Vision-Based Landing of Fixed-Wing Miniature Air Vehicles

Abstract

This paper outlines a method for using vision-based feedback to accurately land a MAV on a visually identifiable target of approximately known location. The method presented is robust to wind, capable of handling both stationary and moving targets, and capable of correcting for camera misalignment, state estimation biases, and parameter estimation biases. Landing results from actual flight tests are presented which demonstrate the effectiveness of the proposed method.

Chaotic biogeography-based optimization approach to target detection in UAV surveillance

“…Advancements in digital camera technology have made significant performances in recent years with effective image processing software. Much attention has been directed forward vision-based methods for their usefulness in both commercial and military applications [7][8][9][10][11]. Vision strategy provides a better idea for safer and swifter UAV navigation [12].…”

Localization and perching maneuver tracking for a morphing UAV

“…Methods to extract meaningful scene information for automated landings have also been shown for fixed-wing aircraft. In [3] it was assumed that the landing site was highly structured, while in [4] and [5] a simple visual target was used. Accurate determination of a landing site, whether prepared or not, is an important aspect for safe, automated UAV landings.…”

“…(16)-(17) the subscript denotes the time index and the superscript denotes the model index, where j ∈ {1, 2, ..., m} for the set of models defined by(4).…”

Vision-Based Landing of a Simulated Unmanned Aerial Vehicle with Fast Reinforcement Learning

“…In addition, a reinforcement learning module using Q-learning was used to learn how to produce the optimal shape at every flight condition. Barber et al [4] proposed vision-based landing for small fixed-wing UAVs, where a visual marker is used to generate the roll and pitch commands to the flight controller. Bourquardez and Chaumette [5] introduced a visual servoing algorithm to control an airplane during landing.…”