PhD Studentship: Safe and Robust Reinforcement Learning for Embodied Intelligence with Control-[...] in Nottingham

This exciting opportunity is based within the Mechanical and Aerospace Systems (MAS) Research Group at the Faculty of Engineering, which conducts cutting-edge research into robotics, control, and autonomous systems with applications spanning aerospace, nuclear engineering, and embodied intelligence.

We are seeking a PhD student who is highly motivated to work at the interface of reinforcement learning, control theory, and embodied autonomous systems. The successful candidate will contribute to the development of learning-based control methods that are not only high-performing, but also safe, robust, and trustworthy when deployed in real-world, safety-critical environments. Together, we will advance the foundations of intelligent autonomous systems by combining modern reinforcement learning with rigorous control-theoretic principles, enabling reliable decision-making and control in complex, uncertain, and dynamic settings.

Learning-enabled autonomous systems are increasingly used in applications such as unmanned aerial vehicles, robotic manipulators, and nuclear inspection and decommissioning. While reinforcement learning has demonstrated impressive performance in simulation, many existing methods lack robustness guarantees and can behave unpredictably when faced with model mismatch, uncertainty, or distribution shift. This project is motivated by the need for deployable autonomy: learning-based systems that can operate safely over long horizons, respect physical constraints, and provide predictable closed-loop behaviour. By grounding reinforcement learning in stability theory, robust and optimal control, and physics-informed modelling, this research aims to bridge the gap between data-driven learning and dependable real-world autonomy.

Aim:

• Develop novel safe and robust reinforcement learning methods with strong control-theoretic foundations.
• Investigate stability, robustness, and safety guarantees for learning-based control systems.
• Apply and validate your methods on embodied platforms, such as UAVs, robotic systems, or simulated nuclear robotics scenarios.
• Publish high-quality research in leading international journals and conferences in control, robotics, and machine learning.

The project will be supervised by Dr Anthony Siming Chen (EEE), with co-supervision from Professor David Branson III (M3) and Professor Praminda Caleb-Solly (Computer Science). The supervisory team provides complementary expertise spanning control theory, reinforcement learning, robotics, and real-world autonomous systems.

Who We Are Looking For:

We are looking for an enthusiastic, self-motivated, and resourceful candidate who is keen to pursue research at the intersection of theory and practice.

Essential requirements:

• A first-class or high 2:1 degree in a relevant subject (e.g. robotics, computer science, electrical/electronic engineering, mechanical engineering, aerospace engineering, applied mathematics).
• Strong interest in control theory, reinforcement learning, robotics, or autonomous systems.
• Programming experience (e.g. Python, MATLAB, C/C++).

Desirable (but not required):

• Background in control theory, dynamical systems, optimisation, or machine learning.
• Experience with robotics, ROS, simulation environments, or learning-based control.

Funding support:

After a suitable candidate is found, funding is then sought from the University of Nottingham as part of a competitive process (this will cover home tuition fees and UKRI stipend).

Application:

If you are interested in applying please contact Anthony Siming Chen at a.chen@nottingham.ac.uk.

Equality, diversity and inclusion:

The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.

Additional information:

The Faculty of Engineering provides a thriving working environment for all PGRs creating a strong sense of community across research disciplines. Community and research culture is important to our PGRs and the FoE support this by working closely with our Postgraduate Research Society (PGES) and our PGR Research Group Reps to enhance the research environment for PGRs. PGRs benefit from training through the Researcher Academy’s Training Programme, those based within the Faculty of Engineering have access to bespoke courses developed for Engineering PGRs, including sessions on paper writing, networking and career development after the PhD. The Faculty has outstanding facilities and works in partnership with leading industrial partners.