Camera-GPS-IMU sensor fusion for autonomous flying

GPS-IMU based sensor fusion is widely used for autonomous flying, which yet suffers from the inaccuracy and drift of the GPS signal and also the failure with the loss of GPS (e.g., indoor flying). To circumvent this issue, in this paper, we propose a new framework for camera-GPS-IMU sensor fusion, which, by fusing monocular camera information with that from GPS and IMU, can improve the accuracy and robustness of the autonomous flying. For camera and GPS-IMU calibration, a new Kalman filter is also proposed, which runs in parallel with the state estimation EKF and also utilize multiple key frames generated from the camera information. An autonomous flying experiment is performed to validate the theory.