Fundamentals of Data and Information Fusion for Aerospace Systems Online

This course provides an introductory overview of the concepts, frameworks, representative applications, mathematical sketches, and research issues in the field of Data and Information Fusion. Data and Information Fusion, which spans sensing, tracking and identification, situation assessment, and resource management for decision-making under uncertainty, is becoming prevalent in aerospace systems and is one of the core technologies for enabling autonomous operations. This course is intended for those unfamiliar with the fundamentals and broader implications of these topics and/or are seeking a roadmap and refresher for approaching this topic for aerospace systems research and development. A top-level overview will also be provided in regard to the systems engineering issues for the application of these technologies into real-world aerospace applications such as missile defense, command-and-control, air-traffic control, remote-sensing, and autonomous vehicles.

Learning Outcomes:

  • Describe fundamental concepts of Data and Information Fusion
  • Summarize and apply Multi-Level Reference Model of Data and Information Fusion
  • Develop Networked and Distributed Sensor and Data Fusion
  • Recognize Functional Issues and employ Mathematical Techniques
  • Plan and execute Testing and Evaluation of Data Fusion Processes
  • Perform Systems Engineering of Data Fusion-Enabled Systems
  • Describe Aerospace Applications of Data and Information Fusion

Who Should Attend
This course is directed to technical program managers, lead engineers, and graduate students who want to get a first-level understanding of Data and Information Fusion both as a field of study and from a systems development/application perspective as well.

Classroom hours / CEUs: 8 classroom hours / .8 CEU/PDH

  1. Lecture 1: History/Foundations, Reference Model, Terminology, Multidisciplinary Aspects, The Profession, Breadth of Applications, Benefits
    • Terminology and basic functional concepts
    • Understanding Data & Information Fusion (DIF) as an Estimation process
    • Appreciating the multidisciplinary nature of DIF
    • Brief examples of applications in aerospace, disaster relief, condition-based maintenance
    • Notions of the Cost-Benefit Tradespace
  2. Lecture 2: Understanding the Fusion Node Concept, involving Alignment/Common Referencing, Data Association, and Estimation
    • The Fusion Node (FN) as the foundational component of all DIF architectures
    • A sample of the DN in an example DIF architecture—and the Dual Node Network concept
    • The crucial role of Data Association and the concept of its structure
  3. Lecture 3: Functions & Architectures, Typical alternatives/tradeoffs, Distributed & Networked Architectures and Fusion Issues

    • The Distributed Network setting for DIF operations
    • Typical network topologies and tradeoffs
    • Subtle yet critical issues: double counting; correlation effects
    • Example application in Counter-Drone applications
  4. Lecture 4: Representative Mathematical Flow and Issues; Multi-sensor Multi-object Tracking Example

    • Using the Fusion Node idea to frame the approach
    • Reviewing each functional component:
      • Alignment: coordinate systems, uncertainty normalization
      • Data Association: association hypotheses, scoring, optimization
      • Estimation: Kalman Filtering and Variations
      • Fusion: Information Matrix Fusion and Covariance Intersection
  5. Lecture 5: Introduction to High-level Data Fusion for Situational Awareness Tracking Example
    • Brief introduction to Situational Awareness problem formulation and high-level data fusion
    • Introduction to Bayesian Networks and Dempster-Schafer Theory for heterogeneous data fusion
    • Hands-on working examples with Bayesian Networks and Dempster-Schafer belief function fusion
  6. Lecture 6: Systems Engineering of Data Fusion Systems

    • Brief Introduction to Engineering Complex Systems and System of Systems
    • Systems Engineering Needs for Data Fusion Systems
    • Functional, Physical, and Allocated Architectures of Data Fusion Systems
    • Modeling, Simulation, and Executable Architectures for Data Fusion Systems
  7. Lecture 7: Testing and Evaluation of Fusion Processes

    • Test and Evaluation Challenge for DIF Systems
    • Trade space analysis, Experimental Design, and Machine Learning for Data Fusion Systems
    • Machine Learning Application Example for Distributed Target Tracking Test and Evaluation
  8. Lecture 8: Aerospace Applications of Data and Information Fusion
    • Aerospace Mission Concepts and the Role of DIF; Example application to include:
      • Missile Defense and Command and Control (C2) Systems
      • Autonomous Vehicles, Unmanned Aerial Systems (UAS) and Counter-UAS
      • DIF for Space Debris Tracking
      • Role of DIF in Space Exploration Missions

Dr. James Llinas brings over 35 years of experience in multisource information processing and data fusion technology to his research, teaching, and business development activities. He is an internationally-recognized expert in sensor, data, and information fusion, co-authored the first integrated book on Multisensor Data Fusion, and has lectured internationally for over 20 years on this topic. His experience in applying this technology to different problem areas ranges from defense applications to non-defense applications to include intelligent transportation systems, medical diagnostics, and condition-based maintenance, among others. Current research activities related to the field of Information Fusion include funded programs in Space Situational Awareness, Machine Understanding, Autonomy/Autonomous Operations, and Missile Defense. He has been a Consultant to many U.S. and International defense organizations to include the Air Force Research Laboratory, DARPA, NSA, and the NRO.

Dr. Llinas created the concept for and is now Director for the “Center for Multisource Information Fusion” located at the State University of New York at Buffalo. This first-of-its-kind, University-based research center has been conducting basic research in Data and Information Fusion over some 20+ years.

Dr. Ali Raz is an Assistant Professor at George Mason University Department of Systems Engineering and Operations Research. His research and teaching interests are in complex aerospace systems, systems engineering, and information fusion. Dr. Raz also holds a visiting faculty appointment with the U.S. Navy Naval Surface Warfare Center at Crane, IN. Previously, he was a visiting Assistant Professor at Purdue University School of Aeronautics and Astronautics and has also taught at the U.S. Naval Post Graduate School. He has worked at the John Hopkins University Applied Physics Laboratory, Missile Defense Agency, and Honeywell Aerospace in support of complex systems engineering and information fusion research activities. He holds a Bachelor and Master of Science in Electrical Engineering from Iowa State University, and a Ph.D. in Aeronautics and Astronautics from Purdue University. He is a co-chair of International Council on Systems Engineering Complex Systems Working Group and a Certified Systems Engineering Professional (CSEP). He is also a senior member of the AIAA and an active participant of the Information, Command and Control Systems (IC2S) and Sensor Systems and Information Fusion (SSIF) technical committees.



AIAA Training Links