AFRL. Technology Directorates AFRL

Transcription

1 Sensors Directorate and ATR Overview for Integrated Fusion, Performance Prediction, and Sensor Management for ATE MURI 21 July 2006 Lori Westerkamp Sensor ATR Technology Division Sensors Directorate Air Force Research Laboratory

2 AFRL Technology Directorates AFRL MGen T. Bowlds Staff XP Air Vehicles Space Vehicles Information Munitions Directed Energy AFOSR Materials & Manufacturing Sensors Propulsion Human Effectiveness 2

3 Sensors Directorate Our Mission To lead the discovery, development, and integration of affordable sensor and countermeasure technologies for our warfighters. Our Vision Robust sensors and adaptive countermeasures that guarantee complete freedom of air and space operations for our forces, and deny these capabilities to our adversaries at times and places 3 of our choosing.

4 Priority Warfighter Needs Being Addressed by Sensors Directorate Sense, identify, and track all air and surface targets and threats world wide and in all weather Counter difficult targets (WMD, hidden, LO) Protect air and space assets Control the battlespace electromagnetic spectrum Rapidly prosecute time-critical targets and threats Balance: Performance & Affordability 4

5 Sensors Directorate Technology Thrusts Radio Frequency Sensors & Countermeasures Automatic Electro-Optical Target Recognition Sensors & Countermeasures & Sensor Fusion Application Sub-thrusts Radio Frequency Apertures Algorithms & Phenomenology Digital Receivers & Exciters Reference Systems Components Battlespace Access Persistent ISR of the Battlespace Prosecution of Time Sensitive Targets Transmitters & Receivers Phenomenology & Algorithms Optical Apertures Signatures & Modeling Assessment & Foundation Innovative Algorithms 5 Enabling Sub-thrusts

6 Potential Growth Areas Hidden Target Detection & Identification Automatic Target Recognition (ATR) & Sensor Fusion Electronic Warfare Time Critical Targeting (TCT) 6

7 ATR Scope FUNCTIONS ID M60 TRACK GEOLOCATE FIND go l A 1 PD 0 0 ms h t ri S S s E re C u O at R n g P Si N IO nt e T FAR 10 m A R ss e U s T As MA SENSORS 7

8 ATR Approach Characterized Performance High Performance Computing Operational Databases FIND FIX TRACK & ID Operational Target Models/Databases ASSESSMENT& FOUNDATION SIGNATURES & MODELING INNOVATIVE ALGORITHMS Sensor Data Management System (SDMS) Signature Center Challenge Problems Standard Metrics ATR Theory Phenomenology Exploration EM Modeling Synthetic Data 8

9 ATR Facilities Advanced Recognition Capability (ARC) Facility 1 PD 0 0 FAR 10 PD PID Sensor Resolution Signature Center Sensor Data Management System (SDMS) 9

10 Operating Conditions (OCs) Sensors Targets Interactions Environment 10

11 How can we make ATR easier? T-72 T-62 Better Features Greater discriminating power Less variability Often conflicting! Better Data Resolution, dwell, persistence, Multiple sources (modes, looks, phenomenologies) Fuel Drums Side Fenders Smoke Canisters Length Width Height 6.9 m 3.6 m 2.2 m Length Width Height 6.6 m 3.5 m 2.4 m 11

12 ATR-Driven Sensing Cueing, Prioritization for the Human 10 ~1 ~1 Low Dielectric/Low Loss Face Sheet Short Circuits Resonant Cross Slots Cavity 12

13 Clear Box View of ATR 1 PD 0 0 Sensor Target Environment Detect Track Geolocate ID FAR 10 ATR Decisions Human Decisions Target Models & Database Feature Extractor Target Knowledge Discriminator Target Knowledge Decision Rule Trained Features 13 Templates Models

14 Multiple Sensor ATR Sensor Management Target Environment Sensor(s) Detect Track Geolocate ID ATR Decisions Human Decisions Adaptation Sensor Model Anticipate Registration Environment Model Performance Model Target Models & Database Behavior Models 14

15 ATR Theory Goals Performance Prediction Algorithm (or feature) dependent As a function of sensing, target, and environment conditions Tool for developers (how will this new feature help?), maturers (does this work well enough for my application?), and users (is this system going to work in my scenario today?) Performance Bounds Algorithm independent performance limits As a function of sensing, target, and environment conditions Is the limit the algorithm (keep working) or the sensor (motivate sensor improvements)? Performance Models Packaged tools from Performance Prediction usable by sensor management and fusion algorithms to weigh sensor contribution 15

16 Growing ATR Complexity Targets Dismounts Civilian Vehicles Smaller More Variable Military Vehicles Tougher Clutter More Obscuration Aircraft ID Function Forested Urban M or e Track Open Sp ec ific Detect Environments 16