Probabilistic robotics / (Registro nro. 13052)
[ vista simple ]
000 -Cabecera | |
---|---|
Campo de control de longitud fija | 10658nam a2200349 a 4500 |
003 - Identificador del Número de control | |
Identificador del número de control | AR-sfUTN |
008 - Códigos de información de longitud fija-Información general | |
Códigos de información de longitud fija | 170717s2006 ||||| |||| 00| 0 eng d |
020 ## - ISBN | |
ISBN | 9780262201629 |
040 ## - Fuente de la catalogación | |
Centro transcriptor | AR-sfUTN |
041 ## - Código de lengua | |
Código de lengua del texto | eng |
080 ## - CDU | |
Clasificación Decimal Universal | 519.71 T417 |
Edición de la CDU | 2000 |
100 1# - Punto de acceso principal-Nombre de persona | |
Nombre personal | Thrun, Sebastian |
245 10 - Mención de título | |
Título | Probabilistic robotics / |
Mención de responsabilidad | Sebastian Thrun, Wolfram Burgard, Dieter Fox. |
260 ## - Publicación, distribución, etc. (pie de imprenta) | |
Lugar de publicación, distribución, etc. | Cambridge, MA : |
Nombre del editor, distribuidor, etc. | MIT Press, |
Fecha de publicación, distribución, etc. | 2006 |
300 ## - Descripción física | |
Extensión | 647 p. |
336 ## - Tipo de contenido | |
Fuente | rdacontent |
Término de tipo de contenido | texto |
Código de tipo de contenido | txt |
337 ## - Tipo de medio | |
Fuente | rdamedia |
Nombre del tipo de medio | sin mediación |
Código del tipo de medio | n |
338 ## - Tipo de soporte | |
Fuente | rdacarrier |
Nombre del tipo de soporte | volumen |
Código del tipo de soporte | nc |
490 ## - Mención de serie | |
Mención de serie | Intelligent Robotics and Autonomous Agents Series |
505 80 - Nota de contenido con formato | |
Nota de contenido con formato | CONTENIDO<br/>I Basics 1<br/>1 Introduction 3<br/>1.1 Uncertainty in Robotics 3<br/>1.2 Probabilistic Robotics 4<br/>1.3 Implications 9<br/>1.4 Road Map 10<br/>1.5 Teaching Probabilistic Robotics 11<br/>1.6 Bibliographical Remarks 11<br/>2 Recursive State Estimation 13<br/>2.1 Introduction 13<br/>2.2 Basic Concepts in Probability 14<br/>2.3 Robot Environment Interaction 19<br/>2.3.1 State 20<br/>2.3.2 Environment Interaction 22<br/>2.3.3 Probabilistic Generative Laws 24<br/>2.3.4 Belief Distributions 25<br/>2.4 Bayes Filtres 26<br/>2.4.1 The Bayes Filter Algorithm 26<br/>2.4.2 Example 28<br/>2.4.3 Mathematical Derivation of the Bayes Filter 31<br/>2.4.4 The Markov Assumption 33<br/>2.5 Representation and Computation 34<br/>3 Gaussian Filters 39<br/>3.1 Introduction 39<br/>3.2 The Kalman Filter 40<br/>3.2.1 Linear Gaussian Systems 40<br/>3.2.2 The Kalman Filter Algorithm 43<br/>3.2.3 Illustration 44<br/>3.2.4 Mathematical Derivation of the KF 45<br/>3.3 The Extended Kalman Filter 54<br/>3.3.1 Why Linearize? 54<br/>3.3.2 Linearization Via Taylor Expansion 56<br/>3.3.3 The EKF Algorithm 59<br/>3.3.4 Mathematical Derivation of the EKF 59<br/>3.3.5 Practical Considerations 61<br/>3.4 The Unscented Kalman Filter 65<br/>3.4.1 Linearization Via the Unscented Transform 65<br/>3.4.2 The UKF Algorithm 67<br/>3.5 The Information Filter 71<br/>3.5.1 Canonical Parameterization 71<br/>3.5.2 The Information Filter Algorithm 73<br/>3.5.3 Mathematical Derivation of the Information Filter 74<br/>3.5.4 The Extended Information Filter Algorithm 75<br/>3.5.5 Mathematical Derivation of the Extended Information Filter 76<br/>3.5.6 Practical Considerations 77<br/>4 Nonparantetric Filtres 85<br/>4.1 The Histogram Filter 86<br/>4.1.1 The Discrete Bayes Filter Algorithm 86<br/>4.1.2 Continuous State 87<br/>4.1.3 Mathematical Derivation of the Histogram Approximation 89<br/>4.1.4 Decomposition Techniques 92<br/>4.2 Binary Bayes Filters with Static State 94<br/>4.3 The Particle Filter 96<br/>4.3.1 Basic Algorithm 96<br/>4.3.2 Importance Sampling 100<br/>4.3.3 Mathematical Derivation of the PF 103<br/>4.3.4 Practical Considerations and Properties of Particle Filters 104<br/>5 Robot Motion 117<br/>5.1 Introduction 117<br/>5.2 Preliminaries 118<br/>5.2.1 Kinematic Configuration 118<br/>5.2.2 Probabilistic Kinematics 119<br/>5.3 Velocity Motion Model121<br/>5.3.1 Closed Form Calculation 121<br/>5.3.2 Sampling Algorithm 122<br/>5.3.3 Mathematical Derivation of the Velocity Motion Model 125<br/>5.4 Odometry Motion Model 132<br/>5.4.1 Closed Form Calculation 133<br/>5.4.2 Sampling Algorithm 137<br/>5.4.3 Mathematical Derivation of the Odometry Motion Model 137<br/>5.5 Motion and Maps140<br/>6 Robot Perception 149<br/>6.1 Introduction 149<br/>6.2 Maps 152<br/>6.3 Beam Models of Range Finders 153<br/>6.3.1 The Basic Measurement Algorithm 153<br/>6.3.2 Adjusting the Intrinsic Model Parameters 158<br/>6.3.3 Mathematical Derivation of the Beam Model 162<br/>6.3.4 Practical Considerations 167<br/>6.3.5 Limitations of the Beam Model 168<br/>6.4 Likelihood Fields for Range Finders 169<br/>6.4.1 Basic Algorithm 169<br/>6.4.2 Extensions 172<br/>6.5 Correlation-Based Measurement Models 174<br/>6.6 Feature-Based Measurement Models 176<br/>6.6.1 Feature Extraction 176<br/>6.6.2 Landmark Measurements 177<br/>6.6.3 Sensor Model with Known Correspondence 178<br/>6.6.4 Sampling Poses 179<br/>6.6.5 Further Considerations 180<br/>II Localization 189<br/>7 Mobile Robot Localization: Markov and Gaussian 191<br/>7.1 A Taxonomy of Localization Problems 193<br/>7.2 Markov Localization 197<br/>7.3 Illustration of Markov Localization 200<br/>7.4 EKF Localization 201<br/>7.4.1 Illustration 201<br/>7.4.2 The EKF Localization Algorithm 203<br/>7.4.3 Mathematical Derivation of EKF Localization 205<br/>7.4.4 Physical Implementation 210<br/>7.5 Estimating Correspondences 215<br/>7.5.1 EKF Localization with Unknown Correspondences 215<br/>7.5.2 Mathematical Derivation of the ML Data Association 216<br/>7.6 Multi-Hypothesis Tracking 218<br/>7.7 UKF Localization 220<br/>7.7.1 Mathematical Derivation of UKF Localization 220<br/>7.7.2 Illustration 223<br/>8 Mobile Robot Localization: Grid And Monte Carlo 237<br/>8.1 Introduction 237<br/>8.2 Grid Localization 238<br/>8.2.1 Basic Algorithm 238<br/>8.2.2 Grid Resolutions 239<br/>8.2.3 Computational Considerations 243<br/>8.2.4 Illustration 245<br/>8.3 Monte Carlo Localization 250<br/>8.3.1 Illustration 250<br/>8.3.2 The MCL Algorithm 252<br/>8.3.3 Physical Implementations 253<br/>8.3.4 Properties of MCL 253<br/>8.3.5 Random Particle MCL: Recovery from Failures 256<br/>8.3.6 Modifying the Proposal Distribution 261<br/>8.3.7 KLD-Sampling: Adapting the Size of Sample Sets 263<br/>8.4 Localization in Dynamic Environments 267<br/>III Mapping 279<br/>9 Occupancy Grid Mapping 281<br/>9.1 Introduction 281<br/>9.2 The Occupancy Grid Mapping Algorithm 284<br/>9.2.1 Multi-Sensor Fusion 293<br/>9.3 Learning Inverse Measurement Models 294<br/>9.3.1 Inverting the Measurement Model 294<br/>9.3.2 Sampling from the Forward Model 295<br/>9.3.3 The Error Function 296<br/>9.3.4 Examples and Further Considerations 298<br/>9.4 Maximum A Posteriori Occupancy Mapping 299<br/>9.4.1 The Case for Maintaining Dependencias 299<br/>9.4.2 Occupancy Grid Mapping with Forward Models 301<br/>10 Simultaneous Localization and Mapping 309<br/>10.1 Introduction 309<br/>10.2 SLAM with Extended Kalman Filters 312<br/>10.2.1 Setup and Assumptions 312<br/>10.2.2 SLAM with Known Correspondence 313<br/>10.2.3 Mathematical Derivation of EKF SLAM 317<br/>10.3 EKF SLAM with Unknown Correspondences 323<br/>10.3.1 The General EKF SLAM Algorithm 323<br/>10.3.2 Examples 324<br/>10.3.3 Feature Selection and Map Management 328<br/>11 The GraphSLAM Algorithm 337<br/>11.1 Introduction 337<br/>11.2 Intuitive Description 340<br/>11.2.1 Building Up the Graph 340<br/>11.2.2 Inference 343<br/>11.3 The GraphSLAM Algorithm 346<br/>11.4 Mathematical Derivation of GraphSLAM 353<br/>11.4.1 The Full SLAM Posterior 353<br/>11.4.2 The Negative Log Posterior 354<br/>11.4.3 Taylor Expansion 355<br/>11.4.4 Constructing the Information Form 357<br/>11.4.5 Reducing the Information Form 360<br/>11.4.6 Recovering the Path and the Map 361<br/>11.5 Data Association in GraphSLAM 362<br/>11.5.1 The GraphSLAM Algorithm with Unknown Correspondence 363<br/>11.5.2 Mathematical Derivation of the Correspondence Test 366<br/>11.6 Efficiency Consideration 368<br/>11.7 Empirical Implementation 370<br/>11.8 Alternative Optimization Techniques 376<br/>12 The Sparse Extended Information Filter 385<br/>12.1 Introduction 385<br/>12.2 Intuitive Description 388<br/>12.3 The SEIF SLAM Algorithm 391<br/>12.4 Mathematical Derivation of the SEIF 395<br/>12.4.1 Motion Update 395<br/>12.4.2 Measurement Updates 398<br/>12.5 Sparsification 398<br/>12.5.1 General Idea 398<br/>12.5.2 Sparsification in SEIFs 400<br/>12.5.3 Mathematical Derivation of the Sparsification 401<br/>12.6 Amortized Approximate Map Recovery 402<br/>12.7 How Sparse Should SEIFs Be? 405<br/>12.8 Incremental Data Association 409<br/>12.8.1 Computing Incremental Data Association Probabilities 409<br/>12.8.2 Practical Considerations 411<br/>12.9 Branch-and-Bound Data Association 415<br/>12.9.1 Recursive Search 416<br/>12.9.2 Computing Arbitrary Data Association Probabilities 416<br/>12.9.3 Equivalence Constraints 419<br/>12.10 Practical Considerations 420<br/>12.11 Multi-Robot SLAM 424<br/>12.11.1 Integrating Maps 424<br/>12.11.2 Mathematical Derivation of Map Integration 427<br/>12.11.3 Establishing Correspondence 429<br/>13 The FastSLAM Algorithm 437<br/>13.1 The Basic Algorithm 439<br/>13.2 Factoring the SLAM Posterior 439<br/>13.2.1 Mathematical Derivation of the Factored SLAM Posterior 442<br/>13.3 FastSLAM with Known Data Association 444<br/>13.4 Improving the Proposal Distribution 451<br/>13.4.1 Extending the Path Posterior by Sampling a New Pose 451<br/>13.4.2 Updating the Observed Feature Estimate 454<br/>13.4.3 Calculating Importance Factors 455<br/>13.5 Unknown Data Association 457<br/>13.6 Map Management 459<br/>13.7 The FastSLAM Algorithms 460<br/>13.8 Efficient Implementation 460<br/>13.9 FastSLAM for Feature-Based Maps 468<br/>13.9.1 Empirical Insights 468<br/>13.9.2 Loop Closure 471<br/>13.10 Grid-based FastSLAM 474<br/>13.10.1 The Algorithm 474<br/>13.10.2 Empirical Insights 475<br/>IV Planning and Control 485<br/>14 Markov Decision Processes 487<br/>14.1 Motivation 487<br/>14.2 Uncertainty in Action Selection 490<br/>14.3 Value Iteration 495<br/>14.3.1 Goals and Payoff 495<br/>14.3.2 Finding Optimal Control Policies for the Fully Observable Case 499<br/>14.3.3 Computing the Value Function 501<br/>14.4 Application to Robot Control 503<br/>15 Partially Observable Markov Decision Processes 513<br/>15.1 Motivation 513<br/>15.2 An Illustrative Example 515<br/>15.2.1 Setup 515<br/>15.2.2 Control Choice 516<br/>15.2.3 Sensing 519<br/>15.2.4 Prediction 523<br/>15.2.5 Deep Horizons and Pruning 526<br/>15.3 The Finite World POMDP Algorithm 527<br/>15.4 Mathematical Derivation of POMDPs 531<br/>15.4.1 Value Iteration in Belief Space 531<br/>15.4.2 Value Function Representation 532<br/>15.4.3 Calculating the Value Function 533<br/>15.5 Practical Considerations 536<br/>16 Approximate POMDP Techniques 547<br/>16.1 Motivation 547<br/>16.2 QMDPs 549<br/>16.3 Augmented Markov Decision Processes 550<br/>16.3.1 The Augmented State Space 550<br/>16.3.2 The AMDP Algorithm 551<br/>16.3.3 Mathematical Derivation of AMDPs 553<br/>16.3.4 Application to Mobile Robot Navigation 556<br/>16.4 Monte Carlo POMDPs 559<br/>16.4.1 Using Particle Sets 559<br/>16.4.2 The MC-POMDP Algorithm 559<br/>16.4.3 Mathematical Derivation of MC-POMDPs 562<br/>16.4.4 Practical Considerations 563<br/>17 Exploration 569<br/>17.1 Introduction 569<br/>17.2 Basic Exploration Algorithms 571<br/>17.2.1 Information Gain 571<br/>17.2.2 Greedy Techniques 572<br/>17.2.3 Monte Carlo Exploration 573<br/>17.2.4 Multi-Step Techniques 575<br/>17.3 Active Localization 575<br/>17.4 Exploration for Learning Occupancy Grid Maps 580<br/>17.4.1 Computing Information Gain 580<br/>17.4.2 Propagating Gain 585<br/>17.4.3 Extension to Multi-Robot Systems 587<br/>17.5 Exploration for SLAM 593<br/>17.5.1 Entropy Decomposition in SLAM 593<br/>17.5.2 Exploration in FastSLAM 594<br/>17.5.3 Empirical Characterization 598<br/> |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | SISTEMAS DE CONTROL-MATEMATICA |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | ROBOTICS |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | PROBABILITIES |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | ROBOTICA |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | SISTEMAS DE CONTROL |
650 ## - Punto de acceso adicional de materia - Término de materia | |
Término de materia | MATEMATICA-SISTEMAS DE CONTROL |
700 1# - Punto de acceso adicional - Nombre de persona | |
Nombre personal | Burgard, Wolfram |
700 1# - Punto de acceso adicional - Nombre de persona | |
Nombre personal | Fox, Dieter |
942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
Tipo de ítem Koha | Libro |
Esquema de clasificación | Clasificación Decinal Universal |
Estado | Estado perdido | Estado de conservación | Tipo de préstamo | Biblioteca | Biblioteca | Fecha de adquisición | Origen de la adquisición | Número de inventario | Total Checkouts | ST completa de Koha | Código de barras | Date last seen | Precio efectivo a partir de | Tipo de ítem Koha |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Sólo Consulta | Facultad Regional Santa Fe - Biblioteca "Rector Comodoro Ing. Jorge Omar Conca" | Facultad Regional Santa Fe - Biblioteca "Rector Comodoro Ing. Jorge Omar Conca" | 02/02/2018 | Compra Exp.N°29/2011 CIDISI P25/128 Leone | 10541 | 519.71 T417 | 10541 | 02/02/2018 | 02/02/2018 | Libro |