We present an open-source system for Micro-Aerial Vehicle (MAV) autonomous navigation from vision-based sensing. Our system focuses on dense mapping, safe local planning, and global trajectory generation, especially when using narrow fieldof-view sensors in very cluttered environments. In addition, details about other necessary parts of the system and special considerations for applications in realworld scenarios are presented. We focus our experiments on evaluating global planning, path smoothing, and local planning methods on real maps made on MAVs in realistic search-and-rescue and industrial inspection scenarios. We also perform thousands of simulations in cluttered synthetic environments, and finally validate the complete system in real-world experiments. K E Y W O R D S aerial robotics, GPS-denied operation, mapping, obstacle avoidance, planning 1 | INTRODUCTION Autonomous navigation from on-board sensing is essential for Micro-Aerial Vehicles (MAVs) in many applications. In this study, we specifically target applications where MAVs can assist human operators in difficult tasks, such as search-and-rescue (S&R) and industrial inspection appli-Helen Oleynikova: work performed while at ETH, now with Microsoft. Zachary Taylor: work performed while at ETH, now with Oculus.

Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based localization have focused on the description of local surface geometry, usually using pointclouds as the underlying representation. We propose a system for geometrybased localization that extracts features directly from an implicit surface representation: the Signed Distance Function (SDF). The SDF varies continuously through space, which allows the proposed system to extract and utilize features describing both surfaces and free-space. Through evaluations on public datasets, we demonstrate the flexibility of this approach, and show an increase in localization performance over stateof-the-art handcrafted surfaces-only descriptors. We achieve an average improvement of 12% on an RGB-D dataset and 18% on a LiDAR-based dataset. Finally, we demonstrate our system for localizing a LiDAR-equipped Micro Aerial Vehicle (MAV) within a previously built map of a search and rescue training ground.

No abstract

No abstract