Vehicle Interaction Machine Learning Model for Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air traffic control systems and collision avoidance systems, such as TCAS, lack advanced warning mechanisms for potential loss of separation between vehicles, particularly as air traffic and vehicle congestion increase, posing risks of mid-air collisions and vehicle collisions.
Innovation Solution
A system and method utilizing a vehicle interaction machine learning model to detect real-time anomalies by analyzing historical and real-time data, predicting future interactions, and transmitting alerts to prevent collisions, applicable to both aircraft and other vehicles like autonomous cars and ships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional ATC and TCAS systems are used to manage aircraft separation, then basic collision avoidance is achieved, but advanced warning for potential loss of separation is not provided
Solution Approach 1:
The system performs preliminary analysis of historical trajectory data and real-time encounter models to identify potential loss of separation events before they occur. The machine learning model predicts future vehicle interactions and generates advance warnings, allowing operators to take preventive actions before actual collision risks materialize.
Solution Approach 2:
The system creates a protective information layer by continuously monitoring encounter models and predicting potential safety events. This advance warning mechanism cushions against future collisions by providing early alerts and recommended mitigation actions, allowing the system to buffer against potential loss of separation events.
2Productivity
If more vehicles are accommodated in congested airspace, then air traffic capacity increases, but risk of mid-air collisions increases
Solution Approach 1:
The system implements continuous feedback by monitoring real-time vehicle positions, evaluating encounter models, and comparing actual trajectories against predicted safe separation patterns. When potential loss of separation is detected, the system provides immediate feedback through alerts and recommended mitigation actions to operators or autonomous control systems.
Solution Approach 2:
The machine learning model acts as an intermediary between raw trajectory data and collision avoidance decisions. It processes historical and real-time data to generate encounter models that mediate between increased traffic density and safety requirements, identifying potential conflicts before they become actual collision risks.
3Device complexity
If manual ATC monitoring is used to detect loss of separation, then system complexity is low, but detection speed and accuracy decrease
Solution Approach 1:
The system performs self-service by automatically evaluating real-time data against trained encounter models to detect potential loss of separation events. The machine learning model autonomously identifies anomalies and generates alerts without requiring constant manual ATC intervention, freeing operators to focus on higher-level decision-making while maintaining high detection accuracy.
Data Source
AI summary
Disclosed are methods, systems, and non-transitory computer-readable mediums for detecting and avoiding loss of separation between vehicles. A first method may include training a vehicle interaction machine learning model to predict future vehicle interactions based on identified vehicle interactions and an identified risk of encounter between two or more selected vehicles. A second method may include obtaining real-time data associated with a vehicle-of-interest; evaluating the real-time data associated with the vehicle-of-interest to form encounter models; monitoring the encounter models with a model access function of the vehicle interaction machine learning model to detect real-time anomalies; and in response to detecting a real-time anomaly, transmitting an alert. A third method may include obtaining trajectory information; analyzing the trajectory information to determine whether a trajectory is a new trajectory type or whether the trajectory is a member of a new interaction; updating training data for the vehicle interaction machine learning model.