Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{Kodjabachian:1998:ieeeTNN,
  author =       "Jerome Kodjabachian and Jean-Arcady Meyer",
  title =        "Evolution and development of neural controllers for
                 locomotion, gradient-following, and obstacle-avoidance
                 in artificial insects",
  journal =      "IEEE Transactions on Neural Networks",
  year =         "1998",
  volume =       "9",
  number =       "5",
  pages =        "796--812",
  month =        sep,
  keywords =     "genetic algorithms, genetic programming, animats,
                 leaky integrators, recurrent neural networks, sgoce
                 paradigm, developmental grammar",
  ISSN =         "1045-9227",
  DOI =          "doi:10.1109/72.712153",
  size =         "17 pages",
  abstract =     "This paper describes how the SGOCE paradigm has been
                 used to evolve developmental programs capable of
                 generating recurrent neural networks that control the
                 behaviour of simulated insects. This paradigm is
                 characterised by an encoding scheme, an evolutionary
                 algorithm, syntactic constraints, and an incremental
                 strategy that are described in turn. The additional use
                 of an insect model equipped with six legs and two
                 antennae made it possible to generate control modules
                 that allowed it to successively add gradient-following
                 and obstacle-avoidance capacities to walking behaviour.
                 The advantages of this evolutionary approach, together
                 with directions for future work, are discussed",
  notes =        "also known as \cite{712153}",
}

Genetic Programming entries for Jerome Kodjabachian Jean-Arcady Meyer

Citations