A cricket-inspired Neural Network For FeedForward Compensation and Multisensory Integration

Abstract

A nonlinear feedforward compensator was designed as part of a bioinspired neural network to model sensorimotor integration and control in crickets. Female crickets perform auditory orientation (phonotaxis) towards the male's calling song to find a mate. Crickets also use visual sensing, for example in the optomotor reflex which allows them to maintain a straight trajectory against disturbances. The compensator describe in this paper allows the efficient integration of the phonotaxis and optomotor systems. The design is inspired by the neurophysiological concepts of efferent-copy and corollary discharge, which can be directly intepreted within control theory as feedforward compensation for predictable disturbances. The aim is to predict the reafferent visual stimulus caused by phonotaxis, based on the efferent response, thus filtering out the optical disturbances induced by the phonotactic reflex, while still detecting any external noise. The feedforward compensator design was formulated as an identification problem, drawing data from experiments on a robot performing phonotaxis. The compensator parameters were first derived by trial-and-error, and then optimised using a genetic algorithm. The scheme is implemented in a bioinspired neural network on a robot, and experiments are carried out to compare the behaviour to the cricket.