Constructing a small humanoid walking robot as a platform for the genetic evolution of walking

Abstract

Walking robots form the next challenge in the eld of autonomous robots. This paper describes the construction of a fully autonomous humanoid walking robot as a platform for machine learning algorithms like e.g. Genetic Programming. Built from o-the-shelf components, the described humanoids are cheap, robust and easy to program, which make them an ideal test platform for several experimental approaches in machine learning, sensor fusion, or adaptive control. In addition to these research related topics, the walking robots are an ideal tool for educational purposes.