Evolving Robot’s Behavior by Using CNNs

Abstract

This paper deals with a new kind of robotic control, based on Chua’s nonlinear circuit called Cellular Neural Network (CNN). A CNN is a net of coupled circuits, connected in a grid structure, which inherits its features and properties from the well known Artificial Neural Network and Cellular Automata. It has been demonstrated that CNNs are able of universal computation, many cognitive processes such as pattern recognition, features extraction, image processing, and mathematical simulations of nonlinear equations such as Navier-Stokes equations, reaction-diffusion equations, and so on. Using an approach like Evolutionary Robotics, we evolved, instead of Neural Networks, CNNs by using Genetic Algorithms (GAs), for controlling the behavior of an hexapod robot in a simulated environment. We developed a Java3D software in which physical simulations are carried on by using different kind of robots. In this program, a module for evolving the robot’s behavior by GAs has been implemented. Furthermore, many advanced sensors and actuators complete the evolution of the robot’s behavior. The evolved behavior of our robots is very similar to that of real insects, and we analyzed the pathways these agents perform in the simulated environment.