Artificial Intelligence (AI) has become a key enabler of intelligent vehicular (V2X) and Unmanned Aerial Vehicle (UAV) networks. These networks face extreme mobility and rapidly changing topologies, making stable communication and decision-making very difficult. Traditional AI models such as CNN and RNN fail to adapt quickly to these dynamic conditions. This survey reviews recent AI-based approaches designed to improve reliability, latency, and energy efficiency in V2X and UAV networks. The study compares Deep Reinforcement Learning (DRL), Graph Neural Networks (GNN), and Federated Learning (FL) methods, highlighting their benefits and limitations. Future research should focus on adaptive AI architectures that can operate under continuous topology changes and mobility uncertainty.
Entesar Alasaad (Thu,) studied this question.