Onboard Runway Incursion Detection Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current airport runway incursion detection systems rely heavily on human assessment and infrastructure-dependent technologies like ADS-B, which are prone to errors and limited in coverage, posing a high-risk situation for aircraft during landing.
Innovation Solution
An onboard system that uses multiple data sources, including visual sensing and ADS-B, to automatically detect and report runway incursions, employing sensor fusion and machine learning to enhance situational awareness and decision-making capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ADS-B system is used for runway incursion detection, then real-time position data can be obtained, but the system is prone to erroneous reporting and has limited coverage
Solution Approach 1:
The patent combines multiple detection sources including ADS-B, visual sensing systems, and ground radar into a unified detection framework. This multi-source fusion approach allows cross-validation of data, reducing reliance on any single erroneous source while maintaining real-time detection capabilities.
Solution Approach 2:
The system introduces an intermediary verification layer that processes and validates ADS-B data before final detection decisions. This intermediary layer filters erroneous reports by comparing ADS-B position data with visual sensing results and predicted object tracks, thereby maintaining real-time detection while improving reliability.
2Loss of information
If human assessment is used for runway incursion detection, then situational understanding can be achieved, but the process is slow and cannot keep up with high speeds
Solution Approach 1:
The patent replaces human mechanical assessment processes with automated computational systems. Machine learning models and algorithms automatically analyze sensor data, track objects, and detect incursions, eliminating the time delay inherent in human visual assessment while preserving comprehensive situational awareness through multi-parameter analysis.
Solution Approach 2:
The system performs preliminary tracking and classification of objects before final incursion detection. By continuously predicting object tracks and pre-processing sensor data, the system prepares situational awareness information in advance, enabling rapid detection decisions without the time penalty of real-time human assessment.
3Area of stationary object
If ground radar-based detection is used, then detection coverage can be improved, but the system is infrastructure-dependent and not available at all airports
Solution Approach 1:
The patent designs a universal detection system that can operate with multiple sensor types including onboard visual sensing, ADS-B receivers, and optional ground radar. This multi-functional architecture allows the system to adapt to different airport environments by utilizing available infrastructure while maintaining core detection capabilities through onboard sensors that do not require external infrastructure.
Solution Approach 2:
The system dynamically configures its sensor utilization based on available infrastructure and environmental conditions. When ground radar is available, it enhances detection coverage; when not available, the system seamlessly transitions to relying on onboard visual sensing and ADS-B data, maintaining adaptability across diverse airport environments without requiring permanent infrastructure installation.
4Measurement precision
If multiple detection sources are used, then detection accuracy can be improved, but the system complexity increases
Solution Approach 1:
The patent segments the detection system into modular functional components: data acquisition modules for different sensor types, processing modules for each sensor type, fusion modules for combining data, and decision modules for incursion detection. This segmentation allows each component to be optimized independently while maintaining overall system accuracy, reducing the complexity burden of multi-source integration.
Data Source
AI summary
An on-board system and method for leveraging multi-modal means of detecting runway incursions to increase aircraft safety, and to provide a necessary enabler for both reduced crew operations and autonomous flights in the future. The system and method detect incursions using visual perception for all types of vehicles and objects that may incur, and an ADS-B for self-reporting vehicles. The system and method fuse prior known information (such as ownship pose and map data) with detections from sensors and other sources. The system actively tracks detections and computes the current and predicted future states to decide if there is an on-going incursion on the runway. The system reports the runway state to the pilots and/or autonomous receivers.