Skip to main content

Research Repository

Advanced Search

A virtual creatures model for studies in artificial evolution

Channon

A virtual creatures model for studies in artificial evolution Thumbnail


Authors



Abstract

We present the results of our replication of Karl Sims' work on the evolution of artificial creatures in a physically realistic 3D environment. We used standard McCulloch-Pitts neurons instead of a more complex set of ad hoc neurons, which we believe makes our model a more general tool for future experiments in artificial (co-)evolution. We provide a detailed description of our model and freely accessible source code. We describe our results both qualitatively and quantitatively, including an analysis of some 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.

Citation

Channon. (2005). A virtual creatures model for studies in artificial evolution. In 2005 IEEE Congress on Evolutionary Computation, vols 1-3, proceedings (565 -572)

Publication Date Jan 1, 2005
Pages 565 -572
Book Title 2005 IEEE Congress on Evolutionary Computation, vols 1-3, proceedings
ISBN 0-7803-9363-5
Keywords computer science, artificial intelligence
Publisher URL https://doi.org/10.1109/CEC.2005.1554733

Files

A virtual creatures model for studies in artificial evolution (AChannon).pdf (294 Kb)
PDF






You might also like



Downloadable Citations