Evolving Robotic Neuro-Controllers Using Gene Expression Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4208

  author =       "Jonathan Mwaura and Ed Keedwell",
  title =        "Evolving Robotic Neuro-Controllers Using Gene
                 Expression Programming",
  booktitle =    "2015 IEEE Symposium Series on Computational
                 Intelligence, SSCI",
  year =         "2015",
  pages =        "1063--1072",
  address =      "Cape Town, South Africa",
  month =        dec,
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming, gene
                 expression programming",
  bibdate =      "2016-05-26",
  bibsource =    "DBLP,
  isbn13 =       "978-1-4799-7560-0",
  URL =          "http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7371400",
  DOI =          "doi:10.1109/SSCI.2015.153",
  size =         "10 pages",
  abstract =     "Current trends in evolutionary robotics (ER) involve
                 training a neuro-controller using one of the various
                 population based algorithms. The most popular technique
                 is to learn the optimal weights for the neural network.
                 There is only a limited research into techniques that
                 can be used to fully encode a neural network (NN) and
                 therefore evolve the architecture, weights and
                 thresholds as well as learning rates. The research
                 presented in this paper investigates how the
                 chromosomes of the gene expression programming (GEP)
                 algorithm can be used to evolve robotic neural
                 controllers. The designed neuro-controllers are used in
                 a robotic wall following problem. The ensuing results
                 show that the GEP neural network (GEPNN) is a promising
                 tool for use in evolutionary robotics.",

Genetic Programming entries for Jonathan Mwaura Ed Keedwell