The Georgia Tech Systems Research lab developed miniature autonomous robotic blimps (GT-MAB) as flying vehicles for indoor experiments that support research on mobile sensor networks, 3D motion control and human-robot interaction (HRI). The GT-MAB is naturally cushioned and offers fun experiences that often encourages physical contact with humans. GT-MAB’s human-friendly physical form is contrasted with drones which typically have a hard exterior and sometimes large, exposed propeller blades.
The motivation for developing this capability is to extend GT-MAB's capability to localize itself without the help from opti-track. Such capability will enable GT-MAB to achieve more complex tasks such as autonomous navigation.
The goal of this project is to deploy and achieve robust visual odometry on current mininature blimp, given the constraints of camera image quality and the platform dynamics characteristics.
Visualized Trajectories
Top view (x-y) of trajectories
Drifts in X, Y, Z Axis
Side view (x-z) of trajectories
Drifts in Scale
