Tony Cohn holds BSc and PhD degrees from the University of Essex where he studied under Pat Hayes. He spent 10 years at the University of Warwick before moving to Leeds in 1990 where he founded a research group working on knowledge representation and reasoning with a particular focus on qualitative spatial/spatio-temporal reasoning, the best known being the well cited region connection calculus (RCC).
He is Editor-in-Chief Spatial Cognition and Computation and has been Chairman/President of the UK AI Society SSAISB, the European Association for Artificial Intelligence (EurAI), KR inc, the IJCAI Board of Trustees and was the Editor-in-Chief for Artificial Intelligence 2007-2014 and of the AAAI Press 2004-14. He remains a Director of KR Inc.
He is the recipient of the 2015 IJCAI Donald E Walker Distinguished Service Award which honours senior scientists in AI for contributions and service to the field during their careers, as well as the 2012 AAAI Distinguished Service Award for “extraordinary and sustained service to the artificial intelligence community”. He is a Fellow of the Royal Academy of Engineering, and is also a Fellow of AAAI, AISB, EurAI (Founding Fellow), the BCS, and the IET. He was a member of the UK Research Excellence Framework (REF) 2014 Sub Panel 11 (Computer Science and Informatics) of Panel B.
Theme 1: decision support systems (DSS) for urban infrastructure: One such DSS has been developed in the EPSRC funded assessing the underworld project has been gaining industrial interest. The DSS relies on a number of AI technologies, including ontologies and reasoning with rules which encode uncertain and vague knowledge; a demo of the system can be viewed at http://bit.ly/2pV7k3Z.
Theme 2: activity recognition: A particular focus is the use of high level qualitative spatio-temporal representations, rather than relying on low level visual features as in much of the other literature. Advantages of this qualitative approach are that it helps abstract away from noise, that instances of activities that are metrically different, are more alike when described qualitatively (which facilitates activity class learning), and that the resulting model can be made to be human-introspectable.
Theme 3: grounding language to vision: Recent work has been addressing how descriptions of objects, names, properties, spatial relations and actions can be learnt simultaneously, and incrementally, as well as learning the grammar of the language. The approach is developmental, inspired by acquiring concepts and grounding as a young child might.
Theme 4: qualitative spatial reasoning for the humanities
Tony is involved in a new AHRC network investigating the application of qualitative spatial representations in the digital humanities as an alternative to GIS. The aim is to help find patterns in the information, through techniques including visualisation of the data. These patterns can generate new questions or new perspectives on the world from which the data came.