Evolving coordinated quadruped gaits with the HyperNEAT generative encoding

Author(s): 
Clune J
Beckmann BE
Ofria C
Pennock RT
Year: 
2009
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.


Evolving Gaits for Legged Robots: Neural Networks with Geometric Patterns Perform Better

Neural networks evolved to produce gaits for legged robots. The use of the HyperNEAT generative encoding produces geometric patterns (regularities) in the neural wiring of the evolved brains, which improves performance by producing coordinated, regular leg movements.

Evolving artificial neural networks (ANNs) and gaits for robots are difficult, time-consuming tasks for engineers, making them suitable for evolutionary algorithms (aka genetic algorithms). Generative encodings (aka indirect and developmental encodings) perform better than direct encodings by producing neural regularities that result in behavioral regularities.

Evolving Gaits for Legged Robots: Neural Networks with Geometric Patterns Perform Better

Neural networks evolved to produce gaits for legged robots. The use of the HyperNEAT generative encoding produces geometric patterns (regularities) in the neural wiring of the evolved brains, which improves performance by producing coordinated, regular leg movements.

Pub. Info: 
Proceedings of the IEEE Congress on Evolutionary Computation. 2764-2771
BibTeX: 

@inproceedings{Clune:2009:ECQ:1689599.1689966,
author = {Clune, Jeff and Beckmann, Benjamin E. and Ofria, Charles and Pennock, Robert T.},
title = {Evolving Coordinated Quadruped Gaits with the HyperNEAT Generative Encoding},
booktitle = {Proceedings of the Eleventh Conference on Congress on Evolutionary Computation},
series = {CEC'09},
year = {2009},
isbn = {978-1-4244-2958-5},
location = {Trondheim, Norway},
pages = {2764--2771},
numpages = {8},
url = {http://dl.acm.org/citation.cfm?id=1689599.1689966},
acmid = {1689966},
publisher = {IEEE Press},
address = {Piscataway, NJ, USA},
}