Vision-Based Autonomous Aerial Refueling

Abstract

Unmanned aerial vehicles(UAV) are playing more and more important roles in both the military and civilian domains.However,the drawbacks of short duration and low payload capacity significantly limit UAV applications which could involve complex,long-term missions.Autonomous aerial refueling(AAR) can effectively resolve some of these limitations by extending the UAV's payload and range.Computer vision can support for autonomous aerial refueling.The paper reviews two typical vision-based boom-and-receptacle refueling(BRR) approaches and then a switching scheme based stereovision(SSS) that combines the advantages of these two approaches and avoids the disadvantages.The system design and key vision-based BRR solutions techniques are described.