Graz Griffins’ Solution to the European Robotics Challenges 2014

Kurzfassung

An important focus of current research in the field of Micro Aerial Vehicles (MAVs) is to increase the safety of their operation in general unstructured environments. An example of a real-world application is visual inspection of industry infrastructure, which can be greatly facilitated by autonomous multicopters. Currently, active research is pursued to improve real-time vision-based localization and navigation algorithms. In this context, the goal of Challenge 3 of the EuRoC 20144 Simulation Contest was a fair comparison of algorithms in a realistic setup which also respected the computational restrictions onboard an MAV. The evaluation separated the problem of autonomous navigation into four tasks: visual-inertial localization, visual-inertial mapping, control and state estimation, and trajectory planning. This EuRoC challenge attracted the participation of 21 important European institutions. This paper describes the solution of our team, the Graz Griffins, to all tasks of the challenge and presents the achieved results.