GRASP Seminar Series: Spring 2006

April 28, 12:00 p.m. (View Online)

Henrik Christensen
Royal Institute of Technology, Stockholm / Georgia Institute of Technology

"Beyond geometric mapping"

Abstract: Autonomy for mobile systems inherently requires localisation of the system to ensure that it is not getting lost. In addition localisation is also an important service for goal achievement. For operation in natural environments -- be it domestic houses or outdoors -- there is often a need to perform concurrent localisation and mapping. The problem is typically referred to as Simultaneous Localisation and Mapping (SLAM). So far most of the research in SLAM has emphasized a purely geometric approach to mapping. Such an approach is well suited for fully autonomous systems in limited environments, but when a system cooperates with a human there is a need to provide a common representation for mapping. Euclidean geometry (SE(3)) is not necessarily the best possible basis for such a representation. People typically refer to places and locations in terms of their location relatively to landmarks or relatively to local topological regions. In addition such places and locations are referred to through semantic labels -- "the kitchen", "Henrik's office", etc. Such representations might, however, not be suitable for robot localization. There is consequently a need to establish a common basis in which both objectives can be accommodated. We will refer the overall process as Human Augmented Mapping. Neither the robot, not the human operator is perfect, and there is thus a need for a dialogue between the user and the robot to resolve ambiguities.

The presentation will discuss a SLAM based representation using graphical models, associated topical information and annotated semantic information. Inference and uncertainty modelling within the representation is briefly outlined. In addition integration of a language model for description of spatial references is introduced to allow "discussion" of ambiguous situations. The system has been tested across a number of different environments and users. In addition to a model of the overall system and its architecture, empirical results are also presented for three different robots, in four environments across 10 users.

Biography: Henrik I Christensen is a Distinguished Professor of Computing at Georgia Institute of Technology and a full professor of computer science at the Royal Institute of Technology, Stockholm. He is also director of the Center for Autonomous Systems, KTH. He is during 2006 part-time at Georgia Tech and part time at the Swedish Royal Institute of Technology (KTH). He will be full-time GT from January 2007. His main research interests are in human centered robotics, sensory/data fusion and systems integration. A fundamental assumption is that all work must be evaluated. This requires a solid theoretical model, a credible scenario and thorough testing and verification. He has published more than 200 contributions in robotics, vision and artificial intelligence, incl 9 edited books. He serves/d on the most prestigious journals within robotics. At present he is serving on the editorial board of 5 journals in robotics and AI. He served as the founding chairman of the EU network of excellence in robotics - EURON (1999-2006). He is a science advisor to the European Commission and several international companies. He has earlier held positions at Oak Ridge National Laboratory (1988), Aalborg University (1991-1996), University of Pennsylvania (1996, visiting), Swedish Royal Institute of Technology (1996-2006). He received a certificate of apprenticeship in mechanical engineering (1981), and M.Sc. and Ph.D. degrees in EE from Aalborg University 1987 and 1990, respectively.


Full Seminar schedule...

GRASP Laboratory
Site maintained by graspadm@grasp.cis.upenn.edu
Last update: 14 May, 2006