PhD Studentship in Control for Autonomous Driving

About the project

About the Project Develop the next generation of reliable autonomous driving systems. Applications are invited for a fully funded PhD studentship in the field of control within the Department of Mechanical Engineering at Imperial. The studentship covers full tuition fees and provides a tax-free stipend at the UKRI rate. This opportunity is available to UK (Home) students only. Research Project Autonomous driving is one of the most exciting technological developments of our time. While remarkable progress has been made, ensuring that autonomous vehicles operate safely and reliably in complex real-world environments remains a fundamental challenge. Modern autonomous driving systems increasingly rely on machine learning to interpret camera images and make high-level driving decisions, while separate control algorithms execute these decisions through steering, braking, and acceleration. Bridging the gap between these data-driven perception and decision-making systems and model-based control is a critical open research problem. This PhD project will develop novel methods that seamlessly integrate machine learning and control, enabling autonomous vehicles to make intelligent decisions while maintaining the safety, robustness, and performance guarantees provided by modern control theory. As a PhD researcher, you will: Design and develop novel control algorithms for autonomous vehicles. Investigate new interfaces between machine learning-based decision-making and model-based control. Perform rigorous theoretical analysis of the proposed methods. Validate your algorithms in realistic open-source autonomous driving simulation environments. Contribute to cutting-edge research at the intersection of control, machine learning, and robotics. This project offers an excellent opportunity to develop expertise in one of the fastest-growing areas of engineering while contributing to technologies with significant societal impact. Candidate Profile We are looking for a motivated, curious, and enthusiastic researcher who enjoys tackling challenging problems and developing mathematically rigorous solutions with practical impact. Applicants should satisfy the academic requirements for admission to a PhD programme at Imperial College London and normally hold (or expect to obtain) a First Class or 2:1 Honours degree in Mechanical Engineering, Computing, Electrical Engineering, Mathematics, or a closely related discipline. You should have strong expertise in at least one of the following areas: Machine learning, particularly computer vision Control systems, especially model predictive control Autonomous driving or autonomous robotic systems You should also have: Strong programming skills (e.g. Python and/or MATLAB) A genuine interest in autonomous vehicles and intelligent systems Excellent analytical, communication, and teamwork skills Research Environment The successful candidate will join the Autonomous Systems Group in the Department of Mechanical Engineering at Imperial College London, working in a collaborative research environment at the intersection of control, robotics, and machine learning. The project offers opportunities to engage with leading researchers and contribute to internationally recognised research. Further information about the research group is available at: https://www.imperial.ac.uk/autonomous-systems How to Apply Information about the PhD application process is available at: http://www.imperial.ac.uk/mechanical-engineering/study/phd/how-to-apply/ Interested applicants should send: an up-to-date CV, a brief motivation letter explaining their interest in the project, and the contact details of one referee to Dr Johannes Kohler at j.kohler@imperial.ac.uk . Shortlisted candidates will subsequently be invited to complete the formal online PhD application through Imperial College London. Application Deadline Applications are reviewed on a rolling basis until the position is filled. The preferred start date is between September 2026 and February 2027 , with some flexibility by mutual agreement.

Research areas