图书信息:

书  名:Multi-View Geometry Based Visual Perception and Control of Robotic Systems
作  者:Jian Chen, Bingxi Jia, Kaixiang Zhang
出 版 社:CRC Press
出版日期:2018年6月
语  种:英文
I S B N:9780815365983
页  数:360

内容简介:   

  This book describes visual perception and control methods for robotic systems that need to interact with the environment. Multiple view geometry is utilized to extract low-dimensional geometric information from abundant and high-dimensional image information, making it convenient to develop general solutions for robot perception and control tasks. In this book, multiple view geometry is used for geometric modeling and scaled pose estimation. Then Lyapunov methods are applied to design stabilizing control laws in the presence of model uncertainties and multiple constraints.


英文目录:
Preface
Authors
PART I: FOUNDATIONS
1 Robotics
  1.1 Pose Representation
    1.1.1 Position and Translation
    1.1.2 Orientation and Rotation
    1.1.3 Homogeneous Pose Transformation
  1.2 Motion Representation
    1.2.1 Path and Trajectory
    1.2.2 Pose Kinematics
  1.3 Wheeled Mobile Robot Kinematics
    1.3.1 Wheel Kinematic Constraints
    1.3.2 Mobile Robot Kinematic Modeling
    1.3.3 Typical Nonholonomic Mobile Robot
2 Multiple-View Geometry
  2.1 Projective Geometry
    2.1.1 Homogeneous Representation of Points and Lines
    2.1.2 Projective Transformation
  2.2 Single-View Geometry
    2.2.1 Pinhole Camera Model
    2.2.2 Camera Lens Distortion
  2.3 Two-View Geometry
    2.3.1 Homography for Planar Scenes
    2.3.2 Epipolar Geometry for Nonplanar Scenes
    2.3.3 General Scenes
  2.4 Three-View Geometry
    2.4.1 General Trifocal Tensor Model
    2.4.2 Pose Estimation with Planar Constraint
  2.5 Computation of Multiple-View Geometry
    2.5.1 Calibration of Single-View Geometry
    2.5.2 Computation of Two-View Geometry
      2.5.2.1 Computation of Homography
      2.5.2.2 Computation of Epipolar Geometry
    2.5.3 Computation of Three-View Geometry
      2.5.3.1 Direct Linear Transform
      2.5.3.2 Matrix Factorization
    2.5.4 Robust Approaches
3 Vision-Based Robotic Systems
  3.1 System Overview
    3.1.1 System Architecture
    3.1.2 Physical Configurations
  3.2 Research Essential

PART II: VISUAL PERCEPTION OF ROBOTICS
4 Introduction to Visual Perception
  4.1 Road Reconstruction and Detection for Mobile Robots
    4.1.1 Previous Works
    4.1.2 A Typical Vehicle Vision System
      4.1.2.1 System Configuration
      4.1.2.2 Two-View Geometry Model
      4.1.2.3 Image Warping Model
      4.1.2.4 Vehicle-Road Geometric Model
      4.1.2.5 More General Configurations
  4.2 Motion Estimation of Moving Objects
  4.3 Scaled Pose Estimation of Mobile Robots
    4.3.1 Pose Reconstruction Based on Multiple-View Geometry
    4.3.2 Dealing with Field of View Constraintsm
      4.3.2.1 Key Frame Selection
      4.3.2.2 Pose Estimation
    4.3.3 Dealing with Measuring Uncertainties
      4.3.3.1 Robust Image Feature Extraction
      4.3.3.2 Robust Observers
      4.3.3.3 Robust Controllers
      4.3.3.4 Redundant Degrees of Freedom
5 Road Scene 3D Reconstruction
  5.1 Introduction
  5.2 Algorithm Process
  5.3 3D Reconstruction
    5.3.1 Image Model
    5.3.2 Parameterization of Projective Parallax
    5.3.3 Objective Function Definition and Linearization
    5.3.4 Iterative Maximization
    5.3.5 Post Processing
  5.4 Road Detection
    5.4.1 Road Region Segmentation
    5.4.2 Road Region Diffusion
  5.5 Experimental Results
    5.5.1 Row-Wise Image Registration
    5.5.2 Road Reconstruction
    5.5.3 Computational Complexity
    5.5.4 Evaluation for More Scenarios
6 Recursive Road Detection with Shadows
  6.1 Introduction
  6.2 Algorithm Process
  6.3 Illuminant Invariant Color Space
    6.3.1 Imaging Process
    6.3.2 Illuminant Invariant Color Space
    6.3.3 Practical Issues
  6.4 Road Reconstruction Process
    6.4.1 Image Fusion
    6.4.2 Geometric Reconstruction
      6.4.2.1 Geometric Modeling
    6.4.3 Road Detection
    6.4.4 Recursive Processing
  6.5 Experiments
    6.5.1 Illuminant Invariant Transform
    6.5.2 Road Reconstruction
    6.5.3 Comparisons with Previous Method
    6.5.4 Other Results
7 Range Identification of Moving Objects
  7.1 Introduction
  7.2 Geometric Modeling
    7.2.1 Geometric Model of Vision Systems
    7.2.2 Object Kinematics
    7.2.3 Range Kinematic Model
  7.3 Motion Estimation
    7.3.1 Velocity Identification of the Object
    7.3.2 Range Identification of Feature Points
  7.4 Simulation Results
  7.5 Conclusions
8 Motion Estimation of Moving Objects
  8.1 Introduction
  8.2 System Modeling
    8.2.1 Geometric Model
    8.2.2 Camera Motion and State Dynamics
  8.3 Motion Estimation
    8.3.1 Scaled Velocity Identification
    8.3.2 Range Identification
  8.4 Simulation Results
  8.5 Conclusions

PART III: VISUAL CONTROL OF ROBOTICS
9 Introduction to Visual Control
  9.1 Previous Works
    9.1.1 Classical Visual Control Approaches
      9.1.1.1 Position Based Methods
      9.1.1.2 Image Based Methods
      9.1.1.3 Multiple-View Geometry Based Method
    9.1.2 Main Existing Problems
      9.1.2.1 Model Uncertainties
      9.1.2.2 Field of View Constraints
      9.1.2.3 Nonholonomic Constraints
  9.2 Task Descriptions
    9.2.1 Autonomous Robot Systems
    9.2.2 Semiautonomous Systems
  9.3 Typical Visual Control Systems
    9.3.1 Visual Control for General Robots
    9.3.2 Visual Control for Mobile Robots
10 Visual Tracking Control of General Robotic Systems
  10.1 Introduction
  10.2 Visual Tracking with Eye-to-Hand Configuration
    10.2.1 Geometric Modeling
      10.2.1.1 Vision System Model
      10.2.1.2 Euclidean Reconstruction
    10.2.2 Control Development
      10.2.2.1 Control Objective
      10.2.2.2 Open-Loop Error System
      10.2.2.3 Closed-Loop Error System
      10.2.2.4 Stability Analysis
  10.3 Visual Tracking with Eye-in-Hand Configuration
    10.3.1 Geometric Modeling
    10.3.2 Control Development
      10.3.2.1 Open-Loop Error System
      10.3.2.2 Controller Design
  10.4 Simulation Results
  10.5 Conclusion
11 Robust Moving Object Tracking Control
  11.1 Introduction
  11.2 Vision System Model
    11.2.1 Camera Geometry
    11.2.2 Euclidean Reconstruction
  11.3 Control Development
    11.3.1 Open-Loop Error System
    11.3.2 Control Design
    11.3.3 Closed-Loop Error System
  11.4 Stability Analysis
    11.4.1 Convergence of the Rotational Error
    11.4.2 Convergence of the Translational Error
  11.5 Simulation Results
    11.5.1 Simulation Configuration
    11.5.2 Simulation Results and Discussion
  11.6 Conclusion
12 Visual Control with Field-of-View Constraints
  12.1 Introduction
  12.2 Geometric Modeling
    12.2.1 Euclidean Homography
    12.2.2 Projective Homography
    12.2.3 Kinematic Model of Vision System
  12.3 Image-Based Path Planning
    12.3.1 Pose Space to Image Space Relationship
    12.3.2 Desired Image Trajectory Planning
    12.3.3 Path Planner Analysis
  12.4 Tracking Control Development
    12.4.1 Control Development
    12.4.2 Controller Analysis
  12.5 Simulation Results
    12.5.1 Optical Axis Rotation
    12.5.2 Optical Axis Translation
    12.5.3 Camera y-Axis Rotation
    12.5.4 General Camera Motion
  12.6 Conclusions
13 Visual Control of Mobile Robots
  13.1 Introduction
  13.2 Goemetric Reconstruction
    13.2.1 Eye-to-Hand Configuration
    13.2.2 Eye-in-Hand Configuration
      13.2.2.1 Geometric Modeling
      13.2.2.2 Euclidean Reconstruction
  13.3 Control Development for Eye-to-Hand Configuration
    13.3.1 Control Objective
    13.3.2 Open-Loop Error System
    13.3.3 Closed-Loop Error System
    13.3.4 Stability Analysis
    13.3.5 Regulation Extension
  13.4 Control Development for Eye-in-Hand Configuration
    13.4.1 Open-Loop Error System
    13.4.2 Closed-Loop Error System
    13.4.3 Stability Analysis
  13.5 Simulational and Experimental Verifications
    13.5.1 Eye-to-Hand Case
    13.5.2 Eye-in-Hand Case
      13.5.2.1 Experimental Configuration
      13.5.2.2 Experimental Results
      13.5.2.3 Results Discussion
  13.6 Conclusion
14 Trifocal Tensor Based Visual Control of Mobile Robots
  14.1 Introduction
  14.2 Geometric Modeling
  14.3 Control Development
    14.3.1 Error System Development
    14.3.2 Controller Design
    14.3.3 Stability Analysis
  14.4 Simulation Verification
    14.4.1 Pose Estimation
    14.4.2 Visual Trajectory Tracking and Pose Regulation
    14.4.3 Trajectory Tracking with Longer Range
  14.5 Conclusion
15 Unified Visual Control of Mobile Robots with Euclidean
  Reconstruction
  15.1 Introduction
  15.2 Control Development
    15.2.1 Kinematic Model
    15.2.2 Open-Loop Error System
    15.2.3 Controller Design
    15.2.4 Stability Analysis
  15.3 Euclidean Reconstruction
  15.4 Simulation Results
  15.5 Conclusion

PART IV: APPENDICES 287
Appendix A: Chapter
  A.1 Proof of Theorem 7.1
Appendix B: Chapter 10
    B.1
    B.2
    B.3
Appendix C: Chapter 11
    C.1
    C.2 Proof of Property 11.1
    C.3 Proof of Lemma 11.1
    C.4 Proof of Property 11.2
Appendix D: Chapter 12
    D.1 Open-Loop Dynamics
    D.2 Image Jacobian-Like Matrix
    D.3 Image Space Navigation Function
Appendix E: Chapter 13
Appendix F: Chapter 14
    F.1
    F.2 Proof of  for  and  
    F.3 Proof of  
     F.4 Proof of  in the Closed-Loop System (14.19)
References
Index


  控制理论专业委员会 ©2011-2021 版权所有

中国自动化学会 控制理论专业委员会
电话:86-10-82541403;Email:tcct@iss.ac.cn