Evolution of Human Competitive Driving Agent Operating a Scale Model of a Car

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Ivan Tanev and Katsunori Shimohara",
  title =        "Evolution of Human Competitive Driving Agent Operating
                 a Scale Model of a Car",
  booktitle =    "Proceedings of SICE Annual Conference",
  year =         "2007",
  pages =        "1582--1587",
  month =        "17-20 " # sep,
  organization = "Kagawa University, Japan",
  DOI =          "doi:10.1109/SICE.2007.4421235",
  size =         "6 pages",
  keywords =     "genetic algorithms, genetic programming, artificial
                 intelligence, Automatic control, Cameras, Delay, Driver
                 circuits, Electronic mail, Humans, Information systems,
                 Transmitters, remotely operated vehicles, road
                 vehicles, telecontrol, adaptive racing games, car,
                 human competitive driving agent, overhead video camera,
                 standard RC transmitter, driving style, evolution,
                 remote control",
  abstract =     "We present an evolutionary design of the driving style
                 of agent, remotely operating a scale model of a car in
                 a human competitive way. The agent perceives the
                 environment from an overhead video camera and conveys
                 its actions via standard RC transmitter. In order to
                 cope with the video feed latency we propose an
                 anticipatory modelling in which the agent considers its
                 current actions based on the anticipated intrinsic
                 state of the car and surrounding. We formalised the
                 driving style by defining the key parameters, which
                 describe it, and applied genetic algorithms to evolve
                 the optimal values of these parameters. The evolved
                 agent is human competitive in that it yields both
                 faster and more consistent lap times than those of a
                 human around a predefined circuit. Presented work can
                 be viewed as a step towards the development of a
                 framework of adaptive racing games in which the human
                 competes against a computerised opponent with matching

Genetic Programming entries for Ivan T Tanev Katsunori Shimohara