Oliver Grainge MINDS CDT, 2022

Doctoral Researcher, University of Southampton

Oliver Grainge is a doctoral researcher working on visual localisation for robots and drones, specifically helping a robot work out where it is using only a camera, in places where GPS is unavailable or unreliable.

The challenge is not simply finding the right algorithm. The most accurate systems for this task are computationally expensive, which means they cannot run in real time on the limited processors that small autonomous vehicles carry. Oliver's research develops techniques to compress these AI systems significantly, reducing their memory footprint and computational demands while preserving their ability to recognise locations reliably. His work covers quantisation, structured pruning, and compact neural network architectures, all evaluated on real-world visual place recognition benchmarks.

More recently he has been working on the quality of the data these systems are trained on, building an automated pipeline that creates high-quality training datasets from GPS-tagged images without manual labelling. Improving the data is often as effective as improving the model.

His work has been published in IEEE Robotics and Automation Letters, with papers on low-bit quantised neural networks for visual place recognition (2024), structured pruning (2025), and a ternary transformer approach for compact visual place recognition (2025).

After his PhD, Oliver plans to work as a computer vision researcher in industry. He is due to graduate in 2026.