This is a joint project with BAE Systems plc, offering access to industrially relevant datasets, equipment, and evaluation scenarios alongside academic research training. It would suit candidates interested in careers in academia or industry, especially in AI, sensing, autonomy, robotics, or embedded systems.
Background
Accurate 3D mapping is increasingly important for autonomy, navigation, inspection, and situational awareness across defence and other safety-critical applications. Yet many real-world deployments cannot depend on cloud computing or high-bandwidth communications. Instead, sensing and AI inference must operate directly at the edge, under tight constraints on power, bandwidth, and compute. This studentship addresses that challenge by developing a multimodal sensing and inference framework that can run on compact AI edge hardware while remaining reliable in complex, contested, or visually degraded environments.
Aim
You will design, build, and evaluate a hardware-aware AI framework for cognitive 3D mapping. The work will bring together three complementary sensing streams:
- structured illumination for active optical depth recovery and high-precision 3D sensing;
- event-based vision for low-latency, high-dynamic-range perception with reduced data rates;
- RF sensing and localisation, spanning radar-style observables and passive RF localisation using software-defined radio.
A central theme of the project is co-design across sensing, AI reconstruction, and embedded deployment. You will explore how multimodal models can generate consistent 3D scene representations with quantified uncertainty, and how these can be deployed efficiently on edge accelerators such as NVIDIA Jetson, Edge TPU, or neuromorphic hardware.
What We Offer
Joining our team means gaining access to exceptional resources and opportunities to develop you into a leading researcher:
- A world-class research environment spanning research environment, spanning sensing, nanotechnology, AI, and clinical medicine
- A supportive and inclusive research culture, underpinned by the Concordat.
- Close technical supervision from both academic and industrial partners to work on a real-world industry problem
- Excellent opportunities to publish in leading journals and conferences, and to present your work internationally and travel to conferences.
- Three years of funding, including tuition fees and stipend at the standard rate for eligible UK students.
- Consumables budget for purchasing state-of-the-art edge AI compute units and sensors.
- A project environment well suited to students interested in careers in academia, advanced R&D, or industry innovation.
What You Should Have
We are seeking a motivated candidate with the enthusiasm and technical foundation to contribute to ambitious interdisciplinary research. You should ideally have:
- A first-class or upper second-class degree, or a master’s degree, in Engineering, Computer Science, Physics, Mathematics, Robotics, or a related discipline.
- A strong interest in one or more of the following areas: AI and machine learning, computer vision, signal processing, sensing, robotics, or embedded systems.
- Programming experience in at least one language such as Python, MATLAB, or C/C++.
- Strong analytical, quantitative, and problem-solving skills.
- The ability to work effectively both independently and as part of a multidisciplinary academic–industry team.
- Eligibility for Home fee status.
Project Environment
The project will be based in the Faculty of Engineering at the University of Nottingham, with Dr Sendy Phang and Dr George Gordon as the academic supervisors. The student will benefit from a research culture that combines hands-on systems development with advanced AI methods, alongside co-supervision and strategic input from BAE Systems through industry supervisor Dr Hassan Zaidi.
How to Apply
Start date: 1 October 2026.
For informal enquiries and details on how to apply, please contact Dr Sendy Phang at sendy.phang@nottingham.ac.uk with:
- your CV,
- a cover letter outlining your research interests and motivation to do this PhD project,
- all academic transcripts,
- and any publications.
Apply
