Decision making in autonomous systems is crucial for safe operation of it. Humans are highly adept at making decisions especially in situations which they have not experience before, or for which outcomes are highly unpredictable. The intuition of humans is built up of multiple levels of abstraction of massive amounts of heterogenous personal and social experiences. The project will investigate a new paradigm in AI, named Intuitive learning, which will try to develop models of intuitive decision making. We will build on the foundations on deep learning, one-short learning and meta-learning paradigms to develop intuition algorithms. The application of algorithms will be demonstrated for localization and navigation of robots (Using our in-house built UK's first autonomous quadbike) and multi-agent simulation of accident avoidance. Investigations will start by developing deep learning models for visual understanding of robot sensor data, which is a foundation of robot navigation. The PTV group has kindly offered to support the student with providing free access to their simulation platform VSSIM. The project perfectly aligns with two grand challenges of Industrial strategy : "to put the UK at the forefront of the artificial intelligence and data revolution"1,pg.36, and to "become world leader in shaping the future of mobility" 1,pg.48. This project proposes a significant advancement in AI that will have massive benefits on intelligent mobility applications.

The goal of this project is to develop a theoretical understanding of the flow through and around wave energy devices at the large and small scales, as well as to investigate the effect of biofilm growth (biofouling) on the performance of the devices. We will develop new advanced mathematical models to understand the hydrodynamics of large-scale effects of waves on floating bodies, and to link them with small-scale effects induced by surface tension and biofilm growth at low Reynolds numbers. Understanding these effects is of vital importance to quantify the design loads of the entire system and to improve its efficiency.

This research focuses upon the potential of data mining and statistical learning techniques for complex pattern recognition in automotive test data, with an additional focus upon using machine learning to augment non-linear system modelling.

This award would enable the already close relationship that has been built up between the University and the UHL NHS Trust to be further cemented by its focus on working together by the exchange of staff. It will generate cutting edge interdisciplinary research activity within specified thematic areas for the mutual benefit of both organisations.