Field Report

You have free access to this content

The MIT–Cornell collision and why it happened

  1. Luke Fletcher1,
  2. Seth Teller1,
  3. Edwin Olson1,
  4. David Moore1,
  5. Yoshiaki Kuwata1,
  6. Jonathan How1,
  7. John Leonard1,
  8. Isaac Miller2,
  9. Mark Campbell2,
  10. Dan Huttenlocher2,
  11. Aaron Nathan2,
  12. Frank-Robert Kline2

Article first published online: 22 OCT 2008

DOI: 10.1002/rob.20266

Issue

Journal of Field Robotics

Journal of Field Robotics

Special Issue: Special Issue on the 2007 DARPA Urban Challenge, Part III

Volume 25, Issue 10, pages 775–807, October 2008

Additional Information

How to Cite

Fletcher, L., Teller, S., Olson, E., Moore, D., Kuwata, Y., How, J., Leonard, J., Miller, I., Campbell, M., Huttenlocher, D., Nathan, A. and Kline, F.-R. (2008), The MIT–Cornell collision and why it happened. Journal of Field Robotics, 25: 775–807. doi: 10.1002/rob.20266

Author Information

  1. 1

    Massachusetts Institute of Technology Cambridge, Massachusetts 02139

  2. 2

    Cornell University Ithaca, New York 14853

Publication History

  1. Issue published online: 22 OCT 2008
  2. Article first published online: 22 OCT 2008
  3. Manuscript Accepted: 3 SEP 2008
  4. Manuscript Received: 15 FEB 2008

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (1504K)

Abstract

Midway through the 2007 DARPA Urban Challenge, MIT's robot “Talos” and Team Cornell's robot “Skynet” collided in a low-speed accident. This accident was one of the first collisions between full-sized autonomous road vehicles. Fortunately, both vehicles went on to finish the race and the collision was thoroughly documented in the vehicle logs. This collaborative study between MIT and Cornell traces the confluence of events that preceded the collision and examines its root causes. A summary of robot–robot interactions during the race is presented. The logs from both vehicles are used to show the gulf between robot and human-driver behavior at close vehicle proximities. Contributing factors are shown to be (1) difficulties in sensor data association leading to an inability to detect slow-moving vehicles and phantom obstacles, (2) failure to anticipate vehicle intent, and (3) an overemphasis on lane constraints versus vehicle proximity in motion planning. Finally, we discuss approaches that could address these issues in future systems, such as intervehicle communication, vehicle detection, and prioritized motion planning. © 2008 Wiley Periodicals, Inc.

Get PDF (1504K)