News & Events

14.11.2014

Using Semantic Knowledge to deal with Contradictions in Robotics


Alessandro Saffiotti

AASS Cognitive Robotics Laboratory
Orebro University, Sweden

 

 

We the humans know the semantics of the environment where we live. We know the function of objects and places around us, we know which objects belong to which place, and so on.  We use this knowledge when we plan our activities, and when something in our plans go wrong. Robots should do the same.  However, it is only recently that researchers in autonomous robotics have started to endow robots with semantic knowledge, and with the ability to reason from this knowledge.  In this talk, I will outline the efforts in this direction performed at the AASS Cognitive Robotic Systems Lab of Orebro University, Sweden.  Our effort are based on a specific type of semantic maps, which integrates hierarchical spatial information and semantic knowledge, and leverage this knowledge to facilitate taskplanning and reasoning about exceptions.  I will focus in particular on the second issue: how can semantic knowledge allow a robot to recognize when things are NOT as they should be, and provide indications to correct these deviations.  I will discuss in particular the generation of goals from semantic knowledge. For instance, if a robot has semantic knowledge that perishable items must be kept in a refrigerator, and it observes a bottle of milk on a table, this robot will generate the goal to bring that bottle into a refrigerator.This work was done in cooperation with Cipriano Galindo, from the University of Malaga, Spain. 

 

Date: 14.11.2014

Time: 15:30 h

Location: Cartesium, Bremen

Speaker-URL`s: http://aass.oru.se/~asaffio/

Alessandro Saffiotti (MSc, PhD) is full professor of Computer Science at the University of Orebro, Sweden, where he heads the AASS Cognitive Robotic Systems laboratory.  He holds a MSc in Computer Science from the University of Pisa, Italy, and a PhD in Applied Science from the Universite Libre de Bruxelles, Belgium.  His research interests encompass artificial intelligence, autonomous robotics, and technology for elderly people.  He is the inventor of the notion of "Ecology ofphysically embedded intelligent systems", a new approach to include robotic technologies in everyday life that has been applied in several projects.  He is the initiator of a series of ongoing international initiatives on combining AI and Robotics.  He has published more than 160 papers in international journals and conferences, and organized many international events.  He is or has been P.I. in a dozen EU projects and networks.  He is a member of AAAI, a senior member of IEEE, and an ECCAI fellow.