2006 | Sebastian Thrun, Mike Montemerlo, Hendrik Dahlkamp, David Stavens, Andrei Aron, James Diebel, Philip Fong, John Gale, Morgan Halpenny, Gabriel Hoffmann, Kenny Lau, Celia Oakley, Mark Palatucci, Vaughan Pratt, and Pascal Stang; Sven Strohband, Cedric Dupont, Lars-Erik Jendrossek, Christian Koelen, Charles Markey, Carlo Rummel, Joe van Niekerk, Eric Jensen, and Philippe Alessandrini; Gary Bradski, Bob Davies, Scott Ettinger, Adrian Kaehler, and Ara Nefian; Pamela Mahoney
The paper describes the development and performance of Stanley, the robot that won the 2005 DARPA Grand Challenge. The challenge aimed to develop an autonomous robot capable of navigating complex off-road terrain without manual intervention. Stanley, based on a 2004 Volkswagen Touareg R5 TDI, was equipped with advanced sensors and a six-processor computing platform. The robot's software system relied on state-of-the-art artificial intelligence technologies, including machine learning and probabilistic reasoning. The paper details the major components of Stanley's architecture, such as vehicle state estimation, laser terrain mapping, computer vision terrain analysis, and road property estimation. These components enabled Stanley to navigate the challenging course, achieving the fastest completion time of 6 hours, 53 minutes, and 58 seconds. The success of Stanley's development and performance highlights advancements in autonomous driving technology.The paper describes the development and performance of Stanley, the robot that won the 2005 DARPA Grand Challenge. The challenge aimed to develop an autonomous robot capable of navigating complex off-road terrain without manual intervention. Stanley, based on a 2004 Volkswagen Touareg R5 TDI, was equipped with advanced sensors and a six-processor computing platform. The robot's software system relied on state-of-the-art artificial intelligence technologies, including machine learning and probabilistic reasoning. The paper details the major components of Stanley's architecture, such as vehicle state estimation, laser terrain mapping, computer vision terrain analysis, and road property estimation. These components enabled Stanley to navigate the challenging course, achieving the fastest completion time of 6 hours, 53 minutes, and 58 seconds. The success of Stanley's development and performance highlights advancements in autonomous driving technology.