GPS emulation via visual-inertial odometry for inspection drones

This work tested the applicability of a navigation system based on cameras and inertial sensors for a quadrotor UAV, motivated by the desire to expand its operational envelope to regions with low GPS signal reception. A standalone navigation module composed of a stereo camera pair, an IMU, synchronization electronics and a SoC computational board was developed and provided with OKVIS, a recent open-source VIO (Visual-Inertial Odometry) algorithm. In order to quantitatively assess its performance, an indoors dataset was recorded in a controlled environment, with precise ground-truth from a motion capture system. The system was integrated with a quadrotor UAV, functioning as an additional GPS sensor from the perspective of the onboard autopilot. For this end, the VIO trajectory data was georeferenced using information from the onboard GPS receiver, as well as from the orientation estimator embedded in the IMU. To the best of our knowledge, our system is the first to follow this integration approach, this being one of the main contributions of this work. Having validated the system with handheld testing, flight tests were performed. We show, qualitatively, that our system effectively yields improved trajectory estimates under low GPS signal reception.