Invited Lectures

First invited lecture, Thursday 21 October 2004, 10:00 - 11:00, Auditorium

Prof. dr. Kerstin Dautenhahn: The Human in the Loop: Case Studies in Human-Robot Interaction Research



Second invited lecture, Friday 22 October 2004, 09:00 - 10:00, Auditorium

Prof. dr. Patrick Doherty: Advanced Research with Autonomous Unmanned Aerial Vehicles



  Kerstin Dautenhahn:
Professor of Artificial Intelligence
Adaptive Systems Research Group
University of Hertfordshire, UK
http://homepages.feis.herts.ac.uk/~comqkd/
Human-Robot Interaction (HRI) is a growing and increasingly popular research area at the intersection of research field such as robotics, psychology, ethology and cognitive science. Robots moving out of the laboratory and manufacturing environments face hard problems of perception, action and cognition. Application areas that heavily involve human contact are a particularly challenging domain (Fong et al., 2003; Dautenhahn, 2003). Interaction and communication of embodied physical robots with humans is multimodal, and involves deep issues of social intelligence and interaction that have traditionally been studied e.g. in psychology. The design of a robot's behaviour, appearance, and cognitive and social skills is highly challenging, and requires interdisciplinary collaborations beyond robotics and across the traditional boundaries of established disciplines. For example, it addresses deep issues into the nature of human social intelligence, as well as sensitive ethical issues in domains where robots are interacting with vulnerable people (e.g. children, elderly, people with special needs).
In my talk I will describe challenges of human-robot interaction studies as part of two projects that I am involved in: Aurora (www.aurora-project.com) and Cogniron (http://www.cogniron.org/). The Aurora project investigates the use robots in therapy and education of children with autism. While it is still a long way until robots can make a significant therapeutic contribution, I will show examples of results which show that robots are not only interesting toys for children with autism, but are able to encourage imitation and joint attention (Robins et al., 2004a,b). This work exemplifies the need to consider in great detail the psychological and behavioural profiles of robot “users”, i.e. there is no such thing as a “typical child with autism”. The second project that I will introduce concerns the involvement of my research group in Cogniron, a new FP6 Integrated project aiming at a “Cognitive Robot Companion”. I will show first results from user studies performed in summer 2004, pointing out the need for personalized robots that can account for the individual nature of its human companions (Dautenhahn, 2004). While the above mentioned two projects use available robotic platforms, the design of a robot’s appearance and behaviour, and in particular the balance between the two, is an often underestimated factor in HRI research, depending on human’s perception and interpretation of robots. In a recent study using photos of a whole range of different robot designs we investigated children’s perception of robots. Interestingly, we found a confirmation of Masahiro Mori’s “uncanny valley”, implying that trying to make robots as closely as possible resembling humans is not necessarily the best route towards believable and acceptable robot companions (Dautenhahn, 1998; Dautenhahn, 2002; Woods et al., 2004). Such psychological approaches result in design guidelines for socially acceptable robots, robots that we might eventually even like to live with?!
To learn more take a look at some Selected References

Bio:

Kerstin Dautenhahn is Professor of Artificial Intelligence in the School of Computer Science at University Hertfordshire in England where she coordinates the Adaptive Systems Research Group and directs the Robotics and Interactive Systems Laboratory. She earned a doctoral degree (Dr. rer. nat.) in 1993 at University of Bielefeld, Germany, Department of Biological Cybernetics. Dr. Dautenhahn is a former member of the AI division of the German National Research Center for Information Technology (GMD), Germany, the AI Lab at Vrije Universiteit Brussel (VUB), Belgium, and the Department of Cybernetics at University of Reading in UK. She has a background in Biology, Artificial Intelligence and Behaviour-Based Robotics. She has pioneered research in social robotics, imitation learning, and the study of robots in autism therapy. Dr. Dautenhahn is involved in several European projects on Socially Intelligent Agents and Social Robotics (Victec, Elvis, Cogniron, Robot-Cub). She has edited 10 different special journal issues and published more than 100 research articles. Dr. Dautenhahn has edited or co-edited "Human Cognition and Social Agent Technology" (John Benjamins Publishers, 2000), "Imitation in Animals and Artifacts" (MIT Press, 2002), and "Socially Intelligent Agents - Creating Relationships with Computers and Robots" (Kluwer Academic Publishers, 2002). She is Associate Editor of Adaptive Behavior and editor-in-chief of the journal "Interaction Studies Social Behaviour and Communication in Biological and Artificial Systems", published by John Benjamins Publishing Company. In April 2005 she will host the annual convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB) with the special theme "Social Intelligence and Interaction in Animals, Robots and Agents".



Patrick Doherty
Professor of Computer Science
Department of Computer and Information Science (IDA)
Linköping University, Sweden
http://www.ida.liu.se/~patdo/patdosite1/index.html
The emerging area of intelligent unmanned aerial vehicle (UAV) research has shown rapid development in recent years and offers a great number of research challenges for artificial intelligence and knowledge representation. For both military and civilian applications, there is a desire to develop more sophisticated UAV platforms where the emphasis is placed on intelligent capabilities and their integration in complex distributed software architectures. Such architectures should support the integration of deliberative, reactive and control functionalities in addition to the UAV's integration with larger network centric systems.
In my talk I will present some of the research and results from a long term basic research project with UAVs currently being pursued at Linköping University, Sweden. The talk will focus on knowledge representation techniques used in the project and the support for these techniques provided by the software architecture developed for our UAV platform, a Yamaha RMAX helicopter. Additional focus will be placed on some of the planning and execution monitoring functionality developed for our applications in the areas of traffic monitoring, surveying and photogrammetry and emergency services assistance.

Bio:

Patrick Doherty is a professor of computer science at the Department of Computer and Information Science (IDA), Linköping University, Sweden. He is the director of the Artificial Intelligence and Integrated Computer Systems Division at IDA and head of the Knowledge Processing Laboratory. He is also President of the Swedish Artificial Intelligence Society. His current research interests include formal knowledge representation and approximate reasoning, automated planning, reasoning about action and change, autonomous aerial robotics systems, and software architectures for autonomous systems.