CNN-based Ego-Motion Estimation for Fast MAV Maneuvers
This work provides improved ego-motion estimation for Micro Air Vehicles (MAVs) undergoing fast maneuvers, which is crucial for their autonomous navigation and control.
This paper addresses the challenge of ego-motion estimation for MAVs during fast maneuvers, which suffer from large visual disparity and motion blur. The authors developed CNN-based models that predict relative pose from monocular images, achieving better accuracy than existing networks and traditional methods, with self-supervised learning outperforming supervised learning.
In the field of visual ego-motion estimation for Micro Air Vehicles (MAVs), fast maneuvers stay challenging mainly because of the big visual disparity and motion blur. In the pursuit of higher robustness, we study convolutional neural networks (CNNs) that predict the relative pose between subsequent images from a fast-moving monocular camera facing a planar scene. Aided by the Inertial Measurement Unit (IMU), we mainly focus on translational motion. The networks we study have similar small model sizes (around 1.35MB) and high inference speeds (around 10 milliseconds on a mobile GPU). Images for training and testing have realistic motion blur. Departing from a network framework that iteratively warps the first image to match the second with cascaded network blocks, we study different network architectures and training strategies. Simulated datasets and a self-collected MAV flight dataset are used for evaluation. The proposed setup shows better accuracy over existing networks and traditional feature-point-based methods during fast maneuvers. Moreover, self-supervised learning outperforms supervised learning. Videos and open-sourced code are available at https://github.com/tudelft/PoseNet_Planar