A robust light invariant vision system for aircraft refueling

Abstract

The application of robotic technologies to aircraft servicing is addressed, specifically the concept of semi-autonomous ground-based robotic refueling. Recognition of the refueling port in realistic lighting conditions was mandatory. A brightness invariant port recognition system (BIPRS) which relies on edge detection, line merging, loop formation, and knowledge-driven recognition was developed and experimentally validated. The BIPRS identified the simulated refueling port in different lighting conditions and was invariant to port orientation and size. BIPRS development is discussed, and highlights of experimental validation are presented. The pattern recognition portion of the refueling task is clearly feasible with current technology.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>