An evolutionary design scheme of neural oscillatory network for generation of biped walking patterns

This paper presents a new scheme for the design of a neural oscillatory network which can be used to generate the desired biped walking pattern trajectories. The scheme is based on evolutionary computation concepts and can solve all of the connection weights in the network according to the desired walking pattern parameters. It also has the advantages in the simplicity, flexibility and high calculation speed. With the results of simulations the scheme proved to be effective. This research also established a foundation for the research on expressing various human walking patterns in mathematical models.