Sciweavers

Share
MIG
2009
Springer

Evolved Controllers for Simulated Locomotion

9 years 5 months ago
Evolved Controllers for Simulated Locomotion
Abstract. We present a system for automatically evolving neural networks as physics-based locomotion controllers for humanoid characters. Our approach provides two key features: (a) the topology of the neural network controller gradually grows in size to allow increasingly complex behavior, and (b) the evolutionary process requires only the physical properties of the character model and a simple fitness function. No a priori knowledge of the appropriate cycles or patterns of motion is needed.
Brian F. Allen, Petros Faloutsos
Added 27 May 2010
Updated 27 May 2010
Type Conference
Year 2009
Where MIG
Authors Brian F. Allen, Petros Faloutsos
Comments (0)
books