Emergent Intelligent Properties of Evolving and Adapting Snake-like Robot’s Locomotion

Abstract

Inspired by the efficient method of locomotion of the rattlesnake Crotalus cerastes, the objective of this work is to investigate the emergent properties of the automatically designed through genetic programming (GP) fastest possible (sidewinding), robust and adaptive locomotion gaits of simulated snake-like robot (Snakebot). Considering the notion of “emergent intelligence” as the ability of Snakebot to achieve its goals (of moving fast) without the need to be explicitly taught about how to do so, we present the empirical results on the emergence of sidewinding locomotion as fastest locomotion of the Snakebot. The emergent properties of evolved robust sidewinding gaits featuring desired velocity characteristics of Snakebot in challenging environment are discussed. The ability of Snakebot to adapt to partial damage by gradually improving its velocity characteristics, and the emergent properties of obtained adaptive gaits are elaborated. Concluding on the practical implications of the analogy between the emergent properties of the robust and the adaptive locomotion gaits, this work could be viewed as a step towards building real Snakebots, which are able to perform robustly in difficult environment.