Autonomous Marine Vehicles Planning and Control: Planning and Control

Master the future of marine exploration and technology with Autonomous Marine Vehicles Planning and Control, which provides a comprehensive, interdisciplinary guide to the principles, control, and real-world applications of autonomous marine vehicles. Autonomous Marine Vehicles Planning and Control explores the intricate and rapidly evolving field of autonomous marine vehicles, focusing on unmanned surface vehicles (USVs) and autonomous underwater vehicles (AUVs). This book is designed to provide a comprehensive overview of the fundamental principles, advanced control methodologies, and practical applications of these autonomous systems in various marine environments. Through a series of detailed chapters, the book delves into the technical aspects, innovative algorithms, and real-world challenges associated with the deployment and operation of USVs and AUVs. Through a highly technical and research-oriented approach, each chapter combines theoretical analysis with practical case studies and simulation results to illustrate the effectiveness of the proposed methods. The book also addresses the interdisciplinary nature of the field, integrating concepts from robotics, artificial intelligence, and marine engineering to provide a holistic view of autonomous marine vehicle technology.

Table of Contents:
Preface v 1 Introduction 1 1.1 Overview 1 1.2 System Structure 6 1.3 Mathematical Model of a USV 8 1.4 Maritime Applications 11 1.5 Motivation of this Book 13 References 13 2 Automatic Control Module 15 2.1 Origin and Development 16 2.2 Common Control System Development 17 2.2.1 Dynamic Positioning and Position Mooring Systems 17 2.2.1.1 Dynamic Positioning Control System 18 2.2.1.2 Position Mooring Control System 22 2.2.2 Waypoint Tracking and Path-Following Control Systems 24 2.2.2.1 Waypoint Tracking Control System 24 2.2.2.2 Path-Following Control System 26 2.3 Advanced Control System Development 31 2.3.1 Linear Quadratic Optimal Control 31 2.3.2 State Feedback Linearization 36 2.3.2.1 Decoupling in the BODY Frame (Velocity Control) 36 2.3.2.2 Decoupling in the NED Frame (Position and Attitude Control) 38 2.3.3 Integrator Backstepping Control 40 2.3.4 Sliding-Mode Control 45 2.3.4.1 SISO Sliding-Mode Control 45 2.3.4.2 Sliding-Mode Control Using the Eigenvalue Decomposition 49 References 52 3 Perception and Sensing Module 57 3.1 Low-Pass and Notch Filtering 58 3.1.1 Low-Pass Filtering 58 3.1.2 Cascaded Low-Pass and Notch Filtering 59 3.2 Fixed Gain Observer Design 60 3.2.1 Observability 60 3.2.2 Luenberger Observer 60 3.2.3 Case Study: Luenberger Observer for Heading Autopilots Using Only Compass Measurements 61 3.3 Kalman Filter Design 61 3.3.1 Discrete-Time Kalman Filter 61 3.3.2 Continuous-Time Kalman Filter 62 3.3.3 Extended Kalman Filter 63 3.3.4 Corrector–Predictor Representation for Nonlinear Observers 64 3.3.5 Case Study: Kalman Filter for Heading Autopilots Using Only Compass Measurements 64 3.3.5.1 Heading Sensors Overview 64 3.3.5.2 System Model for Heading Autopilot Observer Design 65 3.3.6 Case Study: Kalman Filter for Dynamic Positioning Systems Using GNSS and Compass Measurements 66 3.4 Nonlinear Passive Observer Designs 67 3.4.1 Case Study: Passive Observer for Dynamic Positioning Using GNSS and Compass Measurements 67 3.4.2 Case Study: Passive Observer for Heading Autopilots Using only Compass Measurements 68 3.4.3 Case Study: Passive Observer for Heading Autopilots Using Both Compass and Rate Measurements 71 3.5 Integration Filters for IMU and Global Navigation Satellite Systems 71 3.5.1 Integration Filter for Position and Linear Velocity 72 3.5.2 Accelerometer and Compass Aided Attitude Observer 73 3.5.3 Attitude Observer Using Gravitational and Magnetic Field Directions 73 References 74 4 Model Predictive Control for Autonomous Marine Vehicles: A Review 75 4.1 Introduction 75 4.1.1 Object Introduction 75 4.1.2 Previous Reviews 77 4.2 Fundamental Models and a General Picture 85 4.2.1 Model of AMVs 85 4.2.1.1 6-DOF Model 85 4.2.1.2 3-DOF Model 90 4.2.2 Model Predictive Control 92 4.2.3 Literature Search 96 4.3 Methodology 99 4.3.1 MPC Applications of AMVs 99 4.3.1.1 Real-Coded Chromosome 99 4.3.1.2 Path Following 101 4.3.1.3 Trajectory Tracking 104 4.3.1.4 Cooperative Control/Formation Control 106 4.3.1.5 Collision Avoidance 108 4.3.1.6 Energy Management 111 4.3.1.7 Other Topics 113 4.4 Discussion 114 4.4.1 Limitations of Existing Techniques and Challenges in Developing MPC 114 4.4.1.1 Uncertainties of AMV Motion Models 114 4.4.1.2 Stability and Security of the New MPC Method 115 4.4.1.3 The Balance Between Effectiveness and Efficiency of the Methods 115 4.4.1.4 The Practical Application Scenario of the MPC and the Discussion of the Working Conditions 116 4.4.1.5 Challenges Posed by the Marine Environment Affect MPC Development for AMVs 116 4.4.2 Trends in the Technology Development for MPC in AMV 117 4.4.2.1 More Cooperative Control with MPC 117 4.4.2.2 Rigorous Theoretical Derivation and Experimental Verification 117 4.4.2.3 Real-Time MPC for AMVs Applications 118 4.4.2.4 The Combination of Machine Learning/Neural Networks and MPC for AMVs Applications 118 4.4.2.5 Address the Challenges Posed by the Marine Environment 119 4.4.2.6 Potential Interdisciplinary Approaches that Combine MPC with Other Innovative Fields 120 4.5 Conclusion 121 Acknowledgement 121 References 121 5 Controller-Consistent Path Planning for Unmanned Surface Vehicles 129 5.1 Introduction 129 5.2 Problem Formulation 131 5.3 Methodology 132 5.3.1 Improved Artificial Fish Swarm Algorithm 132 5.3.1.1 Prey Behavior 133 5.3.1.2 Follow Behavior 135 5.3.1.3 Swarm Behavior 135 5.3.1.4 Random Behavior 136 5.3.1.5 Adaptive Visual and Step 136 5.3.2 Expanding Technique 138 5.3.3 Node Cutting and Path Smoother 139 5.3.4 Establishment of USV Model 141 5.4 Simulation 144 5.4.1 Monte Carlo Simulation 145 5.4.2 Path Quality Test 146 5.4.3 Simulation Using USV Control Model in Practical Environment 149 5.5 Conclusion 151 References 152 6 Nonlinear Model Predictive Control and Routing for USV-Assisted Water Monitoring 155 6.1 Introduction 156 6.2 Problem Formulation 161 6.2.1 Heterogeneous Global Path Planning Problem 161 6.2.1.1 USV Model 161 6.2.1.2 Task Model 162 6.2.1.3 Problem Statement 162 6.2.2 Problem Analysis 164 6.2.3 Path Following Problem 164 6.2.3.1 Basic Assumptions 165 6.2.3.2 Vessel Model 165 6.2.3.3 Problem Description 168 6.3 Methodology 169 6.3.1 Greedy Partheno Genetic Algorithm 169 6.3.1.1 Dual-Coded Chromosome 170 6.3.1.2 Fitness Function 170 6.3.1.3 Greedy Randomized Initialization 171 6.3.1.4 Local Exploration 172 6.3.1.5 Mutation Operators 174 6.3.1.6 Algorithm Flow 175 6.3.2 Nonlinear Model Predictive Control 177 6.3.2.1 State Space Model 177 6.3.2.2 NMPC Design 178 6.3.2.3 Solver 180 6.3.2.4 Stability 181 6.4 Results and Discussion 181 6.4.1 Simulation: Global Task Planning 181 6.4.1.1 Convergence Test 181 6.4.1.2 Heterogeneous Task Planning 185 6.4.2 Simulation: NMPC Control Performance 188 6.4.2.1 Test 1: Simulation Under Different Model Uncertainties 190 6.4.2.2 Test 2: Comparative Study with Other Methods 192 6.4.3 Simulation Verification of the Framework 196 6.5 Conclusion 200 References 201 7 Global-Local Hierarchical Framework for USV Trajectory Planning 207 7.1 Introduction 207 7.2 Problem Formulation 212 7.2.1 Marine Environment 212 7.2.2 Dynamic Obstacles 213 7.2.3 Effects of Currents 213 7.2.4 USV Model and Constraints 213 7.2.5 Protocol Constraints 216 7.2.6 Objective Functions 217 7.2.6.1 The Minimum Cruising Time 217 7.2.6.2 The Minimum Variation of Heading Angle 217 7.2.6.3 The Safest Path 218 7.2.7 Problem Statement 219 7.3 Methodology 221 7.3.1 Adaptive-Elite GA with Fuzzy Inference (AEGAfi) 221 7.3.1.1 Real-Coded Chromosome 221 7.3.1.2 Initialization Based on Adaptive Random Testing (ART) 222 7.3.1.3 Adaptive Elite Selection 223 7.3.1.4 Double-Functioned Crossover 224 7.3.1.5 Mutation Operators 225 7.3.1.6 Fuzzy-Based Probability Choice 226 7.3.1.7 Fitness Function Design 227 7.3.2 Replanning Strategy Based on Sensory Vector 229 7.3.2.1 Sensory Vector Structure 229 7.3.2.2 Formulation of V s 230 7.3.2.3 Formulation of Gap Vector V g Based on COLREGs 232 7.3.2.4 Formulation of Transition Path 234 7.4 Simulation Study 236 7.4.1 Convergence Benchmark Analysis 236 7.4.2 Simulation Under Static Environment 238 7.4.3 Simulation Under Time-Varying Environment 246 7.4.4 Simulation on Real-World Geography 251 7.5 Conclusion 254 Appendix 255 List of Abbreviations 255 Acknowledgements 256 References 256 8 Reinforcement Learning for USV-Assisted Wireless Data Harvesting 263 8.1 Introduction 263 8.2 Fundamental Models 269 8.2.1 Environment Model 272 8.2.2 Sensor Node and Communication Model 273 8.2.3 USV Model 275 8.2.3.1 Kinematic Model 275 8.2.3.2 Sensing Module 277 8.3 Methodology 278 8.3.1 Brief States on Q-Learning 278 8.3.2 Interactive Learning 279 8.3.2.1 Heuristic Reward Design 279 8.3.2.2 Design of Value-Iterated Global Cost Matrix 279 8.3.2.3 Local Cost Matrix and Path Generation 282 8.3.2.4 USV Actions with Discrete Precise Clothoid Path 283 8.3.3 Summary of the Path Planning Algorithm 286 8.3.4 Time Complexity 287 8.4 Results and Discussion 288 8.4.1 Performance Indicators 288 8.4.2 Hyper-Parameter Analysis 290 8.4.3 Comparative Study with State of the Art 294 8.5 Conclusion 298 Appendix 299 References 300 9 Achieving Optimal Dynamic Path Planning for Unmanned Surface Vehicles: A Rational Multi-Objective Approach and a Sensory-Vector Re-Planner 307 9.1 Introduction 308 9.2 Problem Formulation 314 9.2.1 Environment Modeling 315 9.2.1.1 Motion Area 315 9.2.1.2 Effects of Currents 315 9.2.2 Dynamic Obstacles 316 9.2.3 Motion Constraints 317 9.2.4 Objective Functions 317 9.2.4.1 Path Length 317 9.2.4.2 Path Smoothness 318 9.2.4.3 Energy Consumption 318 9.2.4.4 The Safest Path 318 9.2.5 Optimization Problem Statement 319 9.3 Methodology 321 9.3.1 Framework of NSGA-II 321 9.3.2 Aensga-ii 322 9.3.2.1 Real-Coded Representation 322 9.3.2.2 Initialization Using Candidate Set Adaptive Random Testing (CSART) 323 9.3.2.3 Adaptive Crowding Distance (ACD) Strategy 324 9.3.2.4 Improved Binary Tournament Selection 326 9.3.3 Fuzzy Satisfactory Degree 327 9.3.4 Replanning Strategy Based on Sensory Vector 330 9.3.4.1 Sensory Vector Structure 330 9.3.4.2 Formulation of Gap Vector V g Based on COLREGs 333 9.3.4.3 Formulation of Transition Path 335 9.4 Results and Discussion 336 9.4.1 Convergence and Diversity Analysis 336 9.4.2 Implementation in Static Environment 342 9.4.2.1 Fixed Currents 342 9.4.2.2 Time-Varying Currents 346 9.4.3 Simulation Under Dynamic Environment 351 9.5 Conclusion 356 Acknowledgements 357 References 357 10 Coordinated Trajectory Planning for Multiple AUVs 363 10.1 Introduction 363 10.1.1 Background 363 10.1.2 Related Work 364 10.1.3 Contributions 366 10.2 Problem Model 367 10.2.1 Environment Model 367 10.2.2 AUV Model 369 10.2.3 Space and Time Constraint Model 370 10.2.4 Optimization Terms 371 10.2.5 Problem Statement 374 10.3 Solver Design 374 10.3.1 Brief States on Grey Wolf Optimizer 374 10.3.2 Parallel Grey Wolf Optimizer Design 376 10.4 Results and Discussion 379 10.4.1 Simulation 1: Allocation Task 380 10.4.2 Simulation 2: Rendezvous Task 381 10.5 Conclusion 385 Acknowledgements 385 References 386 11 Coverage Strategy for USV-Assisted Coastal Bathymetric Mapping 389 11.1 Introduction 390 11.2 Fundamental Models 394 11.2.1 Region of Interest 394 11.2.2 USV Model 395 11.3 Methodology 396 11.3.1 Coastal Line Approximation 396 11.3.2 Coverage Strategy 397 11.3.2.1 Trapezoidal Cellular Decomposition 397 11.3.2.2 Optimal Back and Forth Coverage Algorithm 398 11.3.2.3 Theoretical Analysis 402 11.3.3 Fuzzy-Biased Random Key Evolutionary Algorithm (FRKEA) 403 11.3.3.1 Chromosome Mapping 404 11.3.3.2 Evaluation in Real Space 405 11.3.3.3 Elitist Breeding 406 11.3.3.4 Mutating 407 11.3.3.5 Fuzzy Bias 409 11.4 Results and Discussion 411 11.4.1 Convergence Analysis 412 11.4.2 Simulation Study 414 11.4.2.1 Competitive Study 414 11.4.2.2 Parameter Analysis 417 11.4.3 Lake Trials 419 11.5 Conclusion 423 References 424 12 Energy-Efficient Coverage for USV-Assisted Bathymetric Survey Under Currents 429 12.1 Introduction 429 12.2 Methodology 433 12.2.1 Problem Models 433 12.2.1.1 Region of Interest 433 12.2.1.2 Current Model 433 12.2.1.3 USV Kinematics Under Currents 434 12.2.1.4 Energy Estimation 435 12.2.2 Coverage Strategy 436 12.3 Results and Discussion 440 12.3.1 Preparation 440 12.3.2 Analysis on Polygon Shapes 441 12.3.3 Analysis on Attacking Angle 444 12.3.4 Analysis on Different Coverage Strategy 445 12.3.5 Test on a Complex Concave ROI 447 12.4 Conclusion 454 References 455 13 Modeling and Solving Time-Sensitive Task Allocation for USVs with Mixed Capabilities 459 13.1 Introduction 459 13.2 Problem Formulation 463 13.2.1 Fundamental Models 463 13.2.1.1 USV Model 463 13.2.1.2 Target Model 464 13.2.2 Extended-Restriction Multiple Traveling Salesman Problem (ER-MTSP) 465 13.2.3 Problem Analysis 467 13.3 Methodology 468 13.3.1 Dual-Coded Chromosome Representation 468 13.3.2 Adaptive Random Testing Initialization 469 13.3.3 Hierarchical Crossover 469 13.3.4 Customized Mutation Strategy 472 13.3.5 Two-Phase Refinement Strategy 473 13.3.6 Linguistic Satisfactory Degree 475 13.4 Results and Discussion 477 13.4.1 Convergence and Diversity Analysis 477 13.4.2 Case Studies 480 13.4.3 Field Test 487 13.5 Conclusion 492 References 493 14 Joint Optimized Coverage Planning Framework for USV-Assisted Offshore Bathymetric Mapping: From Theory to Practice 497 14.1 Introduction 498 14.2 Problem Formulation 502 14.2.1 Definitions 502 14.2.2 Problem Statement 503 14.2.3 Theoretical Analysis 506 14.3 Methods for Problem Solving 507 14.3.1 Bisection-Based Convex Decomposition 507 14.3.2 Hierarchical Heuristic Optimization Algorithm 510 14.3.2.1 Order Generation 510 14.3.2.2 Candidate Pattern Finding 514 14.3.2.3 Tour Finding 518 14.3.2.4 Final Optimization 519 14.4 Results and Discussion 520 14.4.1 Validation in Simulation 520 14.4.2 Lake Experiments 526 14.5 Conclusion 530 Acknowledgements 530 Appendix 530 References 530 15 Pipe Segmentation and Geometric Reconstruction from Poorly Scanned Point Clouds Based on Deep Learning and BIM-Generated Data Alignment Strategies 535 15.1 Introduction 535 15.2 Related Studies 537 15.2.1 Pipe Segmentation 537 15.2.1.1 Descriptor-Based Methods 537 15.2.1.2 Learning-Based Methods 538 15.2.2 Dataset Preparation 538 15.2.3 Pipe Reconstruction 539 15.3 Methodology 539 15.3.1 BIM-Based Data Generating 540 15.3.2 Network Architecture 542 15.3.2.1 Overall Architecture 542 15.3.2.2 PipeSegNet Architecture 543 15.3.2.3 Feature Alignment Module 545 15.3.2.4. Label Alignment Module 546 15.3.2.5 Loss Function 547 15.3.3 Pipe Geometric Reconstruction 548 15.4 Experiment 552 15.4.1 Experimental Settings 552 15.4.2 Evaluation Metrics 555 15.4.3 Results and Discussion 556 15.5 Conclusion 563 Acknowledgment 564 References 564 16 The Arc Routing Path Planning Problem in the Maritime Domain 571 16.1 Introduction 571 16.2 The Arc Routing Path Planning Problem 575 16.2.1 Introduction to Arc Routing 575 16.2.2 Common Applications of Arc Routing 577 16.3 One Solution for Arc Problem: The Chinese Postman Problem 578 16.3.1 Basic Conception 578 16.3.2 Core Formulation 579 16.3.3 Variants of the Chinese Postman Problem 580 16.3.4 Algorithmic Approaches and Solution Methods 581 16.3.4.1 Polynomial-Time Solutions 581 16.3.4.2 NP-Hard Variants 582 16.4 Case Study 583 16.4.1 Background 583 16.4.2 Platform Design 584 16.4.3 Full Coverage Problem 586 16.4.3.1 Theoretical Formulation: Using the Chinese Postman Problem for Efficient Coverage 586 16.4.3.2 Coverage Path Generation 587 16.4.3.3 Discussion 588 16.5 Concluding Remarks 588 References 589 17 Atmospheric Scattering Model-Based Dataset for Maritime Object Detection with YOLOv 11 591 17.1 Introduction 591 17.2 Methodology 593 17.2.1 Physics-Based Fog Simulation Using Depth Estimation 593 17.2.1.1 MiDaS: Monocular Depth Estimation 593 17.2.1.2 Atmospheric Scattering Model 595 17.2.2 YOLOv 11 596 17.3 Experiment 598 17.3.1 Dataset 598 17.3.2 Foggy Dataset Generation and Model Training 599 17.3.2.1 Foggy Dataset Generation 599 17.3.2.2 Model Training 599 17.4 Result and Discussion 600 17.4.1 Baseline Training and Generalization Analysis 600 17.4.2 Improving Model Robustness with Mixed- Concentration Fog Training 601 17.4.3 Detection Result Comparison 604 17.5 Conclusion 610 References 611 18 Multisensor Perception and Data Fusion Technologies 613 18.1 Camera-Based Detection Approaches 614 18.1.1 RGB and Stereo Camera 614 18.1.2 Infrared and Thermal Camera 617 18.1.3 Object Detection Methodologies 618 18.2 LiDAR-Based Detection Approaches 620 18.2.1 Stages of Object Detection 621 18.2.2 Challenges and Resolutions 623 18.3 Data Fusion Methods 624 18.3.1 Radar 625 18.3.2 Fusion Level 626 18.3.3 Synchronization and Calibration 627 References 629 19 Route Planning for Low-Altitude UAV Using Multi-Objective Optimization 633 19.1 Introduction 634 19.2 Problem Model 636 19.3 Multi-Objective Particle Swarm Optimization 639 19.4 Results and Discussion 643 References 645 20 Autonomous System Design of Marine Vehicles 647 20.1 Introduction 647 20.2 Planning Module Design 649 20.2.1 Recursive Cell Decomposition Method 650 20.2.2 Optimal Path Generation 653 20.2.3 Guidance Planning: Adaptive Line-of-Sight (ALOS) Method 656 20.3 Control Module Design: USV Dynamics Modeling 657 20.4 Combined Navigation Module Design 661 References 663 Index 665

About the Author :
Yong Bai, PhD is a professor in the College of Civil Engineering and Architecture at Zhejiang University. He has written over 200 academic papers in national and international academic journals and internationally published over 20 books. His research interests include marine engineering structures, unmanned surface vehicles, autonomous underwater vehicles, hydrogen vessels, marine pipelines and risers, engineering risk analysis, and safety assessment. Liang Zhao, PhD is a research fellow at Zhejiang University. He has co-authored over 20 research articles in top engineering journals. His current research focuses on planning and decision making for marine robotics, asynchronous maritime perception, and green and intelligent shipping.