close

Have questions, suggestions, or concerns?

Program Directors:

Mailing Address:

Siebel Scholars Foundation
1300 Seaport Blvd., Suite 400
Redwood City, CA 94063

Phone:

(650) 299-5260

2001 - Frank Dellaert

Researchers are just beginning to use robots for mapping.  But these robots must also be aware of their surroundings and kinetics in order to map environments safely and accurately.  For example, how can you ensure that your robot maps a building correctly if it doesn’t know it is about to careen down an escalator?  The prospect of solving that question, along with many others, drew Frank Dellaert to his current research efforts in Robotics and Computer Vision.  As an Associate Professor in the School of Interactive Computing, College of Computing at Georgia Tech, Frank uses Monte Carlo simulations (computer generated repeated random sampling) to improve Simultaneous Localization and Mapping (SLAM) with robots.



SLAM is a technique used by robots and other autonomous vehicles to build a map within an unknown environment while simultaneously keeping track of their location.  Robots also can use SLAM to analyze known urban environments.  Frank and his team are creating 3D images from motion and still images—the same computer vision techniques used in robotics—to create 4D models of cities in order to virtually observe and understand the impact of time upon them.  Frank believes robots are poised to become part of our daily lives and is fascinated with the implications on our future.



Originally from Belgium, Frank has degrees from the Catholic University of Leuven, Belgium, and Case Western University, in addition to his Ph.D. from Carnegie Mellon’s School of Computer Science, where he was named a Siebel Scholar.  Frank teaches about the techniques behind visual effects at Georgia Tech and spends time with his wife and two children when not doing research.