About the project
AI and machine learning are increasingly used in cars, aircraft, robots, and other critical systems, but their performance, correctness, energy consumption, and safety are intertwined in ways that are hard to predict. We seek to untie this knot so we can build intelligent systems that are more trustworthy and resource-efficient.
In brief: How can modern cyber-physical systems (e.g., cars, aircraft, robots) make the right decision at the right time, without draining their batteries, while being safe to operate?
In addition, such systems increasingly rely on AI and machine learning, where computational performance, correctness, energy consumption, and safety are tightly connected. Consider the following simplified problem: A more accurate computation may require more time and energy, while a faster one may produce less reliable results. How to decide which one to use?
This challenge is already visible in space. For instance, NASA’s Perseverance rover adapts its onboard schedule to uncertain durations of science and engineering activities, which also make energy use difficult to predict. Such uncertainty can be particularly problematic if misjudged (a system can become inoperable, inefficient, unsafe, or even waste significant amount of taxpayer's money).
This project seeks to develop scheduling algorithms and analysis methods that explicitly account for uncertainty. Scheduling determines when computations run and how they share resources. Analysis assesses what these choices mean for performance, correctness, energy use, and safety. You will investigate how uncertainty in these quantities can be characterised, how their dependencies affect system behaviour, and how scheduling decisions can improve efficiency while respecting safety requirements.
The research will combine mathematical modelling, probability and statistics, algorithm design, and experimental evaluation. The aim is to provide both theoretical foundations and practical methods for intelligent systems that make better use of limited resources and offer clearer evidence of trustworthy behaviour.
You will be based and trained in the Cyber Physical Systems group in the School of Electronics and Computer Science.
You will be supported to attend international conferences and develop a wide range of technical and transferable skills.
If you feel you have gaps in some areas that might be required for the research, you will be able to attend any lectures across the wide range of courses offered within the School of Electronics and Computer Science to supplement your knowledge, for instance, AI, scheduling theory, computer science, embedded systems.
The School of Electronics and Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
