Experimental Comparison of Fiducial Markers for Pose Estimation

Robust localization is critical for the navigation and control of mobile robots. Global Navigation Satellite Systems (GNSS), Visual Inertial Odometry (VIO), and Simultaneous Localization and Mapping (SLAM) offer different methods for achieving this goal. In some cases however, these methods may not be available or provide high enough accuracy. In such cases, these methods may be augmented or replaced with fiducial marker pose estimation. Fiducial markers can increase the accuracy and robustness of a localization system by providing an easily recognizable feature with embedded fault detection. In this project, we picked four open-source packages (ARTag, AprilTag, ArUco, and STag) that represent the state-of-the-art and most widely used packages and compared them in terms of their accuracy, detection rate and computational cost. Different marker configurations, including single markers, planar and non-planar bundles and multi-sized marker bundles were considered as well as simulated noise from shadows and motion blur. Finally, within this project, we developed and released the ROS package for STag.

A Marsupial Robotic System for Surveying and Inspection of Freshwater Ecosystems

In this project on autonomous infrastructure inspection, we explored the idea of using a heterogeneous marsupial robotic system for freshwater ecosystem inspection. The system was comprised of an Autonomous Surface Vehicle and an Unmanned Aerial Vehicle. Taking advantage of each platform's individual strengths, the system was able to complete long missions and reach remote locations while also being able to generate detailed maps and inspections of points of interest. The system was thoroughly tested during a six month period in a number of field deployments.

R.A.D.A.R (Rapid Assessment for Dyslexia & Abnormalities in Reading)

The goal of the Emmetrolexia group was to create a fast and objective screening method for dyslexia and learning difficulties. My role, as a Research Engineer, was to design and develop an Eye-Tracker that would be used to track the reading patterns of children. My work included the hardware design and component selection for the tracker as well as developing the software to track the subjects eyes, estimate the gaze points and calculate the characteristics of the fixations and saccadic movements. I was also involved in the initial data collection and analysis that was used to create a database and assess our method.