Learning robot behaviors by evolving genetic programs

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

@InProceedings{oai:CiteSeerPSU:454905,
  author =       "Kwang-Ju Lee and Byoung-Tak Zhang",
  title =        "Learning robot behaviors by evolving genetic
                 programs",
  booktitle =    "26th Annual Conference of the IEEE Industrial
                 Electronics Society, IECON",
  year =         "2000",
  volume =       "4",
  pages =        "2867--2872",
  address =      "Nagoya",
  month =        "22-28 " # oct,
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming",
  citeseer-isreferencedby = "oai:CiteSeerPSU:67000;
                 oai:CiteSeerPSU:319694; oai:CiteSeerPSU:269370;
                 oai:CiteSeerPSU:265613",
  citeseer-references = "oai:CiteSeerPSU:454784; oai:CiteSeerPSU:3551;
                 oai:CiteSeerPSU:163604; oai:CiteSeerPSU:160348",
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:454905",
  rights =       "unrestricted",
  URL =          "http://bi.snu.ac.kr/Publications/Conferences/International/SEAL00.pdf",
  URL =          "http://citeseer.ist.psu.edu/454905.html",
  abstract =     "A method for evolving behavior-based robot controllers
                 using genetic programming is presented. Due to their
                 hierarchical nature, genetic programs are useful
                 representing high-level knowledge for robot
                 controllers. One drawback is the difficulty of
                 incorporating sensory inputs. To overcome the gap
                 between symbolic representation and direct sensor
                 values, the elements of the function set in genetic
                 programming is implemented as a single-layer
                 perceptron. Each perceptron is composed of sensory
                 input nodes and a decision output node. The robot
                 learns proper behavior rules based on local, limited
                 sensory information without using an internal map.
                 First, it learns how to discriminate the target using
                 single-layer perceptrons. Then, the learned perceptrons
                 are applied to the function nodes of the genetic
                 program tree which represents a robot controller.
                 Experiments have been performed using Khepera robots.
                 The presented method successfully evolved high-level
                 genetic programs that control the robot to find the
                 light source from sensory inputs",
}

Genetic Programming entries for Kwang-Ju Lee Byoung-Tak Zhang

Citations