Passive Sensor YATO Classification via Feature Vector Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to accurately determine whether an object is moving towards a platform using passive sensors, especially in scenarios where multiple platforms are closely spaced, leading to difficulties in distinguishing which platform is the target.

Innovation Solution

The system employs machine learned classification techniques using feature vectors extracted from data collected by passive sensors, allowing the platform to determine whether an object is moving towards it and whether it is the intended target (YATO) or not (YANTO).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If passive sensors are used to detect incoming objects, then the system avoids active sensor limitations and provides stealth capabilities, but the measurement precision and reliability of determining whether the object is moving toward the platform deteriorates

Engineering Contradiction:

Improvesensor type flexibilityVSAvoidtarget acquisition precision

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system transforms raw sensor data into derived parameters including angular rate, radial velocity, and curvature metrics. These transformed parameters enhance the discriminative power of passive sensor data, enabling reliable determination of whether an object is moving toward the platform despite the inherent limitations of passive detection.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If multiple platforms are closely spaced in formation, then operational coordination and coverage are improved, but the ability to distinguish which platform is the intended target deteriorates due to similar sensor signatures

Engineering Contradiction:

Improvesurveillance coverageVSAvoidplatform identification precision

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system segments the analysis by creating individual feature vectors for each platform based on its unique sensor data. By processing each platform's data separately and comparing the derived parameters (angular rate, radial velocity, curvature), the system can distinguish which platform is the intended target even when platforms are closely spaced in formation.

Inventive Principle:

Principle #1Segmentation

3Device complexity

If traditional classification methods are used for target identification, then system complexity is kept low, but the discriminatory power and accuracy of determining YATO/YANTO status deteriorates

Engineering Contradiction:

Improveclassification system complexityVSAvoidYATO/YANTO classification accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces traditional mechanical or rule-based classification methods with a machine learning classifier. This classifier processes feature vectors containing derived parameters (angular rate, radial velocity, curvature) and automatically determines YATO/YANTO status, significantly improving classification accuracy while maintaining manageable system complexity through software-based solutions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12272117B1System and method for YATO/YANTO classification

Publication Date: 2025.04.08 BAE SYSTEMS INFORMATION ANDELECTRONIC SYSTEMS INTEGRATION INC

AI summary

A passive sensor is used in conjunction with a trained machine learning classifier to make a You Are The One/You Are Not The One (YATO/YANTO) classification or determination as to whether an object, such as a threat, is moving toward a platform. The trained machine learning classifier utilizes a feature vector generated from conditioned temporal data and angular data obtained from passive sensor carried by the platform.