Learning-based risk assessment and motion estimation by vision for unmanned aerial vehicle landing in an unvisited area

Abstract

We proposed a vision-based methodology as an aid for an unmanned aerial vehicle (UAV) landing on a previously unsurveyed area. When the UAV was commanded to perform a landing mission in an unknown airfield, the learning procedure was activated to extract the surface features for learning the obstacle appearance. After the learning process, while hovering the UAV above the potential landing spot, the vision system would be able to predict the roughness value for confidence in a safe landing. Finally, using hybrid optical flow technology for motion estimation, we successfully carried out the UAV landing without a predefined target. Our work combines a well-equipped flight control system with the proposed vision system to yield more practical versatility for UAV applications.

Sequentially trained, shallow neural networks for real-time 3D odometry

“…Currently, motion estimation approaches are more commonly accomplished via deep learning, which has rapidly been adopted for VO applications such as scene tracking or optical flow for unmanned aerial vehicle (UAV) and robotics navigation, [14][15][16] many of which incorporate Fourier-domain or PC methods. 17-21 Supervised 22 and unsupervised 23 learning approaches have been demonstrated to predict the speed, depth, and position of system objects, even with a monocular imaging system.…”