UNMANNED AERIAL SYSTEM TRACKING IN URBAN CANYON ENVIRONMENTS USING EXTERNAL VISION

Unmanned aerial systems (UASs) are at the intersection of robotics and aerospace re-
search. Their rise in popularity spurred the growth of interest in urban air mobility (UAM)
across the world. UAM promises the next generation of transportation and logistics to be
handled by UASs that operate closer to where people live and work. Therefore safety and
security of UASs are paramount for UAM operations. Monitoring UAS traffic is especially
challenging in urban canyon environments where traditional radar systems used for air traffic
control (ATC) are limited by their line of sight (LOS).
This thesis explores the design and preliminary results of a target tracking system for
urban canyon environments based on a network of camera nodes. A network of stationary
camera nodes can be deployed on a large scale to overcome the LOS issue in radar systems
as well as cover considerable urban airspace. A camera node consists of a camera sensor, a
beacon, a real-time kinematic (RTK) global navigation satellite system (GNSS) receiver, and
an edge computing device. By leveraging high-precision RTK GNSS receivers and beacons,
an automatic calibration process of the proposed system is devised to simplify the time-
consuming and tedious calibration of a traditional camera network present in motion capture
(MoCap) systems. Through edge computing devices, the tracking system combines machine
learning techniques and motion detection as hybrid measurement modes for potential targets.
Then particle filters are used to estimate target tracks in real-time within the airspace from
measurements obtained by the camera nodes. Simulation in a 40m×40m×15m tracking
volume shows an estimation error within 0.5m when tracking multiple targets. Moreover,
a scaled down physical test with off-the-shelf camera hardware is able to achieve tracking
error within 0.3m on a micro-UAS in real time.