A gait acquisition of a 6-legged robot using immune networks

Strong demands for developing autonomous decentralized systems have arisen as systems have been increasing in their scale and complexity. On the other hand biological systems such as human beings can be said to be the ultimate decentralized system, and are expected to provide feasible ideas in engineering fields. Immune systems work as on-line fault diagnosis systems by constructing self-nonself recognition networks. In this paper the authors try to apply this immunological self-nonself recognition networks to gait acquisition of a 6-legged walking robot as a practical example. The feasibility of the proposed method is confirmed by simulations