Low-cost vision-based 6-DOF MAV localization using IR beacons

The autonomous operation of Micro Aerial Vehicles (MAVs) is a challenging area of research that has received much research interest in recent years. Particularly, accurate localisation of MAVs is an issue, most important during tasks that require high accuracy, such as indoor flight and landing. Many existing solutions are either not accurate, heavy or expensive. We present a low-cost vision-based solution to the localisation problem of MAVs. An on-board infrared tracking sensor with built-in vision processing is used to detect infrared markers and a point-based pose estimation algorithm is implemented to obtain 6 DOF localisation at high rates. The system performance is compared against Inertial Measurement Unit (IMU) and external stereo vision measurements as ground truth. We show that the system produces accurate 6 DOF estimates at low cost and weight in a computationally inexpensive way, and are immediately usable in control implementations. Thus our solution provides a feasible localization solution for MAVs.