Learning Walking Patterns for Kinematically Complex Robots Using Evolution Strategies

Malte Langosz; Mark Edgington; Jan Hendrik Metzen; José de Gea Fernández; Yohannes Kassahun; Frank Kirchner

In: G. Rudolph; T. Jansen; S.M. Lucas; et al. (Hrsg.). 10th International Conference on Parallel Problem Solving from Nature. International Conference on Parallel Problem Solving From Nature (PPSN-2008), September 13-17, Dortmund, Germany, Pages 1091-1100, Lecture Notes in Computer Science (LNCS), Vol. 5199, Springer, 2008.


Manually developing walking patterns for kinematically complex robots can be a challenging and time-consuming task. In order to automate this design process, a learning system that generates, tests, and optimizes different walking patterns is needed, as well as the ability to accurately simulate a robot and its environment. In this work, we describe a learning system that uses the CMA-ES method from evolutionary computation to learn walking patterns for a complex legged robot. The robot’s limbs are controlled using parametrized distorted sine waves, and the evolutionary algorithm optimizes the parameters of these waveforms, testing the walking patterns in a physical simulation. The best solutions evolved by this system has been transferred to and tested on a real robot, and has resulted in a gait that is superior to those previously designed by a human designer.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence