Genetic Programming of Process Decomposition Strategies for Evolvable Hardware

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

  author =       "Ho-Sik Seok and Kwang-Ju Lee and Byoung-Tak Zhang and 
                 Dong-Wook Lee and Kwee-Bo Sim",
  title =        "Genetic Programming of Process Decomposition
                 Strategies for Evolvable Hardware",
  booktitle =    "Proceedings of the Second NASA / DoD Workshop on
                 Evolvable Hardware",
  year =         "2000",
  pages =        "25--34",
  address =      "Palo Alto, California",
  publisher_address = "1730 Massachusetts Avenue, N.W., Washington, DC,
                 20036-1992, USA",
  month =        "13-15 " # jul,
  organisation = "Jet Propulsion Laboratory, California Institute of
  publisher =    "IEEE Computer Society",
  keywords =     "genetic algorithms, genetic programming, EHW,
                 Intelligent robots, Mobile robots",
  ISBN =         "0-7695-0762-X",
  DOI =          "doi:10.1109/EH.2000.869339",
  URL =          "",
  size =         "10 pages",
  abstract =     "Evolvable hardware is able to offer considerably
                 higher performance than general-purpose processors and
                 significantly more flexibility than ASICs. In order to
                 take the advantages of general-purpose processors and
                 ASICs, dividing a complex process into subprocesses is
                 essential. In this paper, we propose an evolutionary
                 method called context switching that splits a task into
                 a set of subtasks whose complexity is manageable on the
                 given hardware. The method is based on genetic
                 programming. Due to its expressive power, genetic
                 program can represent flexible strategies for
                 decomposing complex tasks. The effectiveness of context
                 switching is demonstrated on the design of adaptive
                 controllers for a team of autonomous mobile robots.",
  notes =        "EH-2000 XC6216. VCC HOT board. Two Khepera, one object
                 some obstacles. cannot map environment. context
                 switching allows process to be bigger than hardware.
                 Uses fitness switching of


Genetic Programming entries for Ho-Sik Seok Kwang-Ju Lee Byoung-Tak Zhang Dong-Wook Lee Kwee-Bo Sim