Nate Kohl's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category


Evolving a Real-World Vehicle Warning System

Evolving a Real-World Vehicle Warning System. Nate Kohl, Kenneth Stanley, Risto Miikkulainen, Michael Samples, and Rini Sherony. In Proceedings of the Genetic and Evolutionary Computation Conference 2006, pp. 1681–1688, July 2006.
http://www.sigevo.org/gecco-2006/

Download

[PDF]1.2MB  

Abstract

Many serious automobile accidents could be avoided if drivers were warned of impending crashes before they occur. Creating such warning systems by hand, however, is a difficult and time-consuming task. This paper describes three advances toward evolving neural networks with NEAT (NeuroEvolution of Augmenting Topologies) to warn about such crashes in real-world environments. First, NEAT was evaluated in a complex, dynamic simulation with other cars, where it outperformed three hand-coded strawman warning policies and generated warning levels comparable with those of an open-road warning system. Second, warning networks were trained using raw pixel data from a simulated camera. Surprisingly, NEAT was able to generate warning networks that performed similarly to those trained with higher-level input and still outperformed the baseline hand-coded warning policies. Third, the NEAT approach was evaluated in the real world using a robotic vehicle testbed. Despite noisy and ambiguous sensor data, NEAT successfully evolved warning networks using both laser rangefinders and visual sensors. The results in this paper set the stage for developing warning networks for real-world traffic, which may someday save lives in real vehicles.

BibTeX Entry

@InProceedings{kohl:gecco06,
   author = "Nate Kohl and Kenneth Stanley and Risto Miikkulainen and Michael Samples and Rini Sherony",
   title = "Evolving a Real-World Vehicle Warning System",
   booktitle = "Proceedings of the Genetic and Evolutionary Computation Conference 2006",
   year = "2006",
   month = "July",
   pages = "1681--1688",
   abstract = { 
  Many serious automobile accidents could be avoided if drivers were
  warned of impending crashes before they occur.  Creating such
  warning systems by hand, however, is a difficult and time-consuming
  task.  This paper describes three advances toward evolving neural
  networks with NEAT (NeuroEvolution of Augmenting Topologies) to warn
  about such crashes in real-world environments.  First, NEAT was
  evaluated in a complex, dynamic simulation with other cars, where it
  outperformed three hand-coded strawman warning policies and
  generated warning levels comparable with those of an open-road
  warning system.  Second, warning networks were trained using raw
  pixel data from a simulated camera.  Surprisingly, NEAT was able to
  generate warning networks that performed similarly to those trained
  with higher-level input and still outperformed the baseline
  hand-coded warning policies.  Third, the NEAT approach was evaluated
  in the real world using a robotic vehicle testbed.  Despite noisy
  and ambiguous sensor data, NEAT successfully evolved warning
  networks using both laser rangefinders and visual sensors.  The
  results in this paper set the stage for developing warning networks
  for real-world traffic, which may someday save lives in real
  vehicles.
	},
  wwwnote = {<a href="http://www.sigevo.org/gecco-2006/">http://www.sigevo.org/gecco-2006/</a>},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Machine Learning}
}    

Generated by bib2html.pl (written by Patrick Riley ) on Sun May 15, 2011 08:27:15