ABSTRACT
Almost a hundred years ago, before we had foreseen a world where cars drive themselves in traffic, the idea of a vehicle that could be both driven and flown had already taken hold of the public imagination. However compelling the imagery facilitated by the media and science fiction, we are nowhere close to an aerial analog of the self-driving car. This could be because we are unable to directly manipulate gravitational forces in the way we manipulate electromagnetic forces. Commonplace flying cars might be some time in coming, but, we might still ask what would be possible if we could realize “personal aviation”. We could ask how such vehicles could operate safely and what steps we need to take to hasten their feasibility.
Because flying cars would almost certainly have to be autonomous to be operable by non-pilots, many of the building blocks needed have immediate relevance in the agenda for developing autonomous drones, as well as, safety aids for pilots of the large number of aircraft that must fly at low elevation and land at unprepared sites.
In my talk, I will discuss results from recent work with autonomous aircraft operating in unstructured environments focused on three technical goals: fly safe, land safe, and, fly without GPS. I will show how presence of a human onboard an autonomous flying vehicle can improve both performance and reliability. I also will show results from a new class of methods that simultaneously produce dense reconstruction and low-drift 6DOF pose estimation in real time, with application to various scales of aircraft.