NORTH ATLANTIC TREATY SCIENCE AND TECHNOLOGY ORGANIZATION ORGANIZATION AC/323(SET-227)TP/947 www.sto.nato.int STO TECHNICAL REPORT TR-SET-227 Cognitive Radar (Radar cognitif) Final Report of Task Group SET-227. Published October 2020 Distribution and Availability on Back Cover NORTH ATLANTIC TREATY SCIENCE AND TECHNOLOGY ORGANIZATION ORGANIZATION AC/323(SET-227)TP/947 www.sto.nato.int STO TECHNICAL REPORT TR-SET-227 Cognitive Radar (Radar cognitif) Final Report of Task Group SET-227. The NATO Science and Technology Organization Science & Technology (S&T) in the NATO context is defined as the selective and rigorous generation and application of state-of-the-art, validated knowledge for defence and security purposes. S&T activities embrace scientific research, technology development, transition, application and field-testing, experimentation and a range of related scientific activities that include systems engineering, operational research and analysis, synthesis, integration and validation of knowledge derived through the scientific method. In NATO, S&T is addressed using different business models, namely a collaborative business model where NATO provides a forum where NATO Nations and partner Nations elect to use their national resources to define, conduct and promote cooperative research and information exchange, and secondly an in-house delivery business model where S&T activities are conducted in a NATO dedicated executive body, having its own personnel, capabilities and infrastructure. The mission of the NATO Science & Technology Organization (STO) is to help position the Nations’ and NATO’s S&T investments as a strategic enabler of the knowledge and technology advantage for the defence and security posture of NATO Nations and partner Nations, by conducting and promoting S&T activities that augment and leverage the capabilities and programmes of the Alliance, of the NATO Nations and the partner Nations, in support of NATO’s objectives, and contributing to NATO’s ability to enable and influence security and defence related capability development and threat mitigation in NATO Nations and partner Nations, in accordance with NATO policies. The total spectrum of this collaborative effort is addressed by six Technical Panels who manage a wide range of scientific research activities, a Group specialising in modelling and simulation, plus a Committee dedicated to supporting the information management needs of the organization. • AVT Applied Vehicle Technology Panel • HFM Human Factors and Medicine Panel • IST Information Systems Technology Panel • NMSG NATO Modelling and Simulation Group • SAS System Analysis and Studies Panel • SCI Systems Concepts and Integration Panel • SET Sensors and Electronics Technology Panel These Panels and Group are the power-house of the collaborative model and are made up of national representatives as well as recognised world-class scientists, engineers and information specialists. In addition to providing critical technical oversight, they also provide a communication link to military users and other NATO bodies. The scientific and technological work is carried out by Technical Teams, created under one or more of these eight bodies, for specific research activities which have a defined duration. These research activities can take a variety of forms, including Task Groups, Workshops, Symposia, Specialists’ Meetings, Lecture Series and Technical Courses. The content of this publication has been reproduced directly from material supplied by STO or the authors. Published October 2020 Copyright © STO/NATO 2020 All Rights Reserved ISBN 978-92-837-2271-7 Single copies of this publication or of a part of it may be made for individual use only by those organisations or individuals in NATO Nations defined by the limitation notice printed on the front cover. The approval of the STO Information Management Systems Branch is required for more than one copy to be made or an extract included in another publication. Requests to do so should be sent to the address on the back cover. ii STO-TR-SET-227 Table of Contents Page List of Figures vii List of Tables x List of Acronyms xi SET-227 Membership List xiv Executive Summary and Synthèse ES-1 Chapter 1 – Context and Definitions 1-1 1.1 What is Cognition? 1-1 1.2 Adaptive Features of Modern Radar Systems 1-1 1.3 The Importance of Cognition in Radars 1-1 1.4 Objectives and Methodology 1-2 1.5 Report Structure 1-3 Chapter 2 – Cognitive Processes 2-1 2.1 Introduction 2-1 2.2 Definitions of Cognitive Processes 2-1 2.2.1 Learning 2-1 2.2.2 Problem Solving 2-2 2.2.3 Concepts and Categories 2-2 2.2.4 Language 2-2 2.2.5 Reasoning 2-3 2.2.6 Decision Making and Judgement 2-3 2.3 Cognitive Science and its Connection to Cognitive Psychology 2-3 2.3.1 History of AI 2-3 2.3.2 Influence of Artificial Intelligence 2-3 2.3.3 Influence of Cognitive Psychology 2-5 2.4 Situational Awareness and Connection to Perception-Action Cycle 2-6 Chapter 3 – Architectures and Components 3-1 3.1 Introduction 3-1 3.2 Cognitive Radar: High Level Architecture 3-1 3.2.1 Guerci’s Perspective and Architectures 3-1 3.2.2 Haykin’s Perspective and Architecture 3-3 3.3 Design of Cognitive Radar Architectures 3-7 3.3.1 Cognitive Radar Architecture Based on Information 3-7 Abstraction Levels 3.3.2 A Three-Layer Cognitive Radar Architecture 3-10 STO-TR-SET-227 iii 3.4 Cognitive Architectures for Radar Applications 3-13 3.4.1 Imaging Radar Cognitive Architecture 3-13 3.4.2 Spectrum Sensing Architecture for Cognitive Radar 3-15 3.5 Conclusions 3-19 Chapter 4 – Techniques and Approaches 4-1 4.1 Perception-Action Cycle and Feedback 4-1 4.2 Metrics for Optimization 4-2 4.3 Waveform Optimization 4-3 4.4 Information Theoretic Methods in Waveform Design 4-5 4.5 Radar Resource Management 4-6 4.5.1 Management Components 4-7 4.5.2 Priority Assignment 4-7 4.5.3 Rule-Based Task Management 4-7 4.5.4 Scheduling 4-8 4.5.5 Attention and Effective Radar Resource Management 4-8 4.6 Anticipation and Stochastic Control 4-9 4.6.1 Partially Observable Markov Decision Processes 4-9 4.6.2 Cognitive Processes 4-10 4.6.3 Anticipative Target Tracking Example 4-10 4.7 Biologically-Inspired Wideband Target Localisation 4-12 4.7.1 Introduction 4-12 4.7.2 Theory 4-14 4.7.3 Experiment 4-15 4.7.4 Conclusions 4-18 4.8 Machine Learning Approaches for Radar Resource Management 4-19 4.8.1 Introduction 4-19 4.8.2 RRM Problem Formulation 4-19 4.8.3 Reinforcement Learning Approach 4-20 4.8.4 Supervised Learning Approach 4-20 4.8.5 Conclusion 4-21 4.9 Perception-Action Cycle, Situational Awareness and Feedback 4-22 4.9.1 Introduction 4-22 4.9.2 Situational Awareness 4-23 4.9.3 Transmitter and Receiver Adaptation Using Situational 4-25 Awareness Chapter 5 – Performance Analysis and Verification 5-1 5.1 The Cognitive Radar Testbed CODIR 5-1 5.1.1 CODIR Sensor 5-2 5.1.2 CODIR Controller 5-2 5.1.3 Choice of Cost Function 5-3 5.2 Summary of Recent Results 5-3 5.2.1 Generic Scenario with Clutter 5-3 iv STO-TR-SET-227 5.2.2 Moving Clutter Environment 5-5 5.2.3 Spectrally Congested and Jammed Environment 5-5 5.2.4 Generalized Cost Function 5-5 5.3 Experimental Demo of Cognitive Spectral Sensing and Transmit 5-5 Notching 5.3.1 Spectrally Notched FM Noise Waveforms 5-6 5.3.2 Assessment of Spectrally Notched FM Noise Waveforms 5-6 5.3.3 Free-Space Experimental Evaluation of Spectrally Notched 5-7 FM Noise Waveforms Chapter 6 – Applications 6-1 6.1 Overview 6-1 6.2 Cognitive Radar in Spectrum Sharing Scenarios 6-3 6.2.1 Spectrum Sensing 6-3 6.2.2 Spectrum Sharing 6-5 6.2.3 Spectrum State Awareness / Spectrum Maps 6-7 6.2.4 Waveform Design and Optimization 6-9 6.2.5 Interference Mitigation 6-10 6.3 Imaging Radar Cognitive Architecture: Implementation 6-11 6.4 Cognitive Jammer-Based ISAR Passive Radar 6-16 6.4.1 Case Study 6-17 6.4.1.1 Sample Case 6-18 6.4.1.2 Jammer Transmitter Adaptation 6-19 6.4.1.3 Requirements for Jamming Signals 6-19 6.4.1.4 ISAR Simulation Results 6-20 6.4.1.5 Conclusions 6-20 Chapter 7 – Enabling Technologies 7-1 7.1 Computing and Optimization 7-1 7.2 Online Waveform Synthesis and Generation 7-1 7.3 Wideband and Tunable Frequency Components 7-2 7.4 Machine Learning and Artificial Intelligence 7-2 7.5 All-Digital Radar Arrays 7-3 7.6 RF System-on-Chip (RFSoC) 7-4 Chapter 8 – Challenges to the Research Community 8-1 8.1 Research Challenges 8-1 8.1.1 Assessment and Evaluation 8-1 8.1.2 The Research and Development Process and Experimentation 8-1 8.2 Practical Challenges 8-2 8.2.1 Requirements Definition 8-2 8.2.2 Robustness 8-3 8.2.3 Implementation and Regulation 8-3 8.2.4 Legal Issues 8-4 STO-TR-SET-227 v Chapter 9 – Conclusions and Recommendations 9-1 9.1 Summary and Conclusions 9-1 9.2 Recommendations 9-1 Chapter 10 – References 10-1 Annex A – List of Meetings A-1 Annex B – Bibliography of Work/Outputs of SET-227 B-1 vi STO-TR-SET-227 List of Figures Figure Page Figure 2-1 Structuring of Intelligent Systems According to Russel 2-5 and Norvig Figure 2-2 Endsley’s Model of Situational Awareness 2-6 Figure 2-3 Wickens’ Model of Information Processing 2-7 Figure 3-1 Cognitive Radar Architecture Proposed by Guerci 3-2 Figure 3-2 Sense-Learn-Adapt Cycle 3-2 Figure 3-3 CoFAR Architecture Proposed by Guerci 3-3 Figure 3-4 Haykin’s Diagram of Cognitive Radar 3-4 Figure 3-5 Diagram of Cognitive Radar with Memory 3-4 Figure 3-6 Block Diagram of Cognitive Radar as a Dynamic 3-5 Closed-Loop Feedback System Figure 3-7 Martone’s Proposed Cognitive Radar Framework 3-7 Figure 3-8 Radar System Architecture, Structured in Information 3-8 Abstraction Levels