Barcelona Media Seminars: Hector Geffner presents the research about action selection in intelligent systems

Jun 17, 2008 - BM news

Hector Geffner has presented the research line of the Artificial Intelligent Group (AI-UPF) about the action selection in intelligent systems, in the Seminar session of 17th June organized by Barcelona Media. Geffner is professor of the Department of Informations and Communication Technologies at Pompeu Fabra University (UPF), head of AI-UPF Group and researcher at the Institució Catalana de Recerca i Estudis Avançats (ICREA).

The AI-UPF group, currently integrated by four doctors and five doctorate candidates, researches the autonomous behaviour of the systems or agents, so that they can act and make decisions by themselves. Professor Geffner explained that there are three types of approaches to solve what is called the "control problem", that is, how to make the system recognise the next step: based on the programming, the learning and / or the model.

Some applications

Professor Geffner mentioned possible applications of the research that the AI-UFP group carries out: robotics, videogames design, web services composition, aerospace, manufacturing processes, logistics...

Hector Geffner obtained his PhD at the University of California in Los Angeles (UCLA) and his dissertation was co-winner of the Association for Computing Machinery (ACM) prize. He worked as researcher at the IBM Thomas J. Watson Research Center, in New York, and at the Universitat Simón Bolívar, in Caracas.

Geffner is author of Default Reasoning: Causal and Conditional Theories published by MIT Press, in 1992, and associated editor of Journal of Artificial Intelligence Research. His research has been concentrated on reasoning, action, planning and learning models.