Gene regulated car driving: using a gene regulatory network to drive a virtual car

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

@Article{Sanchez:2014:GPEM,
  author =       "Stephane Sanchez and Sylvain Cussat-Blanc",
  title =        "Gene regulated car driving: using a gene regulatory
                 network to drive a virtual car",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2014",
  volume =       "15",
  number =       "4",
  pages =        "477--511",
  month =        dec,
  note =         "Special issue on GECCO competitions",
  keywords =     "genetic algorithms, genetic programming, Gene
                 regulatory network, Virtual car racing, Machine
                 learning, Incremental evolution",
  ISSN =         "1389-2576",
  DOI =          "doi:10.1007/s10710-014-9228-y",
  size =         "35 pages",
  abstract =     "This paper presents a virtual racing car controller
                 based on an artificial gene regulatory network. Usually
                 used to control virtual cells in developmental models,
                 recent works showed that gene regulatory networks are
                 also capable to control various kinds of agents such as
                 foraging agents, pole cart, swarm robots, etc. This
                 paper details how a gene regulatory network is evolved
                 to drive on any track through a three-stages
                 incremental evolution. To do so, the inputs and outputs
                 of the network are directly mapped to the car sensors
                 and actuators. To make this controller a competitive
                 racer, we have distorted its inputs online to make it
                 drive faster and to avoid opponents. Another
                 interesting property emerges from this approach: the
                 regulatory network is naturally resistant to noise. To
                 evaluate this approach, we participated in the 2013
                 simulated racing car competition against eight other
                 evolutionary and scripted approaches. After its first
                 participation, this approach finished in third place in
                 the competition.",
  notes =        "TORCS simulator 'We have compared the effect of noise
                 on our driver and on six other approaches. These are Mr
                 Racer's CMA-ES based approach, Autopia's fuzzy
                 controller, Cobostar CMA-ES optimised hand-coded
                 strategies, Cardamone's NEAT driver, Ready2Win's
                 modular architecture and Mariscal's expert system'.",
}

Genetic Programming entries for Stephane Sanchez Sylvain Cussat-Blanc

Citations