Author | : Roland Siegwart |

Publisher | : MIT Press |

Release Date | : 18 February 2011 |

ISBN 10 | : 0262015358 |

Pages | : 453 pages |

Rating | : 5/5 (1 users) |

Machine generated contents note: |g 1. |t Introduction -- |g 1.1. |t Introduction -- |g 1.2. |t An Overview of the Book -- |g 2. |t Locomotion -- |g 2.1. |t Introduction -- |g 2.1.1. |t Key issues for locomotion -- |g 2.2. |t Legged Mobile Robots -- |g 2.2.1. |t Leg configurations and stability -- |g 2.2.2. |t Consideration of dynamics -- |g 2.2.3. |t Examples of legged robot locomotion -- |g 2.3. |t Wheeled Mobile Robots -- |g 2.3.1. |t Wheeled locomotion: The design space -- |g 2.3.2. |t Wheeled locomotion: Case studies -- |g 2.4. |t Aerial Mobile Robots -- |g 2.4.1. |t Introduction -- |g 2.4.2. |t Aircraft configurations -- |g 2.4.3. |t State of the art in autonomous VTOL -- |g 2.5. |t Problems -- |g 3. |t Mobile Robot Kinematics -- |g 3.1. |t Introduction -- |g 3.2. |t Kinematic Models and Constraints -- |g 3.2.1. |t Representing robot position -- |g 3.2.2. |t Forward kinematic models -- |g 3.2.3. |t Wheel kinematic constraints -- |g 3.2.4. |t Robot kinematic constraints -- |g 3.g 3.3. |t Mobile Robot Maneuverability -- |g 3.3.1. |t Degree of mobility -- |g 3.3.2. |t Degree of steerability -- |g 3.3.3. |t Robot maneuverability -- |g 3.4. |t Mobile Robot Workspace -- |g 3.4.1. |t Degrees of freedom -- |g 3.4.2. |t Holonomic robots -- |g 3.4.3. |t Path and trajectory considerations -- |g 3.5. |t Beyond Basic Kinematics -- |g 3.6. |t Motion Control (Kinematic Control) -- |g 3.6.1. |t Open loop control (trajectory-following) -- |g 3.6.2. |t Feedback control -- |g 3.7. |t Problems -- |g 4. |t Perception -- |g 4.1. |t Sensors for Mobile Robots -- |g 4.1.1. |t Sensor classification -- |g 4.1.2. |t Characterizing sensor performance -- |g 4.1.3. |t Representing uncertainty -- |g 4.1.4. |t Wheel/motor sensors -- |g 4.1.5. |t Heading sensors -- |g 4.1.6. |t Accelerometers -- |g 4.1.7. |t Inertial measurement unit (IMU) -- |g 4.1.8. |t Ground beacons -- |g 4.1.9. |t Active ranging -- |g 4.1.10. |t Motion/speed sensors -- |g 4.1.11. |t Vision sensors -- |g 4.2. |t Fundameng 4.2.5. |t Structure from stereo -- |g 4.2.6. |t Structure from motion -- |g 4.2.7. |t Motion and optical flow -- |g 4.2.8. |t Color tracking -- |g 4.3. |t Fundamentals of Image Processing -- |g 4.3.1. |t Image filtering -- |g 4.3.2. |t Edge detection -- |g 4.3.3. |t Computing image similarity -- |g 4.4. |t Feature Extraction -- |g 4.5. |t Image Feature Extraction: Interest Point Detectors -- |g 4.5.1. |t Introduction -- |g 4.5.2. |t Properties of the ideal feature detector -- |g 4.5.3. |t Corner detectors -- |g 4.5.4. |t Invariance to photometric and geometric changes -- |g 4.5.5. |t Blob detectors -- |g 4.6. |t Place Recognition -- |g 4.6.1. |t Introduction -- |g 4.6.2. |t From bag of features to visual words -- |g 4.6.3. |t Efficient location recognition by using an inverted file -- |g 4.6.4. |t Geometric verification for robust place recognition -- |g 4.6.5. |t Applications -- |g 4.6.6. |t Other image representations for place recognition -- |g 4.7. |t Feature Extraction Based ong 4.7.3. |t Range histogram features -- |g 4.7.4. |t Extracting other geometric features -- |g 4.8. |t Problems -- |g 5. |t Mobile Robot Localization -- |g 5.1. |t Introduction -- |g 5.2. |t The Challenge of Localization: Noise and Aliasing -- |g 5.2.1. |t Sensor noise -- |g 5.2.2. |t Sensor aliasing -- |g 5.2.3. |t Effector noise -- |g 5.2.4. |t An error model for odometric position estimation -- |g 5.3. |t To Localize or Not to Localize: Localization-Based Navigation Versus Programmed Solutions -- |g 5.4. |t Belief Representation -- |g 5.4.1. |t Single-hypothesis belief -- |g 5.4.2. |t Multiple-hypothesis belief -- |g 5.5. |t Map Representation -- |g 5.5.1. |t Continuous representations -- |g 5.5.2. |t Decomposition strategies -- |g 5.5.3. |t State of the art: Current challenges in map representation -- |g 5.6. |t Probabilistic Map-Based Localization -- |g 5.6.1. |t Introduction -- |g 5.6.2. |t The robot localization problem -- |g 5.6.3. |t Basic concepts of probability theory -- |gg 5.6.6. |t Classification of localization problems -- |g 5.6.7. |t Markov localization -- |g 5.6.8. |t Kalman filter localization -- |g 5.7. |t Other Examples of Localization Systems -- |g 5.7.1. |t Landmark-based navigation -- |g 5.7.2. |t Globally unique localization -- |g 5.7.3. |t Positioning beacon systems -- |g 5.7.4. |t Route-based localization -- |g 5.8. |t Autonomous Map Building -- |g 5.8.1. |t Introduction -- |g 5.8.2. |t SLAM: The simultaneous localization and mapping problem -- |g 5.8.3. |t Mathematical definition of SLAM -- |g 5.8.4. |t Extended Kalman Filter (EKF) SLAM -- |g 5.8.5. |t Visual SLAM with a single camera -- |g 5.8.6. |t Discussion on EKF SLAM -- |g 5.8.7. |t Graph-based SLAM -- |g 5.8.8. |t Particle filter SLAM -- |g 5.8.9. |t Open challenges in SLAM -- |g 5.8.10. |t Open source SLAM software and other resources -- |g 5.9. |t Problems -- |g 6. |t Planning and Navigation -- |g 6.1. |t Introduction -- |g 6.2. |t Competences for Navigation: Planning and Reactig 6.4. |t Obstacle avoidance -- |g 6.4.1. |t Bug algorithm -- |g 6.4.2. |t Vector field histogram -- |g 6.4.3. |t The bubble band technique -- |g 6.4.4. |t Curvature velocity techniques -- |g 6.4.5. |t Dynamic window approaches -- |g 6.4.6. |t The Schlegel approach to obstacle avoidance -- |g 6.4.7. |t Nearness diagram -- |g 6.4.8. |t Gradient method -- |g 6.4.9. |t Adding dynamic constraints -- |g 6.4.10. |t Other approaches -- |g 6.4.11. |t Overview -- |g 6.5. |t Navigation Architectures -- |g 6.5.1. |t Modularity for code reuse and sharing -- |g 6.5.2. |t Control localization -- |g 6.5.3. |t Techniques for decomposition -- |g 6.5.4. |t Case studies: tiered robot architectures -- |g 6.6. |t Problems -- |t Bibliography -- |t Books -- |t Papers -- |t Referenced Webpages.