Bringing differential GPS to drones

Abstract

I will discuss the use of multiple GPS receivers on drones for orientation estimation. The core challenge is in accurately computing the relative locations between each receiver pair, and translating these measurements into the drone's 3D orientation. Achieving good orientation accuracy requires the relative GPS distances to be accurate to a few centimeters -- a difficult task given that GPS today is only accurate to around 1-4 meters. Moreover, the accuracy needs to be precise even under sharp drone maneuvers, GPS signal blockage, and sudden bouts of missing data. In this talk, I will discuss the design of SafetyNet, an off-the-shelf GPS-only system that addresses these challenges through a series of techniques, culminating in a novel particle filter framework running over multi-GNSS systems (GPS, GLONASS, and SBAS). Results from real flight tests report median orientation accuracies of 2 degrees even under overcast weather conditions.