Model-Based Global Localization for Aerial Robots Using Edge Alignment

Robust state estimation is the core capability for autonomous aerial robots operating in complex environments. Global navigation satellite system and visual odometry/SLAM are popular methods for state estimation. However, there exist scenarios, such as when flying between tall buildings or in the middle of deep canyons, that all these methods fail due to obstructed sky view and high altitude. in this letter, inspired by the fact that offline-generated three-dimensional (3-D) models of cities and natural scenes are readily available, we propose a global localization method for aerial robots by using 3-D models and measurements from a monocular fisheye camera and an inertial measurement unit (IMU). Due to the fact that 3-D models are generated by different cameras at different times, traditional feature-based or direct registration methods usually fail to perform, we therefore propose to use an edge alignment-based method for image-to-model registration under strong changes in lighting conditions and camera characteristics. We additionally aid our model-based localization with electronic image stabilization for better tracking performance, and extended Kalman filter (EKF)-based sensor fusion for closed-loop control. Our method runs onboard an embedded computer in real time. We verify both local accuracy and global consistency of the proposed approach in real-world experiments with comparisons against ground truth. We also show closed-loop control using the proposed method as state feedback.