Evolutionary ordered neural network and its application to robot manipulator control
Jong-Hwan Kim, Chi‐Ho Lee · 2002
This paper proposes an evolutionary design of a neural network architecture, with a one-dimensional linked list encoding scheme. In this scheme, neurons are arranged in a one-dimensional array, and the order informations of neurons play important roles in genetic operation. Due to one-dimensional structure, encoding from neural network architecture to genotype becomes easy, and genetic operation can be easily applied. To avoid the permutation problem, we choose evolutionary programming (EP) rather than a genetic algorithm (GA), i.e., we apply mutation operators only in order to generate offspring. The proposed scheme is applied to a 2-link robot manipulator to control the position of the end effector. Satisfactory simulation results with simple neural network architecture are shown to validate the proposed algorithm.