Runway Incursion Determination Using Probabilistic Object Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing runway incursion detection systems lack the ability to build probability guarantees and adapt to new environments, leading to potential false negatives or false positives, which can be catastrophic in aircraft landings.
Innovation Solution
A system that integrates object detections over time, filters and predicts future object trajectories using Kalman filters and Gaussian processes, and adapts to new environments to ensure accurate runway incursion probability determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If an end-to-end machine learning model is used for runway incursion detection, then the system can process detections automatically, but the system cannot build probability guarantees and may fail to meet false negative or false positive requirements
Solution Approach 1:
The system segments the detection process into distinct modules: an end-to-end machine learning model for automatic object detection, a tracking module for maintaining object histories, and a probabilistic decision module for incursion determination. This segmentation allows each component to specialize while the probabilistic layer ensures reliability guarantees.
Solution Approach 2:
A probabilistic decision maker acts as an intermediary between the automated detection system and the final incursion determination. This intermediary layer computes false negative and false positive probabilities, enabling the system to meet reliability requirements while maintaining automation.
2Reliability
If the system integrates low probability detections over time to meet probability requirements, then reliability improves, but the system complexity increases
Solution Approach 1:
The system implements feedback loops where detection results are integrated over time, tracking object states across multiple frames, and continuously updating probability estimates. This feedback mechanism accumulates evidence to meet probability requirements while managing complexity through structured state transitions.
3Measurement precision
If the system predicts future object trajectories to distinguish incursion types, then detection accuracy improves, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary trajectory predictions using current object states and detected trends to forecast future positions. This preliminary action enables early classification of incursion types (current vs. future incursion) before the actual event occurs, improving accuracy while maintaining real-time performance.
Data Source
AI summary
A system and method for achieving a high confidence threshold when asserting that the runway is clear of obstacles. A landing aircraft periodically scans runway regions to confirm, track, and propagate trajectories of self-reporting and non-cooperative objects. An incurring object, appearing as a very tiny artifact, is unlikely to be detected in every sensor frame. The system and method propagate the trajectories of the incurring objects to confirm that the objects will clear the runway before the aircraft lands by tracking the objects and using a probabilistic decision maker.