PhD Studentship: Resilient Federated Learning for Autonomous Systems under Distribution Shifts University of Sheffield in United Kingdom

[Fully funded PhD studentship with an enhanced tax-free stipend of approximately £25,000 per year, subject to annual increases; open only to candidates eligible for UK home student fees.]

Applications are invited for a fully funded PhD studentship at the University of Sheffield, in the School of Electrical and Electronic Engineering, working in collaboration with the Defence Science and Technology Laboratory (Dstl).

The project is titled Resilient Federated Learning for Autonomous Systems under Distribution Shifts and focuses on improving the robustness of federated learning for autonomous systems such as drone fleets, mobile robots, and sensor networks. The research addresses real-world distribution shifts arising from differences in environment, sensor calibration, and platform configuration, with particular attention to one-to-many supervision settings where a single human operator oversees multiple agents.

The successful candidate will develop a mathematical and algorithmic framework drawing on machine learning, control, and information theory to study how heterogeneity, sensor drift, and platform differences influence model performance and supervisory workload. The project will then design robust federated learning methods and adaptive supervisory strategies, including dynamic aggregation, confidence-based thresholds, and escalation mechanisms. A comparative study across civil and defence scenarios using real and synthetic data will help identify resilience mechanisms that generalise across applications.

The student will join a research environment at a leading centre for machine learning, robotics, and autonomous systems, with opportunities to work across the interface of machine learning, control, information theory, robotics, and AI safety. Modern computing resources and, depending on project direction, access to robotic testbeds or simulators may be available.

Funding support includes an enhanced tax-free stipend of approximately £25,000 per year, subject to annual increases. Due to funding restrictions, eligibility is limited to candidates entitled to UK home student फीस (home fee status).

Applicants should have, or expect to obtain, a first-class or strong upper-second-class degree, or a Master’s degree, in a relevant field such as Control/Systems Engineering, Electrical or Electronic Engineering, Computer Science, or Applied Mathematics. A strong mathematical background and programming ability are essential, and experience in machine learning, reinforcement learning, robotics/autonomous systems, information theory, or human-machine interaction would be beneficial.

Interested candidates should contact Dr Iñaki Esnaola or Dr Morgan Jones with a brief CV to discuss the project informally. Formal applications must be submitted through the University of Sheffield application portal, together with a CV and covering letter. The application deadline is 31 July 2026.