Artificial Intelligence for Unmanned Aerial Vehicles

SHUYAN HU, PHD, is an Associate Professor with the College of Electronics and Information Engineering at Tongji University, Shanghai, China.XIN YUAN, PHD, is a Senior Research Scientist at CSIRO and an Adjunct Senior Lecturer at the University of New South Wales, Sydney, NSW, Australia.KAI LI, PHD, serves as a Visiting Research Scientist with the School of Electrical Engineering and Computer Science, TU Berlin, Germany, and is also a Senior Research Scientist with Real-Time and Embedded Computing Systems Research Centre (CISTER), Porto, Portugal.WEI NI, PHD, is a Senior Principal Research Scientist at CSIRO and a Conjoint Professor at the University of New South Wales, Sydney, NSW, Australia.XIN WANG, PHD, is a Professor with the College of Future Information Technology at Fudan University, Shanghai, China.

• List of Figures xiList of Tables xxiAbout the Authors xxiiiPreface xxviiAcronyms xxix1 Introduction 11.1 UAV Applications 11.2 Sensing, Communication, and Computing of UAVs 21.3 Mobility Models of UAVs 41.4 UAVs Powered with AI 41.5 Book Contributions 61.6 Book Outline 82 Capacity and Connectivity of UAVs in Three-dimensional Spaces 112.1 Introduction 112.2 System Model and Performance Metrics 132.3 Analysis of UAVs with Random Trajectories 202.4 Network Densification and Relay 292.5 Instantaneous Outage Probability of UAVs Under Ground Interference 312.6 Ergodic Outage Probability of UAVs Under Ground Interference 362.7 Ergodic Outage Probability of UAVs Without Ground Interference 392.8 Numerical Evaluation 402.9 Impact of Imperfect CSI at UAV Receiver 442.10 Conclusion 523 Secrecy Risks Posed by Individual UAV Adversary 533.1 Introduction 533.2 System Model 563.3 Achievable Secrecy Rate Under Aerial Eavesdropper 613.4 Numerical and Simulation Results 673.5 Conclusion 764 Secrecy Risks Posed by Cooperative UAV Adversaries 774.1 Ergodic and ;;-Outage Secrecy Capacity Against Cooperative Aerial Eavesdroppers 774.2 Secrecy Under Imperfect Oscillator and Finite Memory of Eavesdroppers 854.3 Numerical and Simulation Results 894.4 Discussion on AI Techniques and Noncooperative Eavesdroppers 954.5 Conclusion 965 Joint Cruise Control and Data Collection of UAVs 995.1 Introduction 995.2 Existing Techniques 1025.3 System Model 1045.4 Joint Optimization of Cruise Control and Task Offloading 1065.5 Combinatorial GNN-enabled DRL 1085.6 Implementation and Performance Evaluation 1125.7 Conclusion 1186 Radio and Video Surveillance with UAVs 1196.1 Introduction 1196.2 System Model 1226.3 Trajectory and Power Optimization for Rotary-wing UAV 1296.4 Trajectory and Power Optimization for Fixed-wing UAV 1406.5 Numerical Results 1446.6 Authentication Management of UAVs 1686.7 Conclusion 1697 Energy Efficiency for UAV-based Radio Sensing and Monitoring 1717.1 Introduction 1717.2 System Models 1747.3 Legitimate Eavesdropping with Jamming 1787.4 Energy Management for Solar-powered UAV 1867.5 Numerical Results 1937.6 Conclusion 2008 Joint Sensing and Communications with UAVs 2018.1 Introduction 2018.2 System Model 2078.3 UAV-assisted JCAS 2138.4 Problem Formulation and DDPG-based Solution for Visual-based UAV 2198.5 Simulation and Experiment 2298.6 Conclusion 2519 Reconfigurable Intelligent Surface-assisted UAVs 2539.1 Introduction 2539.2 DRL-driven RIS-assisted Radio Surveillance 2569.3 RIS-assisted Jamming Rejection for UAV-borne IoT 2729.4 Performance Evaluation 2819.5 Conclusion 29810 Conclusion and Future Work 301A Appendix of Chapter 2 303B Appendix of Chapter 3 307C Appendix of Chapter 4 321Bibliography 337Index 367