, the Internet of Vehicles (IoV) has emerged from the Internet of Things (IoT), where vehicles within an environment communicate with different aspects of society. The vehicles in the IoV environment are comprised of fully autonomous driving vehicles and semi-autonomous driving vehicles. These vehicles in the IoV communicate to both external and internal environments. The vehicles communicate to other vehicles, road infrastructure, sensors, personal devices, pedestrians, and homes. It is expected that each of the vehicles is to be equipped with over 200 sensors in the future. Soon, millions of the vehicles will start full operation in the IoV environment and each is forecast to generate over 25 Gb of data in every hour, thus generating the so-called big data that comes in different forms: structured, semi-structured, and unstructured that require collection, processing, storage, management, and analysis for decision making. The IoV concept is still in it is early stages, and as such, more rigorous research is needed to fully understand it. Few AI approaches have been used for solving problems in IoV and autonomous vehicles, leaving a gap to be bridged. A lot of the applications of AI approaches in IoV are limited in the literature.

Therefore, this Special Issue aims to address the fusion of AI and IoV for autonomous vehicles for practice and theory. Both original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Multitask learning for security and privacy in IoV
• Transfer and reinforcement learning for autonomous vehicles
• Deep learning for collision detection/traffic prediction in IoV
• New deep learning approaches to steering angle control in autonomous vehicles
• Convolutional neural networks for vision and environment perception in IoV
• Explainable deep learning architectures for semi-automated vehicles for IoV
• Machine learning/graph learning for autonomous vehicles
• Meta-heuristic algorithms for deep learning in Vehicle-to-Sensor communication for IoV
• Hybrid intelligent systems in IoV and autonomous vehicles
• Applications of big data in IoV and autonomous vehicles
• Natural language processing for vehicle to home communication
• Multi-criteria reinforcement learning for vehicle-to-vehicle communications
• Distributed AI systems and architectures in edge data analytics for IoV
• Multi-sensor big data fusion using neural and fuzzy systems
• Learning and adaptive sensor fusion in cooperative vehicle-infrastructure systems for IoV