Vision-only aircraft flight control methods and test results

An unmanned aerial vehicle usually carries an array of sensors whose output is used to estimate the vehicle's attitude, velocity and position. This paper details the development of control strategies for a glider, which is capable of flying from a starting point to a ending location using only a single vision sensor. Using vision to control an aircraft presents a few unique challenges. Firstly, absolute state measurements are not available from an image. Secondly, in order to maintain adequate control of the aircraft, the images must be processed at a fast rate. The image processor utilizes an integral image representation and a rejective cascade filter to find and classify simple features in the images, reducing the image to the most probable pixel location of the objective. The navigation algorithms use an extended Kalman filter to generate state estimates based on measurements obtained from the imagery. The algorithms are tested through the flight testing of a glider instrumented only with a single camera.