First Three Generations of Evolved Robots

Created by W.Langdon from gp-bibliography.bib Revision:1.4202

  author =       "Jordan B. Pollack and Hod Lipson and Pablo Funes and 
                 Gregory Hornby",
  title =        "First Three Generations of Evolved Robots",
  booktitle =    "Evolutionary Robotics From Intelligent Robotics to
                 Artificial Life: International Symposium, ER 2001",
  year =         "2001",
  editor =       "T. Gomi",
  volume =       "2217",
  pages =        "62--71",
  series =       "LNCS",
  address =      "Tokyo, Japan",
  month =        oct # " 18-19",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-540-42737-7",
  ISSN =         "0302-9743",
  bibdate =      "Sat Feb 2 13:07:04 MST 2002",
  DOI =          "doi:10.1007/3-540-45502-7_3",
  size =         "10 pages",
  abstract =     "The field of robotics today faces an economic
                 predicament: most problems in the physical world are
                 too difficult for the current state of the art. The
                 difficulties associated with designing, building and
                 controlling robots have led to a stasis, and robots in
                 industry are only applied to simple and highly
                 repetitive manufacturing tasks. Over the last few years
                 we have been trying to address this challenge through
                 an alternative approach: Rather than a seeking an
                 intelligent general-purpose robot, we are seeking the
                 process that can automatically design and fabricate
                 special purpose mechanisms and controllers to achieve
                 specific short-term objectives. This short paper
                 provides a brief review of three generations of our
                 research results. Automatically designed high
                 part-count static structures that are buildable,
                 automatically designed and manufactured dynamic
                 electromechanical systems, and modular robots
                 automatically designed through generative encoding. We
                 expect that with continued improvement in simulation,
                 manufacturing, and transfer, we will achieve the
                 ability to automatically design and fabricate custom
                 machinery for short-term deployment on specific
  notes =        "see also \cite{pollack:2001:AL}",

Genetic Programming entries for Jordan B Pollack Hod Lipson Pablo J Funes Gregory S Hornby