Invited Speaker
Roland Siegwart
Autonomous Systems Lab, Institute of Robotics
and
Intelligent Systems, ETH Zurich
|
|
Biographical Sketch
Roland Siegwart is full professor for autonomous systems at ETH Zurich since July 2006. He has a Diploma in Mechanical Engineering (1983) and PhD in Mechatronics (1989) from ETH Zurich. In 1989/90 he spent one year as postdoctoral fellow at Stanford University. After that he worked part time as R&D director at MECOS Traxler AG and as lecturer and deputy head at the Institute of Robotics, ETH Zürich. In 1996 he was appointed as associate and later full professor for autonomous microsystems and robots at the Ecole Polytechnique Fédérale de Lausanne (EPFL). During his period at EPFL he was Deputy Head of the National Competence Center for Research (NCCR) on Multimodal Information Management (IM2), co-initiator and founding Chairman of Space Center EPFL and Vice Dean of the School of Engineering. In 2005 he hold a visiting position at NASA Ames and Stanford University.
Roland Siegwart is member of the Swiss Academy of Engineering Sciences and board member of the European Network of Robotics (EURON). He served as Vice President for Technical Activities (2004/05) and is currently Distinguished Lecturer (2006/07) of the IEEE Robotics and Automation Society. He is coordinator of two European Projects and co-founder of several spin-off companies.
 Email: rsiegwart@ethz.ch
 Website: http://www.asl.ethz.ch/
Plennary Session
Robots - Intelligent Machines are Coming Closer
cockroaches. Based on simple interaction rules and behaviors, the robots are able to significantly influence the collective decision process of the mixed society in test environment. However, these promising results can unfortunately not be simply scaled up to more complex environments and interactions. The fundamental problem lies in the fact, that collective intelligent is essentially limited by the competences and performance of the individuals of the society. Future robots able to integrate in human society and offer useful services require first of all the perception and representation capacities that can cope with complex settings. This has driven our research in the context of the COGNIRON project towards functional-based environment representations, which we consider as fundamental for higher cognitive functions. We suggest in a first step a hierarchical probabilistic representation of space that is based on objects arranged in topological object graph. In our most recent EU project BACS (Bayesian Approaches to Cognitive Systems) we try in a consortium of ten partners to further enhance and apply the Bayesian approach for solving complex cognitive tasks. Our research and future directions are strongly influenced by the long-term robot experience we made at the Swiss National Exhibition in 2002 and the more recent work on a theater robot and intelligent cars.
|
