GEF: A Self-Programming Robot Using Grammatical Evolution

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Charles Peabody and Jennifer Seitzer",
  title =        "{GEF}: A Self-Programming Robot Using Grammatical
  bibdate =      "2015-04-12",
  bibsource =    "DBLP,
  booktitle =    "Proceedings of the Twenty-Ninth {AAAI} Conference on
                 Artificial Intelligence, January 25-30, 2015, Austin,
                 Texas, {USA}",
  publisher =    "AAAI Press",
  year =         "2015",
  editor =       "Blai Bonet and Sven Koenig",
  isbn13 =       "978-1-57735-698-1",
  pages =        "4194--4195",
  keywords =     "genetic algorithms, genetic programming, grammatical
                 evolution, evolutionary computation, meta-level
                 jumping, contingency handling, robot controllers",
  URL =          "",
  URL =          "",
  size =         "2 pages",
  abstract =     "Grammatical Evolution (GE) is that area of genetic
                 algorithms that evolves computer programs in high-level
                 languages possessing a BNF grammar. In this work, we
                 present GEF (Grammatical Evolution for the Finch), a
                 system that employs grammatical evolution to create a
                 Finch robot controller program in Java. The system uses
                 both the traditional GE model as well as employing
                 extensions and augmentations that push the boundaries
                 of goal-oriented contexts in which robots typically act
                 including a meta-level handler that fosters a level of
                 self-awareness in the robot. To handle contingencies,
                 the GEF system has been endowed with the ability to
                 perform meta-level jumps. When confronted with
                 unplanned events and dynamic changes in the
                 environment, our robot will automatically transition to
                 pursue another goal, changing fitness functions, and
                 generate and invoke operating system level scripting to
                 facilitate the change. The robot houses a raspberry pi
                 controller that is capable of executing one (evolved)
                 program while wirelessly receiving another over an
                 asynchronous client. This work is part of an overall
                 project that involves planning for contingencies. In
                 this poster, we present the development framework and
                 system architecture of GEF, including the newly
                 discovered meta-level handler, as well as some other
                 system successes, failures, and insights.",

Genetic Programming entries for Charles Peabody Jennifer Seitzer