Robust Visual Teach and Repeat Navigation for Unmanned Aerial Vehicles

Vision-based navigation is one of the leading tasks in mobile robotics. It, however, introduces additional challenges in long-term autonomy due to its reliance on stable visual features. As such, visual navigation methods are often sensitive to appearance changes and unreliable in environments with low feature density. We present a teach-and-repeat navigation system for unmanned aerial vehicles (UAVs) equipped with a low-end camera. We use a novel visual place recognition methodology based on high-level CNN features to localize a robot on a previously traversed trajectory and to directly calculate heading corrections for navigation. The developed navigation method is fully vision-based and independent of other sensory information, making it universal and easily transferable. The system has been experimentally verified and evaluated with respect to a state-of-the-art ORB2-TaR navigation system. It showed comparable results in terms of its precision and robustness to environmental changes. In addition, the system was able to safely navigate in environments with low feature density and to reliably solve the wake-up robot problem.