An on-board computer system includes a first neural network trained to receive a video stream of a landing approach, runway data, and aircraft state data and identify environmental landmarks corresponding to components of the runway and environmental obstacles that might interfere with autonomous landing. The on-board computer system also includes a second neural network that receives a flight path vector and a flight director corresponding to vectors based on the aircraft energy state and a desired aircraft flight path respectively. The second neural network determines flight control inputs to bring the flight path vector into conformity with the flight director.
Vision based autonomous landing using flight path vector
2020-10-06
Patent
Elektronische Ressource
Englisch
IPC: | B64D Ausrüstung für Flugzeuge , EQUIPMENT FOR FITTING IN OR TO AIRCRAFT / G02B Optische Elemente, Systeme oder Geräte , OPTICAL ELEMENTS, SYSTEMS, OR APPARATUS / G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL |
Autonomous Ship-board Landing using Monocular Vision
British Library Conference Proceedings | 2016
|A vision-based approach for autonomous landing
IEEE | 2017
|BASE | 2022
|Vision Sensor Fusion for Autonomous Landing
AIAA | 2017
|