Invited Speakers

Speaker-Bio: Yiannis Demiris is a Professor in Human-Centred Robotics at Imperial, where he holds a Royal Academy of Engineering Chair in Emerging Technologies (Personal Assistive Robotics). He established the Personal Robotics Laboratory at Imperial in 2001. He holds a PhD in Intelligent Robotics, and a BSc(Hons) in Artificial Intelligence and Computer Science, both from the University of Edinburgh. He has been a European Science Foundation (ESF) junior scientist Fellow, and a COE Fellow at the Agency of Industrial Science and Technology (AIST - ETL) of Japan. He is currently a Fellow of the Institute of Engineering and Technology (FIET), Fellow of the British Computer Society (FBCS) and Fellow of the Royal Statistical Society (FRSS). Prof. Demiris' research interests include Artificial Intelligence, Machine Learning, and Intelligent Robotics, particularly in intelligent perception, multi-scale user modelling, and adaptive cognitive control architectures in order to determine how intelligent robots can generate personalised assistance to humans in order to improve their physical, cognitive and social well being.

Assistive robotics, particularly those designed to interact with people over extended periods of time, can benefit from personalisation mechanisms that interactively learn models of their human users, and adapt the assistive behaviours to maximise the benefit to their users. From physical mobility assistance to educational support, personalisation mechanisms share perceptual, representational, and learning challenges in determining the nature and timing of the optimal assistance by the robot. In this talk I will outline these challenges, and present our research at the Personal Robotics Lab at Imperial on assistive robotic wheelchairs for children, educational support for children with metabolic disorders, and (paying homage to the acronym of this workshop) work on robot dance tutors for children (and children at heart). I will argue that for such application domains our robots will need to incorporate developmental considerations in their assistive policies to maximise their impact.

Speaker-Bio: Séverin Lemaignan is Associate Professor in Social Robotics and AI at the Bristol Robotics Laboratory, University of the West of England, Bristol. His research interests primarily concern the socio-cognitive aspects of human-robot interaction, both from the perspective of the human cognition and the design of cognitive architectures for the robots. More recently, he has been focusing his experimental work on child-robot interactions in educative settings, exploring how robots can support teachers and therapists to develop effective and engaging novel learning paradigms. Previously, he obtained a joint PhD in Cognitive Robotics from the CNRS/LAAS (France) and the Technical University of Munich (Germany) for which he received the ‘Best PhD in Robotics 2012’ award from French CNRS. He then conducted his research as Research Fellow at EPFL (Switzerland) and Plymouth University (UK) where he was Lecturer in Robotics until 2018. Dr Séverin Lemaignan has been involved in several European projects related to social and cognitive robotics: CHRIS (Cooperative Human Robot Interaction Systems), DREAM (Development of Robot-Enhanced therapy for children with AutisM spectrum disorders), L2TOR (Second language TutOring using social Robots). He has also been awarded in 2015 a EU H2020 Marie Skłodowska-Curie Individual Fellowship for his project DoRoThy (Donating Robots a Theory of Mind).

Participatory methodologies are now well established in social robotics to generate blueprints of what robots should do to assist humans. The actual implementation of these blueprints, however, remains a technical challenge for us, roboticists, and the end-users are not usually involved at that stage.

In two recent studies, we have however shown that, under the right conditions, robots can directly learn their behaviours from domain experts, replacing the traditional heuristic-based robot controllers by autonomously learnt social policies. We have derived from these studies a novel 'end-to-end' participatory methodology called LEADOR, that I will introduce during the workshop.

I will also discuss the next steps for such an approach to be successfully applied to more difficult assistive scenarios, like long-term deployments in schools for autistic children.

Speaker-Bio : Alessandro Di Nuovo is Professor of Machine Intelligence at Sheffield Hallam University. He received the Laurea (MSc Eng) and the PhD in Informatics Engineering from the University of Catania, Italy, in 2005 and 2009, respectively.

At Present, Prof. Di Nuovo is the leader of Technological and Digital Innovation for promoting independent lives at the Advanced Wellbeing Research Centre. He is also the leader of the Smart Interactive Technologies research laboratory of the Department of Computing. He is a member of the Executive Group of Sheffield Robotics, an internationally recognised initiative of two Sheffield Universities to support innovative and responsible research in robotics.

Prof. Di Nuovo has an extensive track record of externally funded interdisciplinary research and innovation in fundamental and applied topics in AI and Robotics.

Prof. Di Nuovo is a lead scientist of the H2020 MSCA-ITN European Training Network on PErsonalized Robotics as SErvice Oriented applications (PERSEO, 2021-2024), a multidisciplinary project to train a cohort of outstanding doctoral candidates to be the new generation of interdisciplinary researchers and professionals for the forthcoming market of personal robots. Prof. Di Nuovo is also a co-investigator of the EPSRC NetworkPlus EMERGENCE (2021-23) that aims at facilitating the Emergence of Healthcare Robots from Labs into Service for tackling frailty in older people.

Prof. Di Nuovo was the leading investigator of the EPSRC project NUMBERS (2017-20), which delivered the first step toward his vision by creating a developmental neurorobotics model of number understanding. The research evidenced similarities between children and robotic behaviours in the early development of numerical cognition, demonstrating an improvement of the machine learning thanks of the embodiment. Prof. Di Nuovo coordinated the H2020 MSCA-IF CARER-AID (2017-19), which developed an intelligent robotic assistant to support caregivers in early diagnosis and treatment of individuals with autism spectrum disorder associated with intellectual disability, in close collaboration with a healthcare provider and research institution. Prof. Di Nuovo won the IBM SUR support for the CATHI project to create a prototype of a robot-led psychological cognitive assessment system powered by the IBM Watson Cloud AI services; he was leading the human-robot interaction work package of the FP7 Large Scale project ROBOT-ERA (2012-15), a multidisciplinary international project concerning the implementation and evaluation of several advanced robotic services for supporting the elderly.

Currently, Prof. Di Nuovo is editor-in-chief (topics AI in Robotics; Human Robot/Machine Interaction) of the International Journal of Advanced Robotic Systems (SAGE).

Improvement of interaction quality in Socially Assistive Robotics can be stimulated by novel artificial intelligence algorithms. This is one of the applications of Cognitive Robotics, which is a multi-disciplinary research area that connects robotics, cognitive science and artificial intelligence, and often applies models based on biological cognition. The effort is to exploit the principles of multimodal interaction and embodied cognition, in which the body is a crucial component of the cognitive process, for the creation of more intelligent robots with human-like abilities and interaction performance. Indeed, cognitive robots capable of social interaction may provide individualised assistance to some classes of people (e.g. children with autism or elderly with cognitive decline) while exploiting the computational intelligence for data collection and processing.

The talk will present significant results of several research projects to provide an overview of the current state-of-the-art in the area of cognitive robotics, increase the awareness of benefits and limitation, and discuss the potential breakthroughs and implications for professionals in several disciplines. The talk will also emphasise responsible user-centred research to empower people rather than substitute them.

Speaker-Bio : Angelo Cangelosi currently is Professor of Machine Learning and Robotics at the University of Manchester (UK). He also is Turing Fellow at the Alan Turing Institute London, Visiting Professor (Jiangsu Talent) at Hohai University and at Universita’ Cattolica Milan, and Visiting Distinguished Fellow at AIST-AIRC Tokyo. His research interests are in developmental robotics, language grounding, human robot-interaction and trust, and robot companions for health and social care. Previously Angelo was Professor of Artificial Intelligence and Cognition, and founding director role, at the Centre for Robotics and Neural Systems at Plymouth University (UK). Cangelosi studied psychology and cognitive science at the Universities of Rome La Sapienza and at the University of Genoa, and was visiting scholar at the University of California San Diego and the University of Southampton. He currently is Principal investigator for the ongoing projects “EnTRUST (UKRI/EPSRC TAS Node on Trust, 2020-24, £1m), “THRIVE++” (US Air Force Office of Science and Research, 2018-2023, $1m) and the H2020 projects TRAINCREASE, eLADDA ETN and PERSEO ETN. He was the coordinator of the EU H2020 Marie Skłodowska-Curie European Industrial Doctorate “APRIL: Applications of Personal Robotics through Interaction and Learning” (2016-2019). Overall, he has secured over £33m of research grants as coordinator/PI. Cangelosi has produced more than 300 scientific publications, and has been general/bridging chair of numerous workshops and conferences including the IEEE ICDL-EpiRob Conferences (Frankfurt 2011, Osaka 2013, Lisbon 2017, Tokyo 2018, Beijing 2021). In 2012-13 he was Chair of the IEEE Technical Committee on Autonomous Mental Development. Cangelosi is Editor of the journals Interaction Studies and IET Cognitive Computation and Systems, and in 2015 was Editor-in-Chief of IEEE Transactions on Autonomous Development. His book “Developmental Robotics: From Babies to Robots” (MIT Press) was published in January 2015, and recently translated in Chinese and Japanese. His latest book “Cognitive Robotics” (MIT Press), coedited with Minoru Asada, will be published in 2021.

Growing theoretical and experimental research on action and language processing and on number learning and gestures clearly demonstrates the role of embodiment in cognition and language processing. In psychology and neuroscience, this evidence constitutes the basis of embodied cognition, also known as grounded cognition (Pezzulo et al. 2012). In robotics and AI, these studies have important implications for the design of linguistic capabilities in cognitive agents and robots for human-robot collaboration, and have led to the new interdisciplinary approach of Developmental Robotics, as part of the wider Cognitive Robotics field (Cangelosi & Schlesinger 2015; Cangelosi & Asada 2021). During the talk we will present examples of developmental robotics models and experimental results from iCub experiments on the embodiment biases in early word acquisition and grammar learning (Morse et al. 2015; Morse & Cangelosi 2017) and experiments on pointing gestures and finger counting for number learning (De La Cruz et al. 2014). We will then present a novel developmental robotics model, and experiments, on Theory of Mind and its use for autonomous trust behavior in robots (Vinanzi et al. 2019). The implications for the use of such embodied approaches for embodied cognition in AI and cognitive sciences, and for robot companion applications will also be discussed.

Cangelosi A., Asada M (Eds.) (2021, in press). Cognitive Robotics. Cambridge, MA: MIT Press.

Cangelosi A., Schlesinger M (2015). Developmental Robotics: From Babies to Robots. Cambridge, MA: MIT Press.

De La Cruz V., Di Nuovo A., Cangelosi A., Di Nuovo S. (2014). Making fingers and words count in a cognitive robot. Frontiers in Behavioral Neuroscience, 8, 13 10.3389/fnbeh.2014.00013

Morse A., Belpaeme T, Smith L, Cangelosi A. (2015). Posture affects how robots and infants map words to objects PLoS ONE, 10(3) 10.1371/journal.pone.0116012

Morse A, Cangelosi A (2017). Why are there developmental stages in language learning? A developmental robotics model of language development. Cognitive Science. 10.1111/cogs.12390

Pezzulo G., Barsalou L.W., Cangelosi A., Fischer M.H., McRae K., Spivey M. (2013). Computational grounded cognition: A new alliance between grounded cognition and computational modelling. Frontiers in Psychology, 6(612), 1-11. 10.3389/fpsyg.2012.00612

Vinanzi, S., Patacchiola, M., Chella, A., & Cangelosi, A. (2019). Would a robot trust you? Developmental robotics model of trust and theory of mind. Philosophical Transactions of the Royal Society B, 374(1771), 20180032. 10.1098/rstb.2018.0032