Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Sensor Fusion and Tracking in an Urban Environment

Back
Abstract:
Team Cornell was one of six teams to complete the 2007 DARPA Urban Challenge, completing over 55 miles of autonomous driving in an urban environment in approximately seven hours, including competition stops. The competition included many urban driving scenarios such as staying in a lane, merging into traffic, passing, intersections, parking, and even robot-robot interaction. A key element of Cornell's solution was the ability to fuse data from many sensors, and track obstacles and other vehicles, in real time. This probabilistic environment was then used for control and planning in the vehicle. This talk will discuss the technical aspects of the fusion process. A multi-threshold, single frame clustering of LIDAR points was used to develop stable clusters for tracking. A Rao-Blackwellized particle filter was used for the joint assignment-tracking problem using laser, radar and vision sensors. Finally, Track IDs were generated from obstacles via global maximum likelihood matching to previous frame given all measurements. The talk will also discuss connections of the tracking to low level control and planning, and will show video and log results from the 2007 DARPA Urban Challenge.

http://www.mae.cornell.edu/campbell/
Type of Seminar:
Public Seminar
Speaker:
Prof. Mark Campbell
Sibley School of Mechanical and Aerospace Engineering , Cornell University, Ithaca, NY
Date/Time:
Sep 16, 2008   17:15 /
Location:

ETH Zentrum, Building ETZ , Room E6
Contact Person:

Prof. Raffaello D'Andrea
No downloadable files available.
Biographical Sketch:
Mark Campbell is an Associate Professor in the Sibley School of Mechanical and Aerospace Engineering at Cornell University. He received his B.S. from Carnegie Mellon in Mechanical Engineering in 1990, and his M.S. and Ph.D. in Control and Estimation from MIT in 1993 and 1996. His research interests are in the areas of autonomous systems, probabilistic models of human decision making, and nonlinear estimation theory. He has been recognized from NASA for his work on the Middeck Active Control Experiment, flown on STS-67. He received best paper awards from the AIAA and Frontiers in Education conference, and teaching awards from Cornell, University of Washington, and the ASEE. He is an Associate Fellow of the AIAA, Australian Research Council International Fellow, and Associate Director of the AACC board.