- author = "Thomas Miconi and Alastair Channon",
- title = "An Improved System for Artificial Creatures Evolution",
- booktitle = "Artificial Life X: Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems",
- year = "2006",
- editor = "Luis Mateus Rocha and Larry S. Yaeger and Mark A. Bedau and Dario Floreano and Robert L. Goldstone and Alessandro Vespignani",
- pages = "255--261",
- address = "Bloomington, IN, USA",
- publisher_address = "Cambridge, MA, USA",
- month = "3-7 " # jun,
- publisher = "MIT Press",
- keywords = "genetic algorithms, genetic programming, Developmental System. reflection, Recursion Unrolling, Creature evolution",
- ISBN = "0-262-68162-5",
-
URL = "
http://www.channon.net/alastair/papers/alife2006.pdf",
- size = "7 pages",
-
abstract = "We present our complete reimplementation of Karl Sims
system for evolving and coevolving autonomous creatures
in a physically realistic three-dimensional (3D)
environment \cite{Sims:1994:evc} \cite{alife94:sims}.
Creatures are articulated structures composed of rigid
blocks and controlled by embedded neural networks. The
main differences with Sims are, first, the use of
standard McCulloch-Pitts neurons (instead of a set of
ad hoc, complex functional neurons) and, second, an
improved genetic encoding and developmental system
(allowing fine-grained control of neural connections in
duplicated morphological features, and
replication-exaptation processes).
This paper expands upon a previous version of our system (Miconi and Channon, 2005, \cite{Miconi:Avc:cec2005}) which implemented a subset of features present in Sims system, and dealt with simple evolutionary experiments based on external fitness functions only: the present paper extends the feature set proposed by Sims, and describes the results of experiments based on the box-grabbing coevolutionary task introduced by Sims. We provide a detailed description of our model and freely accessible source code. We describe some of our results, including an analysis of evolved neural controllers. To the best of our knowledge, our work is the first replication of Sims efforts to achieve results comparable to Sims in efficiency and complexity, with standard neurons and realistic Newtonian physics.",
- notes = "Broken Aug 2026 http://mitpress.mit.edu/catalog/item/default.asp?ttype=2&tid=11018",
