Optimal Guidance Design for UAV Visual Target Tracking in an Urban Environment

摘要: Abstract This paper addresses a vision-based air-to-ground target tracking problem of an unmanned aerial vehicle. A navigation filter is designed based on extended Kalman to simultaneosly localize moving and own-ship UAV by fusing measurements other onboard sensors. Particularly, it suggested utilize sparse optical flow estimation aid the inertial when GPS signals are inaccessible. guidance law aims at making pursue target's horizontal position while vertically avoiding obstacles whose global positions known. In order achieve this purpose, high accuracy in both self localizations required. Since performance significantly depends camera motion relative objects interest, proposes stochastically optimized which attains obstacle avoidance maximizing accuracy. For real-time applicability, one-step-ahead optimization technique applied derive suboptimal solution. Simulation flight test results presented demonstrate advantage using optimal policy instead nominal linear guidance.