Reinforcement learning control for autonomous systems
Funded EU and UK students only. Covers home fees and normal EPSRC stipend (currently £14553/year). All students may apply for this research project, but the full funding is guaranteed for UK and EU students.
Funding sourceUniversity of Surrey
The PhD research activity is related to the development of reinforcement learning control for autonomous systems. The successful candidate will contribute to research strands as part of the recently funded national FAIR-SPACE Hub, which has the vision to establish an international centre of excellence in space robotics and autonomous systems.
The Hub is led by the University of Surrey and supported by five university partners (Imperial, Edinburgh, Liverpool, Warwick and Salford) and 28 national and international project partners representing major space companies, agencies, research institutions as well as cross-sectorial RAI organisations.
The Hub offers the world-class credentials and a unique combination of expertise and capabilities to address key challenges of RAI in the space sector. It will also influence, engage with the wider community of academia, industry, government and the public, and help cultivate and develop future leaders in RAI.
The success of the research programme requires multidisciplinary collaborations, therefore, good communication, presentation and project management skills are essential.
Applicants have to satisfy the standard university eligibility criteria and should have a masters degree (equivalent of first-class distinction). We are looking for candidates with a background in mechatronics, robotics, AI/machine learning or a closely related discipline. Experience with Python, C++, and dSPACE would also be beneficial.
How to apply
Applications can be made through our Automotive Engineering PhD programme page. In your application you must mention this studentship in order to be considered.
Applicants are required to send a cover letter explaining your interest in the project and your relevant qualifications, a CV, and the names and contact details of two references.
Shortlisted applicants will be contacted directly to arrange a suitable time for an interview. The position will remain open until a suitable candidate is found.