Personal Assistive Robots

Professor Yiannis Demiris

[Abstract]

Assistive Robots have great potential in empowering humans with increased capabilities in diverse applications including assisting people with disabilities with activities of daily living. In order for robot assistance to be most effective, it should be personalised to each individual. Artificial Intelligence and Machine learning have shown great potential for personalisation through the acquisition of physiological, behavioural and performance data through computer vision and wearable sensors. In this talk, I will describe our computational architectures for biologically-inspired human action understanding and user modelling through generative ensembles of machine learning algorithms working at multiple levels of abstraction. I will describe a range of applications demonstrating the use of data-driven personalisation in fields such as robotic wheelchairs for children, assisted dressing, robot-assisted education and human-vehicle interaction.

[Biography]

Yiannis Demiris, PhD, is a Professor in Human-Centered Robotics at the Department of Electrical and Electronic Engineering at Imperial College London, where he holds the Royal Academy of Engineering Chair in Emerging Technologies. He is the Director of the Personal Robotics Laboratory, and Head of the Intelligent Systems and Networks Group. He received the B.Sc. and Ph.D. degrees from the Department of Artificial Intelligence, University of Edinburgh, U.K. His current research interests include human robot interaction, computer vision, machine learning, user modelling and personalisation, assistive and healthcare robotics; he has published more than 150 journal and peer reviewed conference papers on these topics. He was a recipient of the Rector’s Award for Teaching Excellence in 2012 and the Faculty of Engineering Award for Excellence in Engineering Education in 2012. He is a Fellow of the Institution of Engineering and Technology (IET), a Fellow of the British Computer Society (BCS) and the Royal Statistical Society (RSS).