What is included with this book?
Introduction | p. 1 |
Applications of SLAM | p. 1 |
Joint Estimation | p. 2 |
Posterior Estimation | p. 3 |
The Extended Kalman Filter | p. 5 |
Quadratic Complexity | p. 5 |
Single-Hypothesis Data Association | p. 6 |
Structure and Sparsity in SLAM | p. 7 |
FastSLAM | p. 8 |
Logarithmic Complexity | p. 10 |
Multi-hypothesis Data Association | p. 10 |
Outline | p. 11 |
The SLAM Problem | p. 13 |
Problem Definition | p. 13 |
SLAM Posterior | p. 15 |
SLAM as a Markov Chain | p. 16 |
Bayes Filter Derivation | p. 17 |
Extended Kalman Filtering | p. 18 |
Scaling SLAM Algorithms | p. 20 |
Submap Methods | p. 20 |
Sparse Extended Information Filters | p. 21 |
Thin Junction Trees | p. 22 |
Covariance Intersection | p. 22 |
Graphical Optimization Methods | p. 22 |
Robust Data Association | p. 23 |
Local Map Sequencing | p. 24 |
Joint Compatibility Branch and Bound | p. 24 |
Combined Constraint Data Association | p. 25 |
Iterative Closest Point | p. 25 |
Multiple Hypothesis Tracking | p. 25 |
Comparison of FastSLAM to Existing Techniques | p. 26 |
FastSLAM 1.0 | p. 27 |
Particle Filtering | p. 27 |
Factored Posterior Representation | p. 29 |
Proof of the FastSLAM Factorization | p. 30 |
The FastSLAM 1.0 Algorithm | p. 32 |
Sampling a New Pose | p. 33 |
Updating the Landmark Estimates | p. 35 |
Calculating Importance Weights | p. 37 |
Importance Resampling | p. 38 |
Robot Path Posterior Revisited | p. 39 |
FastSLAM with Unknown Data Association | p. 39 |
Data Association Uncertainty | p. 39 |
Per-Particle Data Association | p. 41 |
Adding New Landmarks | p. 43 |
Summary of the FastSLAM Algorithm | p. 44 |
FastSLAM Extensions | p. 46 |
Greedy Mutual Exclusion | p. 46 |
Feature Elimination Using Negative Evidence | p. 47 |
Log(N) FastSLAM | p. 48 |
Garbage Collection | p. 50 |
Unknown Data Association | p. 51 |
Experimental Results | p. 51 |
Victoria Park | p. 52 |
Comparison of FastSLAM and the EKF | p. 56 |
Ambiguous Data Association | p. 59 |
Sample Impoverishment | p. 59 |
Summary | p. 62 |
FastSLAM 2.0 | p. 63 |
Sample Impoverishment | p. 63 |
FastSLAM 2.0 | p. 65 |
The New Proposal Distribution | p. 66 |
Calculating the Importance Weights | p. 69 |
FastSLAM 2.0 Overview | p. 71 |
Handling Simultaneous Observations | p. 71 |
FastSLAM 2.0 Convergence | p. 74 |
Convergence Proof | p. 75 |
Experimental Results | p. 79 |
FastSLAM 1.0 Versus FastSLAM 2.0 | p. 79 |
One Particle FastSLAM 2.0 | p. 81 |
Scaling Performance | p. 83 |
Loop Closing | p. 83 |
Convergence Speed | p. 85 |
Grid-Based FastSLAM | p. 87 |
Summary | p. 90 |
Dynamic Environments | p. 91 |
SLAM with Dynamic Landmarks | p. 92 |
Derivation of the Bayes Filter with Dynamic Objects | p. 93 |
Factoring the Dynamic SLAM Problem | p. 95 |
Simultaneous Localization and People Tracking | p. 96 |
Comparison with Prior Work | p. 97 |
FastSLAP Implementation | p. 97 |
Scan-Based Data Association | p. 98 |
Measurement Model | p. 100 |
Motion Model | p. 101 |
Model Selection | p. 101 |
Experimental Results | p. 102 |
Tracking and Model Selection Accuracy | p. 102 |
Global Uncertainty | p. 103 |
Intelligent Following Behavior | p. 103 |
Summary | p. 105 |
Conclusions | p. 107 |
Conclusion | p. 107 |
Limitations of FastSLAM | p. 108 |
Future Work | p. 109 |
References | p. 111 |
Index | p. 117 |
Table of Contents provided by Ingram. All Rights Reserved. |
The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.
The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.