Evolving coordinated quadruped gaits with the HyperNEAT generative encoding
Authors:
- 1 May 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1089778X,p. 2764-2771
Abstract
Legged robots show promise for complex mobility tasks, such as navigating rough terrain, but the design of their control software is both challenging and laborious. Traditional evolutionary algorithms can produce these controllers, but require manual decomposition or other problem simplification because conventionally-used direct encodings have trouble taking advantage of a problem's regularities and symmetries. Such active intervention is time consuming, limits the range of potential solutions, and requires the user to possess a deep understanding of the problem's structure. This paper demonstrates that HyperNEAT, a new and promising generative encoding for evolving neural networks, can evolve quadruped gaits without an engineer manually decomposing the problem. Analyses suggest that HyperNEAT is successful because it employs a generative encoding that can more easily reuse phenotypic modules. It is also one of the first neuroevolutionary algorithms that exploits a problem's geometric symmetries, which may aid its performance. We compare HyperNEAT to FT-NEAT, a direct encoding control, and find that HyperNEAT is able to evolve impressive quadruped gaits and vastly outperforms FT-NEAT. Comparative analyses reveal that HyperNEAT individuals are more holistically affected by genetic operators, resulting in better leg coordination. Overall, the results suggest that HyperNEAT is a powerful algorithm for evolving control systems for complex, yet regular, devices, such as robots.Keywords
This publication has 19 references indexed in Scilit:
- A Hypercube-Based Encoding for Evolving Large-Scale Neural NetworksArtificial Life, 2009
- Functional Scalability through Generative Representations: The Evolution of Table DesignsEnvironment and Planning B: Planning and Design, 2004
- Generative representations for the automated design of modular physical robotsIEEE Transactions on Robotics and Automation, 2003
- A Taxonomy for Artificial EmbryogenyArtificial Life, 2003
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Evolution of Neural Controllers for Locomotion and Obstacle Avoidance in a Six-legged RobotConnection Science, 1999
- Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insectsIEEE Transactions on Neural Networks, 1998
- Application of evolved locomotion controllers to a hexapod robotRobotics and Autonomous Systems, 1996
- Evolving 3D Morphology and Behavior by CompetitionArtificial Life, 1994
- Evolving Dynamical Neural Networks for Adaptive BehaviorAdaptive Behavior, 1992