Learning Linear Models from 2d and 3d Range Data
Speaker: Wolfram Burgard , University of Freiburg
Date: September 20 2005
Time: 11:00AM to 12:00PM
Location: 32-G449 (Patil/Kiva)
Host: Nick Roy, MIT - CSAIL - RVSN
Contact: Nick Roy, nickroy@mit.edu
Relevant URL: In this talk I will present techniques for extracting piecewise linear models from 2d and 3d range data. I will first describe an approach to learn polyline maps from two-dimensional range scans. The idea of this algorithm is to calculate the a set of polylines that best approximates the data. It uses several operators for merging, splitting, and adjusting the points of the polylines during the search for the maximum likelihood approximation. Additionally, I will present a method to learn planes from 3d range data. This approach applies a hierarchical EM to consider the co-planarity of planes during the estimation process. Finally, I will present some recent results obtained with an approach that utilizes constraints between features extracted from range scans to improve the scan-matching process.
Wolfram Burgard is an associate professor for computer science at the University of Freiburg where he heads of the Laboratory for Autonomous Intelligent Systems. He received his Ph.D.~degree in Computer Science from the University of Bonn in 1991. His areas of interest lie in artificial intelligence and mobile robots. Over the past years his research mainly focused on the development of robust and adaptive techniques for state estimation and control of autonomous mobile robots. He and his group developed several innovative probabilistic techniques for robot navigation and control. They cover different aspects such as localization, map-building, path-planning, and exploration. For his work on navigation techniques for mobile robots Wolfram Burgard received several best paper awards at outstanding national and international conferences including AAAI-98, IROS-98, ICRA-2000, IROS-2002, and IROS 2004.
- - - - -
Contact Nick Roy if you would like to meet with Wolfram Monday or Tuesday.
See other events that are part of Robotics Seminar Series Fall 2005
See other events happening in September 2005
