A Perception-Driven Autonomous Urban Vehicle

被引：348

作者：

Leonard, John ^{[1
]}

How, Jonathan ^{[1
]}

Teller, Seth ^{[1
]}

Berger, Mitch ^{[1
]}

Campbell, Stefan ^{[1
]}

Fiore, Gaston ^{[1
]}

Fletcher, Luke ^{[1
]}

Frazzoli, Emilio ^{[1
]}

Huang, Albert ^{[1
]}

Karaman, Sertac ^{[1
]}

Koch, Olivier ^{[1
]}

Kuwata, Yoshiaki ^{[1
]}

Moore, David ^{[1
]}

Olson, Edwin ^{[1
]}

Peters, Steve ^{[1
]}

Teo, Justin ^{[1
]}

Truax, Robert ^{[1
]}

Walter, Matthew ^{[1
]}

Barrett, David ^{[2
]}

Epstein, Alexander ^{[2
]}

Maheloni, Keoni ^{[2
]}

Moyer, Katy ^{[2
]}

Jones, Troy ^{[3
]}

Buckley, Ryan ^{[3
]}

Antone, Matthew ^{[4
]}

Galejs, Robert ^{[5
]}

Krishnamurthy, Siddhartha ^{[5
]}

Williams, Jonathan ^{[5
]}

机构：

[1] MIT, Cambridge, MA 02139 USA

[2] Franklin W Olin Coll, Needham, MA 02492 USA

[3] Charles Stark Draper Lab Inc, Cambridge, MA 02139 USA

[4] BAE Syst Adv Informat Technol, Burlington, MA 01803 USA

[5] MIT, Lincoln Lab, Lexington, MA 02420 USA

来源：

JOURNAL OF FIELD ROBOTICS | 2008年 / 25卷 / 10期

关键词：

D O I：

10.1002/rob.20262

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

This paper describes the architecture and implementation of an autonomous passenger vehicle designed to navigate using locally perceived information in preference to potentially inaccurate or incomplete map data. The vehicle architecture was designed to handle the original DARPA Urban Challenge requirements of perceiving and navigating a road network with segments defined by sparse waypoints. The vehicle implementation includes many heterogeneous sensors with significant communications and computation bandwidth to capture and process high-resolution, high-rate sensor data. The output of the comprehensive environmental sensing subsystem is fed into a kinodynamic motion planning algorithm to generate all vehicle motion. The requirements of driving in lanes, three-point turns, parking, and maneuvering through obstacle fields are all generated with a unified planner. A key aspect of the planner is its use of closed-loop simulation in a rapidly exploring randomized trees algorithm, which can randomly explore the space while efficiently generating smooth trajectories in a dynamic and uncertain environment. The overall system was realized through the creation of a powerful new suite of software tools for message passing, logging, and visualization. These innovations provide a strong platform for future research in aotonomous driving in global positioning system-denied and highly dynamic environments with poor a priori information. (c) 2008 Wiley Periodicals, Inc.

引用

页码：727 / 774

页数：48

共 24 条

[1]

[Anonymous], 1990, Introduction to Algorithms

[2]

[Anonymous], 2001, MULTIPLE VIEW GEOMET

[3] GOLD: A parallel real-time stereo vision system for generic obstacle and lane detection [J].