Autonomous driving in urban environments: Boss and the Urban Challenge

被引:1171
作者
Urmson, Chris [1 ]
Anhalt, Joshua [1 ]
Bagnell, Drew [1 ]
Baker, Christopher [1 ]
Bittner, Robert [1 ]
Clark, M. N. [1 ]
Dolan, John [1 ]
Duggins, Dave [1 ]
Galatali, Tugrul [1 ]
Geyer, Chris [1 ]
Gittleman, Michele [1 ]
Harbaugh, Sam [1 ]
Hebert, Martial [1 ]
Howard, Thomas M. [1 ]
Kolski, Sascha [1 ]
Kelly, Alonzo [1 ]
Likhachev, Maxim [1 ]
McNaughton, Matt [1 ]
Miller, Nick [1 ]
Peterson, Kevin [1 ]
Pilnick, Brian [1 ]
Rajkumar, Raj [1 ]
Rybski, Paul [1 ]
Salesky, Bryan [1 ]
Seo, Young-Woo [1 ]
Singh, Sanjiv [1 ]
Snider, Jarrod [1 ]
Stentz, Anthony [1 ]
Whittaker, William Red [1 ]
Wolkowicki, Ziv [1 ]
Ziglar, Jason [1 ]
Bae, Hong [2 ]
Brown, Thomas [2 ]
Demitrish, Daniel [2 ]
Litkouhi, Bakhtiar [2 ]
Nickolaou, Jim [2 ]
Sadekar, Varsha [2 ]
Zhang, Wende [2 ]
Struble, Joshua [3 ]
Taylor, Michael [3 ]
Darms, Michael [4 ]
Ferguson, Dave [5 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[2] GM Corp, Res & Dev, Warren, MI 48090 USA
[3] Caterpillar Inc, Peoria, IL 61656 USA
[4] Continental AG, Auburn Hills, MI 48326 USA
[5] Intel Res, Pittsburgh, PA 15213 USA
关键词
D O I
10.1002/rob.20255
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Boss is an autonomous vehicle that uses on-board sensors (global positioning system, lasers, radars, and cameras) to track other vehicles, detect static obstacles, and localize itself relative to a road model. A three-layer planning system combines mission, behavioral, and motion planning to drive in urban environments. The mission planning layer considers which street to take to achieve a mission goal. The behavioral layer determines when to change lanes and precedence at intersections and performs error recovery maneuvers. The motion planning layer selects actions to avoid obstacles while making progress toward local goals. The system was developed from the ground up to address the requirements of the DARPA Urban Challenge using a spiral system development process with a heavy emphasis on regular, regressive system testing. During the National Qualification Event and the 85-km Urban Challenge Final Event, Boss demonstrated some of its capabilities, qualifying first and winning the challenge. (C) 2008 Wiley Periodicals, Inc.
引用
收藏
页码:425 / 466
页数:42
相关论文
共 20 条
  • [1] [Anonymous], 1993, Ten Lectures of Wavelets
  • [2] *COMM ARM UNM GROU, 2002, TECHN DEV ARM UNM GR
  • [3] Darms M, 2005, 2005 IEEE Intelligent Vehicles Symposium Proceedings, P729
  • [4] DARMS M, 2007, BASIS SYSTEMARCHITEK
  • [5] DARMS M, 2008, P 2008 IEEE INT VEH, P1192
  • [6] DARMS M, 2008, AUTOREG 2008 STEUER, P521
  • [7] DARMS M, 2008, 5 WORKSH FAHR KARLSR, P57
  • [8] *DARPA, 2007, DARPA URB CHALL
  • [9] USE OF HOUGH TRANSFORMATION TO DETECT LINES AND CURVES IN PICTURES
    DUDA, RO
    HART, PE
    [J]. COMMUNICATIONS OF THE ACM, 1972, 15 (01) : 11 - &
  • [10] FERGUSON D, 2008, MOTION PLANNIN UNPUB