UAV navigation in GPS-denied environment using particle filtered RVL

摘要

Unmanned aerial vehicles have become widespread in today's world and are used for applications ranging fromreal estate marketing and bridge inspection to defense and military applications. These applications have incommon some form of autonomous navigation that requires a good localization capability at all time. Most UAVare using a combination of global navigation satellite systems (GNSS) and inertial measurement unit (IMU) toperform this task. Unfortunately, GNSS are subject to signal unavailability and all sorts of interference impedingon the ability of the UAV to self-localize. In this paper, we propose a new algorithm to perform localization inGNSS-denied environments by using a relative visual localization technique. We developed a new measure basedon the use of local feature points extracted with ORB to estimate the likelihood of a previously captured imageto have been taken in a position close to the current UAV location. The measure is embedded in a particle filterin which IMU data is used in order to reduce the number of images we need to analyze to perform localization.The resulting method have shown significant improvement in both accuracy and execution time in comparisonto previous approaches.