Evolving Controller Symmetry for Multilegged Robots (2010)
Author: Vinod Valsalam
The videos linked below demonstrate the walking behaviors evolved by five neuroevolution methods, which differ only in the way they determine controller symmetry: (1) Evolving symmetry systematically using ENSO, (2) evolving symmetry randomly without using the group-theory mechanisms of ENSO, (3) using fixed S4 symmetry during evolution (i.e. maximal symmetry), (4) using fixed D2 symmetry during evolution, and (5) using direct encoding without symmetry constraints (which is equivalent to using the fixed trivial symmetry during evolution). The videos linked below demonstrate the walking behaviors evolved by five neuroevolution methods, which differ only in the way they determine controller symmetry: (1) Evolving symmetry systematically using ENSO, (2) evolving symmetry randomly without using the group-theory mechanisms of ENSO, (3) using fixed S4 symmetry during evolution (i.e. maximal symmetry), (4) using fixed D2 symmetry during evolution, and (5) using direct encoding without symmetry constraints (which is equivalent to using the fixed trivial symmetry during evolution).

Demo website
Vinod Valsalam Ph.D. Student (Alumni) vkv@alumni.utexas.net
Risto Miikkulainen Professor risto@cs.utexas.edu
ENSO This package contains software implementing the ENSO approach for evolving symmetric modular neural networks. It also in... 2010