Animation of dynamic legged locomotion
Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Limit cycle control and its application to the animation of balancing and walking
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
SIGGRAPH '88 Proceedings of the 15th annual conference on Computer graphics and interactive techniques
Evolving neural networks through augmenting topologies
Evolutionary Computation
Evolutionary controller synthesis for 3-d character animation
Evolutionary controller synthesis for 3-d character animation
Efficient evolution of neural networks through complexification
Efficient evolution of neural networks through complexification
Dynamic response for motion capture animation
ACM SIGGRAPH 2005 Papers
Learning physics-based motion style with nonlinear inverse optimization
ACM SIGGRAPH 2005 Papers
Proceedings of the 2007 ACM SIGGRAPH symposium on Video games
SIMBICON: simple biped locomotion control
ACM SIGGRAPH 2007 papers
Interactive simulation of stylized human locomotion
ACM SIGGRAPH 2008 papers
Competitive coevolution through evolutionary complexification
Journal of Artificial Intelligence Research
Evolution of central pattern generators for bipedal walking in areal-time physics environment
IEEE Transactions on Evolutionary Computation
Interactive Character Animation Using Simulated Physics: A State-of-the-Art Review
Computer Graphics Forum
Hi-index | 0.00 |
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.