seminars
Detail
Publication date: 1 de June, 2021Artificial General Intelligence and Cognitive Robotics
Cognitive robotics is concerned with endowing robots with high-level cognitive functions such as reasoning and planning. Artificial General Intelligence aims at AI systems that can understand general problem descriptions and use their reasoning faculties to solve these problems without human intervention. In this talk I will present and discuss a formal language for describing to a general problem-solving AI system so-called epistemic games. These are characterised by rules that depend what players can and cannot deduce from the information they get during gameplay. I will also present a framework for designing robot architectures that hierarchically integrate symbolic and sub-symbolic reasoning. I will illustrate an instantiation of this framework on a general problem-solving Baxter robot.
| Date | 21/09/2016 |
|---|---|
| State | Concluded |
| Host Bio | Michael Thielscher is a professor of computer science at UNSW Australia, where he also holds the position of an associate director of the iCinema Research Centre, and he is an adjunct professor at the University of Western Sydney. Michael Thielscher received his postgraduate diploma, Ph.D. and Higher Doctorate (Habilitation) in computer science from Darmstadt University. He then joined Dresden University, where he was an associate professor before he moved to his present position. His Habilitation thesis was honoured with the Award for Research Excellence by the alumni of Darmstadt University, and in 2009 he won a Future Fellowship Award from the Australian Research Council. His current research is mainly in Knowledge Representation, Cognitive Robotics, and General Game Playing. He is author of over 150 refereed papers and four books, including a new textbook on General Game Playing, and he has co-authored the award-winning system FLUXPLAYER, which in 2006 was crowned the World Champion at the AAAI General Game Playing Competition. |