Noname manuscript No. (will be inserted by the editor) River Mapping from a Flying Robot: State Estimation, River Detection, and Obstacle Mapping

Citations in the corpus

• A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones (2018, neutral): “, GPS [15]) or onboard sensors (e.”
• DroNet: Learning to Fly by Driving (2018, methodology): “A UAV operating outdoor is usually provided with GPS, range, and visual sensors to estimate the system state, infer the presence of obstacles, and perform path planning [1], [4].”
• Visual-lidar odometry and mapping: low-drift, robust, and fast (2015, methodology): “In comparison to [14], [15], our method differs in that it tightly couples a camera and a lidar such that only one camera is needed for motion recovery.”
• LOAM: Lidar Odometry and Mapping in Real-time (2014, methodology): “For example, the lidar cloud can be registered by state estimation from visual odometry integrated with an IMU [15].”
• Low-drift and real-time lidar odometry and mapping (2017, methodology): “For example, the lidar cloud can be registered by state estimation from visual odometry integrated with an IMU (Scherer et al. 2012).”