A NEURAL-NETWORK FOR PURSUIT TRACKING INSPIRED BY THE FLY VISUAL-SYSTEM

This paper presents an artificial neural network that detects and trac ks an object moving within its field of view. This novel network is in spired by processing functions observed in the fly visual system. The network detects changes in input light intensities, determines motion on both the local and the wide-field levels, and outputs displacement information necessary to control pursuit tracking. Software simulation s demonstrate the current prototype successfully follows a moving targ et within specified radiance and motion constraints. The paper reviews these limiting constraints and suggests future network augmentations to remove them. Despite its current limitations, the existing prototyp e serves as a solid foundation for a future network that promises to p rovide machines with the improved abilities to do high-speed pursuit t racking, interception, and collision avoidance.