Taxiway Cross-Track Estimation Using Aircraft Vision and GPS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing aircraft guidance systems face limitations in accuracy and robustness during taxiing due to the limitations of GPS systems, particularly under adverse environmental conditions or intentional/unintentional interference, necessitating supplemental techniques for precise positioning and control.
Innovation Solution
The implementation of a multichannel neural network model integrated with electronic imaging devices such as digital cameras or LIDAR units on aircraft to generate and refine estimates of cross-track error relative to a taxiway centerline, using pre-processed image data to adjust GPS-based location estimates and rudder control for improved positioning and control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS data is used as the primary technique for determining aircraft position, then the system is simple and easy to operate, but the measurement precision and reliability are limited under adverse environmental conditions
Solution Approach 1:
The patent combines multiple independent positioning techniques (GPS, visual inspection, and neural network-based image processing) into a unified aircraft positioning system. The neural network model processes images from electronic imaging devices to generate cross-track error estimates, which are then integrated with GPS data through post-processing to produce a more accurate and reliable position estimate than any single method alone.
Solution Approach 2:
The patent introduces a neural network model as an intermediary component that processes electronic images to generate cross-track error estimates. This intermediary translates visual information into quantitative positioning data that can be combined with GPS measurements, serving as a bridge between optical sensing and navigation system integration.
2Reliability
If supplemental techniques are introduced to improve GPS accuracy, then the reliability improves under adverse conditions, but the device complexity increases
Solution Approach 1:
The neural network model is designed to perform multiple functions: it processes electronic images from various imaging devices, generates cross-track error estimates, and provides data for both positioning and guidance functions. This multi-functionality reduces the need for separate specialized systems, thereby limiting the increase in overall system complexity while improving reliability.
Solution Approach 2:
The system implements feedback through post-processing that combines GPS data with neural network-generated cross-track error estimates. The feedback loop continuously refines the position estimate by comparing multiple independent measurements and adjusting the final output accordingly, thereby improving reliability without requiring completely separate systems.
Data Source
AI summary
Systems, methods, and computer-readable media storing instructions for determining cross-track error of an aircraft on a taxiway are disclosed herein. The disclosed techniques capture electronic images of a portion of the taxiway using cameras or other electronic imaging devices mounted on the aircraft, pre-process the electronic images to generate regularized image data, apply a trained multichannel neural network model to the regularized image data to generate a preliminary estimate of cross-track error relative to the centerline of the taxiway, and post-process the preliminary estimate to generate an estimate of cross-track error of the aircraft. Further embodiments adjust a GPS-based location estimate of the aircraft using the estimate of cross-track error or adjust the heading of the aircraft based upon the estimate of cross-track error.