[ODE] Creature Evolution input

John DeWeese deweese at ict.usc.edu
Thu Mar 13 11:56:02 2003


Guess what, I'm also doing a project on creature evolution! It's 
clearly "the thing to do".

 > Additionally, if your creatures have complex physiologies, you
 > might want to consider dividing the ANN into multiple smaller
 > (hierarchically organized) ANN's that are each dedicated to
 > controlling just one part of the creature (just like MIT's Attila
 > or Karl Sims' block creatures). For example a simple hexapod could
 > be controlled by seven little ANNs that are interconnected (one
 > for each leg and one to coordinate the effort - the latter
 > actually being optional).

This allows the neural net for the body part, and its connections to 
other neural nets, can be included or encoded in the genome of the part 
by itself. This way, you can keep an established net for some parts, 
while screwing with the connections of others for the sake of evolution.

   - John