The Taub Faculty of Computer Science Events and Talks

Quad-Copters are versatile unmanned aircraft that are used for a myriad of tasks from manual aerial photography to autonomous surveillance. After their initial success in outdoors scenarios, indoor autonomous activity has recently been getting attention in research. Unlike the outdoor environment, which offers cheap and easy localization in the form of GPS, and usually lacks meaningful obstacles, indoor autonomous flight lacks a common means of localization and the tight spaces are fraught with every day objects. Presented here is research in theoretical and experimental work that has been done in indoor monocular vision based localization. Unlike most research in indoor localization and mapping, which uses either a stereo rig, or a depth sensing RGBD camera, this research uses a single grayscale camera to localize the craft and reconstruct the 3D environment from motion. The work takes a published work of integrating information about the outdoor environment into a state of the art Bundle Adjustment algorithm, and extends this approach to the indoor scene. Also described is the work on real-time localization on an embedded processor, for fully autonomous operation.