PhD Studentship: Assured Runtime Control for Safe Autonomy (ARCS-A) (PhD in Engineering (Funded))

Overview

The University of Exeter is offering a funded PhD studentship in engineering on Assured Runtime Control for Safe Autonomy. Modern autonomous ground vehicles used in defence operations rely on AI and machine learning for perception, decision-making and adaptive responses in complex environments where terrain can change abruptly. Certifying these opaque learning-based components formally takes impractical resources, which creates safety assurance challenges and delays adoption of new technology. Earlier independent and DSTL-funded research at the university has established foundational safety assurance techniques for autonomous systems.

This PhD will develop an assured runtime safety controller that lets autonomous systems operate safely in dynamic environments. It is developed in collaboration with SC Group Ltd., with applications to defence autonomous systems. The approach combines techniques such as onboard safety monitoring, adaptation to the operating environment and real-time robust learning of uncertainties and nonlinearities in the dynamical system.

What you will do

The aim is to learn control policies and safety certificates at the same time. Safety certificates are mathematical proofs that control decisions are safe, and data from system operation provides evidence that both the control and the proofs are valid. The resulting controller will prevent unsafe actions when AI and machine learning functions are deployed in the closed-loop control of autonomous ground vehicles.

What you get

The studentship provides UK tuition fees and an annual tax-free stipend of at least 25,000 GBP per year.

Key dates

The closing date is 23 October 2026.