VLSI implementation of a double-layer single cell RD-CNN for motion control
Marco Branciforte, Gianluca Giustolisi, V. Nicotra, Gaetano Palumbo · 2002
In this paper a solution for a VLSI implementation of a double-layer single cell reaction-diffusion cellular neural network (RD-CNN) for motion control is presented, and a particular attention is focused on the realisation of both the nonlinearity block and the resistor implemented by means of the same transconductor in order to minimise the tolerance variations. Moreover, two solutions are given to obtain very large time constants due to the very low frequency involved in motion control. The approaches are validated by simulating both of them with ELDO and by comparing the results with a Matlab simulation.