Towards Autonomous UAV Landing Based on Infrared Beacons and Particle Filtering

摘要

Autonomous fixed-wing UAV landing based on differential GPS is now amainstream providing reliable and precise landing. But the task still remainschallenging when GPS availability is limited like for military UAVs. We discussa solution of this problem based on computer vision and dot markings alongstationary or makeshift runway. We focus our attempts on using infrared beaconsalong with narrow-band filter as promising way to mark any makeshift runway andutilize particle filtering to fuse both IMU and visual data. We believe thatunlike many other vision-based methods this solution is capable of tracking UAVposition up to engines stop. System overview, algorithm description and it'sevaluation on synthesized sequence along real recorded trajectory is presented.