Collaborating with a Genetic Programming System to Generate Modular Robotic Code
by Jeremy Kubica and Eleanor Rieffel
BibTeX:
@inproceedings{kubica_gecco_02,
author = "Jeremy Kubica and Eleanor Rieffel",
title = "Collaborating with a Genetic Programming System to Generate Modular Robotic Code",
booktitle = "GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference",
editor = "W.B.Langdon and E.Cantu-Paz and K.Mathias and R. Roy and D.Davis and R. Poli
and K.Balakrishnan and V. Honavar and G. Rudolph and J. Wegener and L. Bull
and M. A. Potter and A.C. Schultz and J. F. Miller and E. Burke and N.Jonoska",
year = "2002",
pages = "804--811",
address = "New York",
publisher_address = "San Francisco, CA 94104, USA",
month = "9-13 July",
publisher = "Morgan Kaufmann Publishers",
isbn = "1-55860-878-8"
}
Abstract:
The design of primitives can be a difficult problem that can effect the performance
of genetic programming. We look at a joint approach that combines both hand-coding
and genetic programming to define and refine primitives in the context of a creating
distribute control code for modular robots. We give some rules of thumb for designing
and refining sets of primitives, illustrating the rules with lessons we learned in
the course of solving several problems in control code for modular robots.
- Download PS