Computer Vision Algorithms for the DARPA Urban Challenge 2007
The TU Braunschweig participated in the DARPA Urban Challenge 2007, its autonomous vehicle 'Caroline' was among the finalists. The Computer Graphics lab provided the real-time vision algorithms for that task.
Caroline's computer vision system consists of two separate systems. The first is a monocular color segmentation based system that classifies the ground in front of the car as drivable, undrivable or unknown. It assists in situations where the drivable terrain and the surrounding area (e.g. grass, concrete or shrubs) differ in color and it deals with man-made artifacts such as lane markings as well as bad lighting and weather conditions. The second vision system is a multi-view lane detection that identifies the different kinds of lanes described by DARPA, such as broken and continuous as well as white and yellow lane markings. Using four high-resolution color cameras and state-of-the-art graphics hardware, it detects its own lane and the two adjacent lanes to the left and right with a field of view of 175 degrees at up to 35 meters. The output of the lane detection algorithm is directly processed by the artificial intelligence.
Caroline: An Autonomously Driving Vehicle for Urban Environments
in Martin Buehler and Karl Iagnemma and Sanjiv Singh (Eds.): The DARPA Urban Challenge, Springer, ISBN 978-3-642-03990-4, pp. 441-508, January 2010.
vIsage - A visualization and debugging framework for distributed system applications
in Proc. WSCG, vol. 2009, UNION Agency -- Science Press, pp. 1-7, February 2009.
Caroline: An autonomously driving vehicle for urban environments
in Journal of Field Robotics, vol. 25, no. 9, pp. 674-724, December 2008.
Team CarOLO - Technical Paper
Technical Report no. 2008-7, Technische Universität Braunschweig, Carl-Friedrich-Gauss-Fakultät, October 2008.