S D Djahel

This PhD project at Coventry University, hosted by the Centre for Future Transport & Cities (FTC), explores the integration of drone-assisted intelligence with Connected and Autonomous Vehicles (CAVs) to enhance road safety and traffic efficiency. The research leverages recent advances in AI-driven frameworks, including transformer-based models for cooperative perception and multi-agent reinforcement learning (MARL) for decision-making and control. By combining aerial sensing from drones with ground-based vehicle perception, the project aims to develop a novel cooperative intelligence framework that improves environmental awareness and optimizes traffic environments at scale. Unlike traditional V2V or V2X approaches, this project utilizes heterogeneous data fusion from both aerial and ground sensors, enabling more robust and dynamic traffic management. The research question focuses on how cooperative AI systems can efficiently integrate these diverse data sources, multi-agent learning, and realistic drone-CAV interactions to achieve optimal traffic outcomes. The project is highly interdisciplinary, drawing on expertise in Computer Science, Mechanical Engineering, Robotics, Electrical Engineering, and Transport Geography. The successful candidate will benefit from comprehensive research training, including technical, personal, and professional development, as part of Coventry University's Doctoral and Researcher College. The studentship covers tuition fees, a stipend, one return economy airfare to GITAM/Coventry University, visa, and overseas healthcare for the mobility period. Applicants must have a minimum of a 2:1 first degree in a relevant discipline with at least 60% in the project element or equivalent, and a minimum 60% overall module average. A distinction at undergraduate and Master’s level in Computer Science or closely related disciplines is essential. Candidates should demonstrate outstanding academic performance, a strong foundation in programming, mathematics, and AI principles, and familiarity with advanced topics such as Federated Learning and Multi-Agent Deep Reinforcement Learning. English language proficiency (IELTS academic overall minimum score of 7.0 with at least 6.5 in each component) is required. Applicants must be able to rapidly master new simulation environments, analytical evaluation techniques, and experimental frameworks. To apply, submit your application with full supporting documentation, a covering letter, and a 2000-word supporting statement detailing your expertise and interests relevant to the project. For further information, contact Prof S D Djahel at [email protected]. Applications are accepted via the FindAPhD portal until May 1, 2026.