Evolution of a yoga performing humanoid

Evolutionary computational methods are extensively being tested in both high and low-level robot motion planning. Unlike other types of robots, humanoids are complex in both construction and operation due to their myriad degrees of freedom and the difficulty of balancing on one or more limbs. This paper presents the concept, methodology and results of a series of experiments conducted with the aim of building asymmetric motion controllers that present a new level of challenge due to the higher number of parameters that need to be optimized and the necessity of balancing the humanoid on a single limb, compared to symmetric motions.