Second Session Visual Navigation for Flying Robots Workshop

In this paper, we describe a system that enables a low-cost quadrocopter coupled with a ground-based laptop to navigate autonomously in previously unknown and GPSdenied environments. Our system consists of three components: a monocular SLAM system, an extended Kalman lter for data fusion and state estimation and a PID controller to generate steering commands. Next to a working system, the main contribution of this paper is a novel, closed-form solution to estimate the absolute scale of the generated visual map from inertial and altitude measurements. In an extensive set of experiments, we demonstrate that our system is able to navigate in previously unknown environments at absolute scale without requiring arti cial markers or external sensors. Furthermore, we show (1) its robustness to temporary loss of visual tracking and signi cant delays in the communication process, (2) the elimination of odometry drift as a result of the visual SLAM system and (3) accurate, scale-aware pose estimation and navigation. Installation This sheet assumes that all preparatory steps from the installation instructions sheet have been done (i.e., a working ROS environment, pre-compiled AR.Drone drivers, etc). In particular, you should have the tum_ardrone package contained in the git repository you only need to build it: $ rosmake tum_ardrone The following is a condensed version of the full documentation available at the ROS wiki pages. An o ine-version is saved in tum_ardrone/doku: