Autonomous VTOL software for Intelligent and Adaptive Noncooperative landing (AVIAN)

We propose AVIAN, a system designed with the purpose of helping VTOL devices analyze noncooperative naval environments to make predictions and decisions regarding autonomous landing. AVIAN combines onboard camera, IMU, and optional LIDAR sensor data to model the environment for intelligent analysis of potential landing sites. This analysis uses literature-backed computer vision algorithms to locate potential landing sites. Landing sites are analyzed in a ōcoarse to fineö manner, meaning poor-quality sites are swiftly pruned out of consideration. This approach allows for higher- quality sites to be analyzed with computationally expensive operations that would otherwise lag the decision making process. AVIAN uses this site analysis information to either autonomously select a landing site or intelligently curate potential landing sites to a human operator. Upon selecting a site, AVIAN uses modern Simultaneous Localization and Mapping (SLAM) algorithm implementation (ORB-SLAM3) and its own calculated site analysis together to track the VTOLÆs position while autonomously moving towards the selected landing position. Upon ensuring the high quality of a landing site, AVIAN works to safely land, using IMU and camera data to ensure a proper landing. AVIAN then allows for the operator to have the VTOL safely fly back to its starting position.