Evolving Control Laws for a Network of Traffic Signals

Created by W.Langdon from gp-bibliography.bib Revision:1.4215

  author =       "David J. Montana and Steven Czerwinski",
  title =        "Evolving Control Laws for a Network of Traffic
  booktitle =    "Genetic Programming 1996: Proceedings of the First
                 Annual Conference",
  editor =       "John R. Koza and David E. Goldberg and 
                 David B. Fogel and Rick L. Riolo",
  year =         "1996",
  month =        "28--31 " # jul,
  keywords =     "genetic algorithms, genetic programming",
  pages =        "333--338",
  address =      "Stanford University, CA, USA",
  publisher =    "MIT Press",
  URL =          "http://vishnu.bbn.com/papers/gp96.pdf",
  URL =          "http://cognet.mit.edu/sites/default/files/books/9780262315876/pdfs/9780262315876_chap44.pdf",
  URL =          "http://cognet.mit.edu/library/books/view?isbn=0262611279",
  size =         "6 pages",
  abstract =     "Optimally controlling the timings of traffic signals
                 within a network of intersections is a difficult but
                 important problem. Because the traffic signals need to
                 coordinate their behaviour to achieve the common goal
                 of optimising traffic ow through the network, this is a
                 problem in collective intelligence. We apply a hybrid
                 of a genetic algorithm and strongly typed genetic
                 programming (STGP) to the problem of learning control
                 laws which optimize aggregate performance. STGP learns
                 the single basic decision tree to be executed by all
                 the intersections when deciding whether to change the
                 phase of the trafic signal. The genetic algorithm
                 learns different constants to be used in these decision
                 trees for different intersections, hence allowing
                 specialisation based on dierences in geometry and
                 traffic flow. Preliminary experimental work shows that
                 our approach yields good performance on a variety of
                 network configurations and that it can evolve control
                 laws which induce cooperation, communication, and
                 specialization among the traffic signals.",
  notes =        "GP-96 Java demo at

Genetic Programming entries for David J Montana Steven Czerwinski