Neural Network Based Landing Assist Using Remote Sensing Data

This paper presents the application of computer vision and artificial neural networks for autonomous approach and landing and taxiing for an aircraft. In civil aviation and unmanned aircraft system industry, safety has always been the prime concern. We present a system which uses modern pattern recognition algorithm to aid in the landing of all types of aerial vehicles. The auto-land systems used today in aviation sector utilize a radio waves-based system known as Instrument Landing System (ILS) which has been in operation since decades. Although, it is efficient but might sometime be intermittent and is vulnerable to interference.Moreover, the auto-land system works in conjunction with different devices such as radio altimeter, ILS, Global Positioning System (GPS) and others. But, before reaching the Minimum Decision Altitude (MDA), pilots are expected to have the runway threshold marking, aiming point marking, displacement arrows and other touchdown markings/lights in-sight for landing. For this purpose, use of imaging sensors as an augmentation system for pilots during landing can improve the safety manifolds. Our method uses modern artificial neural networks to learn to recognize and localize important visual references during landing and taxiing useful for pilots by utilizing the satellite imagery dataset from Google Earth Engine (GEE) cloud computing.