Emerging technologies such as edge computing, AI, and distributed learning have reshaped the design of cyber-physical transportation systems. Advances in Edge AI enable low-latency learning and inference close to data sources, while Multi-Agent Deep Reinforcement Learning (MADRL) facilitates cooperation among autonomous agents in dynamic, uncertain environments. Simultaneously, the Social Internet of Things (SIoT) offers frameworks for trust, social interaction, and context awareness across connected entities. These technologies are converging in critical domains such as urban mobility, unmanned aerial vehicles (UAVs) traffic management, vehicular edge networks, and autonomous infrastructure coordination. However, key questions remain on how to balance computation between edge and cloud, ensure secure collaboration, and guarantee real-time learning performance at scale. By focusing on the intersection of AI, mobility, and edge intelligence, this Research Topic addresses both theoretical foundations and applied breakthroughs in smart transportation systems.

The increasing demand for efficient, intelligent, and sustainable transportation systems poses complex challenges in modern cities. Traditional centralized solutions are no longer sufficient to handle the growing volume of real-time data, dynamic mobility needs, and heterogeneous agent coordination. This Research Topic aims to explore the fusion of AI-driven edge intelligence and multi-agent systems to address these challenges and enable scalable, cooperative, and adaptive decision-making across smart mobility networks. By leveraging Edge AI, MADRL, and SIoT, we seek to advance the next generation of autonomous transportation technologies, including UAVs, connected vehicles, and smart traffic systems. Our goal is to create a forum for the most recent developments and practical applications that harness distributed intelligence, real-time task offloading, and cooperative behaviors for intelligent traffic control, autonomous fleet coordination, and sustainable mobility solutions. We invite contributions that push the boundaries of research and practice in this rapidly evolving domain.

We welcome original research articles, reviews, system designs, and case studies that explore the synergy between Edge AI, multi-agent learning, and intelligent transportation. Topics of interest include, but are not limited to:

- Task offloading and edge-cloud orchestration in UAV/vehicular networks.

- Multi-agent reinforcement learning for mobility optimization.

- Federated and privacy-preserving learning for smart transportation.

- SIoT-based cooperation and trust in autonomous systems.

- Swarm intelligence and UAV fleet coordination.

-Context-aware and human-in-the-loop mobility systems

- Energy-efficient and sustainable edge-based mobility.

- AI-based traffic signal control and route planning.

- Simulation environments for cooperative transportation AI.

- Urban air mobility and AI-powered aerial-ground integration.

All submissions should emphasize innovation, scalability, and applicability to real-world transportation challenges. Authors are encouraged to highlight cross-disciplinary approaches, benchmark datasets, and open-source tools where applicable.

Are you interested in contributing a manuscript to this Research Topic?

AI-Driven Edge Intelligence and Multi-Agent Systems for Smart Mobility and Autonomous Transportation