The main contribution of this paper is a high frequency, low-complexity,on-board visual-inertial odometry system for quadrotor micro air vehicles. Thesystem consists of an extended Kalman filter (EKF) based state estimationalgorithm that fuses information from a low cost MEMS inertial measurement unitacquired at 200Hz and VGA resolution images from a monocular camera at 50Hz.The dynamic model describing the quadrotor motion is employed in the estimationalgorithm as a third source of information. Visual information is incorporatedinto the EKF by enforcing the epipolar constraint on features tracked betweenimage pairs, avoiding the need to explicitly estimate the location of thetracked environmental features. Combined use of the dynamic model and epipolarconstraints makes it possible to obtain drift free velocity and attitudeestimates in the presence of both accelerometer and gyroscope biases. Astrategy to deal with the unobservability that arises when the quadrotor is inhover is also provided. Experimental data from a real-time implementation ofthe system on a 50 gram embedded computer are presented in addition to thesimulations to demonstrate the efficacy of the proposed system.
展开▼
