Today's state-of-the-art imaging and sensing rely as much on computation as they do on sensor hardware. Furthermore, computational sensing and imaging is increasingly exploiting data-driven and machine learning solutions to enhance performance and develop novel hardware/software co-designed sensing systems. However, in defence scenarios it is vital that verifiable algorithmic solutions are used, which places restrictions on which machine learning approaches are admissible. Importantly, fully black box machine learning solutions should be avoided. This project will therefore focus on the development of novel algorithmic and mathematical frameworks to exploit data and machine learning for imaging and sensing within a controlled explainable and verifiable manner. There will be a specific focus on RF and electro-optic/IR sensor modalities.

This project will consider a range of algorithmic and machine learning technologies including: low rank models and/or auto-encoder type architectures to identify low dimensional data representations; physics-informed and physics aware neural networks that ensure the machine learning solutions adhere to necessary physics within the sensing problem; machine learning solutions targeted reducing computation or processing time; robustness to noise, outliers and adversarial attacks; and Bayesian and variational architectures that can provide uncertainty quantification.

This project will be jointly supervised by:

Prof Mike Davies, Mike.Davies@ed.ac.uk

Prof James Hopgood, James.Hopgood@ed.ac.uk

Smart Products Made Smarter

The PhD project forms part of a larger Prosperity Partnership Programme, Smart Products Made Smarter, a collaboration with Heriot-Watt University, University of Edinburgh and Leonardo. 

We are pleased to invite applications for a PhD studentship to work as part of a leading team of experts. This studentship will be supported by an enhanced stipend of £20,716 per year over 3.5 years.

This grant, sponsored by the EPSRC, is a collaboration between academia and Leonardo. There are currently PhD opportunities available to work on diverse topics as part of this collaborative team. The work will involve strong links with industry.

The research addresses a broad range of challenges. These challenges exemplify future product lifecycle management from smart concept, design, development and manufacture to enhanced end-user capability, united by a common digital thread to enable smarter products to be made smarter. Each challenge area has clearly identified initial research themes and associated research challenges to be addressed and these are indicated below:

Challenge 1 (C1) the Making challenge: To create new hybrid manufacturing processes, that combine multiple Additive Manufacturing (AM) process with precision machining and coating processes to create components that disrupt the traditional functional trade-offs of Size, Weight and Power (SWaP) through techniques such as varying the material properties within a part and harnessing the digital production of optical components.

Challenge 2 (C2) the Manipulation challenge: To create new handling processes that fully exploit the digital data flows which define custom components whose shape and functionality is tailored to production by dexterous, highly adaptable robots that are programmed dynamically.

Challenge 3 (C3) the Computation challenge: To create new signal processing & machine learning methodologies that enable intelligent, digital & connected sensor products while mitigating the data deluge from the multiple sensors produced by Leonardo operating across the EM spectrum.

The themes represent areas that could form the basis of your PhD. These PhD positions offer great flexibility and we welcome the opportunity to explore other ideas & themes.

Please note that this advert will close as soon as a suitable candidate is found.