PhD Research Studentship in Learning-based Control and Optimization

3.5-year D.Phil. studentship 

Project: Optimal Control and Machine Learning at Scale

Supervisor: Prof Luca Furieri

The project aims to establish novel paradigms by leveraging data-driven methods and machine learning (ML) to improve the safety and performance of control architectures for large-scale dynamical systems, while also making ML algorithms more transferable, dependable, and scalable through the lens of control theory. The research will have a strong mathematical foundation, focusing on new methodologies at the intersection of control theory and machine learning. It will also involve computational efforts to understand how large networks of physical systems behave when interfaced with online data-driven algorithms. Target benchmarks will include networks of power systems and autonomous vehicles. Applications will extend to federated learning and multi-agent reinforcement learning. 

The project will enable the candidate to build a unique profile by integrating theoretical and engineering aspects of automatic control and ML, providing an ideal foundation for careers in both academia and the robotics and data science industries. Candidates will collaborate with a broader team working on diverse aspects of optimization, data-driven control, and physical engineering systems. Research collaborations, both nationally and internationally, will be fostered and encouraged.

Eligibility

This international studentship is funded through the Engineering Science department and is open to Home and overseas students (full award – fees plus stipend).

Award Value

Course fees are covered at the level set for UK students (c. £10,700p.a.). The stipend (tax-free maintenance grant) is at least c. £19237 p.a. for the first year, and at least this amount for a further two and a half years. 

Candidate Requirements

Prospective candidates will be judged according to how well they meet the following criteria:

• A first class (or strong 2:1) degree in any of Engineering, Mathematics or Computer Science;
• A strong background in mathematics, control theory, machine-learning, statistics, optimization, or related quantitative fields;
• A creative and rigorous mindset, and a strong motivation to do research;
• Excellent English written and spoken communication skills.

It is desirable that candidates possess expertise in some (but not all, or even most) of the following areas:

• Control Engineering
• Applied Mathematics and Statistics
• Computer Science/AI
• Programming / Software Engineering
• Electrical Engineering or Robotics

Application Procedure

Informal enquiries are encouraged and should be addressed to Prof Luca Furieri via alice.robertson@eng.ox.ac.uk. 

Candidates must submit a graduate application form (via the ‘Apply’ button above) and are expected to meet the graduate admissions criteria. Details are available on the course page of the University website.

Please quote 25ENGCO_LF in all correspondence and in your graduate application.

Application deadline: noon on 3 December 2024.

Start date: October 2025

Advert information