Visual Measurement in Simulation Environment for Vision-Based UAV Autonomous Aerial Refueling

Abstract

Autonomous aerial refueling (AAR) is an important capability of unmanned aerial vehicles (UAVs) for further applications in both military and civilian domains. This paper focuses on the description and comparison of visual measurement strategies in the simulation environment of AAR of UAVs. The visual measurement methods are employed for pose estimation between tanker and UAV receiver aircrafts. Within this effort, methods and techniques for marker detection, pose estimation, and visualization of aerial refueling in virtual reality have been designed and implemented. Series of comparative experiments indicate the preference of various visual measurement approaches in our work. Boom and stationkeeping controllers are designed to ensure system stability when wind turbulence is induced. Furthermore, the hardware-in-loop simulation platform is built to demonstrate the feasibility and effectiveness of the proposed scenarios in actual conditions. The visual attention mechanism is adopted in the preprocessing for the images of virtual scene to remove potential noises. The achieved results make excellent performances of our proposed scheme during the docking maneuver in AAR.