Incremental Acquisition of Complex Visual Behaviour using Genetic Programming

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

@PhdThesis{oai:CiteSeerPSU:574087,
  title =        "Incremental Acquisition of Complex Visual Behaviour
                 using Genetic Programming",
  author =       "Simon Perkins",
  year =         "1998",
  school =       "University of Edingburgh",
  address =      "UK",
  month =        dec,
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://nis-www.lanl.gov/~simes/webdocs/perkins.phdthesis.ps.gz",
  URL =          "http://citeseer.ist.psu.edu/574087.html",
  citeseer-isreferencedby = "oai:CiteSeerPSU:504811;
                 oai:CiteSeerPSU:110595; oai:CiteSeerPSU:301553;
                 oai:CiteSeerPSU:98890; oai:CiteSeerPSU:341224;
                 oai:CiteSeerPSU:154406",
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:574087",
  URL =          "https://www.era.lib.ed.ac.uk/bitstream/handle/1842/363/perkins.phdthesis.ps.gz",
  URL =          "http://hdl.handle.net/1842/363",
  URL =          "http://ethos.bl.uk/OrderDetails.do?did=45&uin=uk.bl.ethos.561717",
  size =         "210 pages",
  abstract =     "In recent years, learning and evolutionary methods
                 have been proposed as methods for automatically
                 designing robot controllers without the need for
                 detailed human design effort. Unfortunately, the
                 reality has been that these methods have only been
                 successfully applied to relatively simple problems
                 involving low-bandwidth sensors and actuators, and
                 simple (often purely reactive) behaviours. Purely
                 automated design methods seem unable to `scale up' to
                 design controllers for the realistically complex tasks
                 we wish to tackle. A promising compromise solution is
                 the idea that the learning/evolutionary system can be
                 left to do most of the work, but with a human providing
                 some sort of high-level assistance to make the problem
                 tractable. Designing robot controllers in this way is
                 often called `robot shaping'. In this thesis I explore
                 a number of dierent forms of shaping, focusing in
                 particular on `black box' techniques which I suggest
                 are more likely to scale up to complex problems than
                 other shaping methods. I also propose a novel extension
                 of Genetic Programming, for use with these shaping
                 methods. Experiments are described in which controllers
                 were evolved, both with and without shaping, for a
                 range of complex tasks including getting a mobile
                 camera to track a moving light in two dimensions, and
                 the harder problem of visually tracking arbitrary
                 moving objects. These controllers are evolved rst in
                 simulation, and then the best ones, evolved using
                 shaping, are transferred successfully to a real robot.
                 I conclude that if used carefully, shaping can reduce
                 learning time and improve nal controller performance.
                 However, choosing an appropriate form of shaping still
                 requires the designer to be very much aware of the
                 underlying details of the evolutionary system. As a
                 result, huma...",
  notes =        "uk.bl.ethos.561717",
}

Genetic Programming entries for Simon Perkins

Citations