Vision Based Navigation and Tracking with Small UAVs
Beard, Randal W.
MetadataShow full item record
This talk will describe our current work on vision-based autonomous navigation and tracking using small UAVs and provide an overview of two ongoing projects. The first project is relative navigation in GPS degraded environments. There are many applications where GPS is either restricted or denied. We have developed an architecture that uses a relative front end to navigate relative to key frames, and then opportunistically uses GPS measurements and SLAM-style loop closures in a back-end process to provide global context. We will show some recent flight results that demonstrate robustness to GPS failure and degradation. The second project we will discuss is robust tracking of multiple ground-based targets from an airborne platform. We will present a new multiple target tracking algorithm that is based on the random sample consensus (RANSAC) algorithm widely used in computer vision. A recursive version of the RANSAC algorithm will be discussed, and its extension to tracking multiple dynamic objects will be explained. The performance of R-RANSAC will be compared to state of the art target tracking algorithms in the context of problems that are relevant to UAV applications.
- IRIM Seminar Series