In comparison to other civilian applications, search an rescue requires quite demanding capabilities. The objective of this research line is to create MAVs that are able to act without relying on external computing power, that are fast and easy to deploy and that can deliver information to the operator in real-time. We started working on this direction when our team, the Graz Griffins, was selected by the organizers to take part in the [website] 2016 DJI Developer Challenge, only 25 out of 140 teams made the cut. The organization provided us with a fully equipped DJI Matrice 100 MAV: aerial platform, onboard computer - DJI Manifold, obstacle sensing system - DJI Guidance and a gimbaled camera - DJI Zenmuse X3.
This video summarizes the capabilities of the Graz Griffins' fully-autonomous M100 quadcopter at the 2016 DJI Developer Challenge Finals, held the 27-28 of August, 2016. Our MAV is able to fly over an area, for instance a 50x50m, create a 3D reconstruction of it and obtain a geo-referenced obstacle map; that it can then use to perform obstacle-free navigation. We are currently starting the mission from a tablet connected to the quadcopter's remote control and receiving back the onboard image, the mission status and other telemetry.
Graz Griffins Team:
Jesus Pestana Puerta
We are currently using our developments for the 2016 DJI Developer Challenge to research on civilian applications. Our current efforts includes:
Landing on moving platforms
Exploring the potential of our current solution, so that we can set objectives to work on in the future
Obtaining more information in real-time and increasing our user interface for the operators to be informed and be able to to take informed decisions during mission execution
Looking for project partners to develop exciting new civilian applications by combining our current aerial robot prototype and the core knowledge of our institute in 3D Reconstruction, Segmentation and other Computer Vision related topics.