Evolving gaits for physical robots with the HyperNEAT generative encoding: the benefits of simulation

Author(s): 
Lee S
Yosinski J
Glette K
Lipson H
Clune J
Year: 
2013
Abstract: 

Creating gaits for physical robots is a longstanding and open challenge. Recently, the HyperNEAT generative encoding was shown to automatically discover a variety of gait regularities, producing fast, coordinated gaits, but only for simulated robots. A follow-up study found that HyperNEAT did not produce impressive gaits when they were evolved directly on a physical robot. A simpler encoding hand-tuned to produce regular gaits was tried on the same robot, and outperformed HyperNEAT, but these gaits were first evolved in simulation before being transferred to the robot. In this paper, we tested the hypothesis that the beneficial properties of HyperNEAT would outperform the simpler encoding if HyperNEAT gaits are first evolved in simulation before being transferred to reality. That hypothesis was confirmed, resulting in the fastest gaits yet observed for this robot, including those produced by nine different algorithms from three previous papers describing gait-generating techniques for this robot. This result is important because it confirms that the early promise shown by generative encodings, specifically HyperNEAT, are not limited to simulation, but work on challenging real-world engineering challenges such as evolving gaits for real 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: 
Applications of Evolutionary Computing. 540-549
BibTeX: 

@incollection{
year={2013},
isbn={978-3-642-37191-2},
booktitle={Applications of Evolutionary Computation},
volume={7835},
series={Lecture Notes in Computer Science},
editor={Esparcia-Alcázar, AnnaI.},
doi={10.1007/978-3-642-37192-9_54},
title={Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation},
url={http://dx.doi.org/10.1007/978-3-642-37192-9_54},
publisher={Springer Berlin Heidelberg},
author={Lee, Suchan and Yosinski, Jason and Glette, Kyrre and Lipson, Hod and Clune, Jeff},
pages={540-549},
language={English}
}