Librería Portfolio

In this book, we look at how cluster technology can be leveraged to build better robots. Algorithms and approaches in key areas of robotics and computer vision, such as map building, target tracking, action selection and landmark learning, are reviewed and cluster implementations for these are presented.The objective of the book is to give professionals working in the beowulf cluster or robotics and computer vision fields a concrete view of the strong synergy between the areas as well as to spur further fruitful exploitation of this connection. The book is written at a level appropriate for an advanced undergraduate or graduate student. The key concepts in robotics, computer vision and cluster computing are introduced before being used to make the text useful to a wide audience in these fields.



Table of Contents:
Dedication -- Prefacevii -- List of Tables -- List of Figures -- 1. Introduction -- 1.1. Robots -- 1.2. Cluster Computing -- 1.3. Overview of the Book -- 2. Clusters and Robots -- 2.1. Parallel Computation -- 2.1.1. Parallel Architectures -- 2.1.2. Multiprocessor -- 2.1.3. Multicomputer -- 2.2. Clusters -- 2.2.1. Terminology -- 2.2.2. Cluster Configuration -- 2.2.3. Programming the Cluster -- 2.2.4. Configuring the Cluster -- 2.2.5. Simple Cluster Configuration with Open MPI -- 2.2.6. Connecting the Cluster to the Robot -- 2.3. Summary -- References -- 3. Cluster Programming -- 3.1. Approaches to Parallel Programming -- 3.2. Programming with MPI -- 3.2.1. Message-Passing -- 3.2.2. Single Program Multiple Data(SPMD) Model -- 3.2.3. Collective Communication -- 3.3. Compiling and Running MPI Programs -- 3.4. Analyzing Parallel Computation Time -- 3.4.1. Speedup and Amdhal´s Law -- 3.4.2. Communication and Calculation -- 3.4.3. Communication Models -- 3.5. Summary -- References -- 4. Robot Motion -- 4.1. Motion of a Mobile Robot in Two Dimensions -- 4.2. Calculation of Location by Dead-Reckoning -- 4.2.1. Partitioning: Block Data Decomposition -- 4.2.2. Program Design -- 4.2.3. Analysis -- 4.3. Dead-Reckoning with Intermediate Results -- 4.3.1. Partitioning -- 4.3.2. Program Design -- 4.3.3. Analysis -- 4.4. Dead-Reckoning for a Team of Robots -- 4.4.1. Partitioning -- 4.4.2. Program Design -- 4.4.3. Analysis -- 4.4.4. Local and Global Buffers -- 4.5. Summary -- References -- 5. Sensors -- 5.1. Transforming Sensor Readings -- 5.1.1. Partitioning: Single Robot Location -- 5.1.2. Analysis -- 5.1.3. Partitioning: Multiple Robot Locations -- 5.1.4. Analysis -- 5.2. Drawing a Map from Sonar Data -- 5.2.1. Finding Straight Lines with the Hough Transform -- 5.2.2. Partitioning -- 5.2.3. Program Design -- 5.2.4. Analysis -- 5.2.5. Load Balanced Hough Calculation -- 5.2.6. Analysis -- 5.3. Aligning Laser Scan Measuremens -- 5.3.1. Polar Scan Matching -- 5.3.2. Partitioning and Analysis -- 5.3.3. Program Design -- 5.4. Summary -- References -- 6. Mapping and Localization -- 6.1. Constructing a Spatial Occupancy Map -- 6.1.1. Probabilistic Sonar Model -- 6.1.2. Bayesian Filtering -- 6.1.3. Partitioning by Map -- 6.1.4. Program Design -- 6.1.5. Analysis -- 6.1.6. Partitioning by Sensor Readings -- 6.1.7. Program Design -- 6.1.8. Analysis -- 6.2. Monte-Carlo Localization -- 6.2.1. Partitioning -- 6.2.2. Program Design -- 6.2.3. Analysis -- 6.2.4. Improving the Serial Fraction -- 6.3. Summary -- References -- 7. Vision and Tracking -- 7.1. Following the Road -- 7.2. Iconic Image Processing -- 7.2.1. Partitioning -- 7.2.2. Program Design -- 7.2.3. Analysis -- 7.2.4. Spatial Pixel Operations -- 7.2.5. Partitioning -- 7.2.6. Program Design -- 7.3. Multiscale Image Processing -- 7.3.1. Partitioning -- 7.4. Video Tracking -- 7.4.1. Spatial Histograms -- 7.4.2. Condensation -- 7.4.3. Partitioning -- 7.4.4. Program Design -- 7.5. Summary -- References -- 8. Learning Landmarks -- 8.1. Landmark Spatiograms -- 8.2. K-Means Clustering -- 8.2.1. Partitioning -- 8.2.2. Program Design -- 8.2.3. Analysis -- 8.3. EM Clustering -- 8.3.1. Partitioning -- 8.3.2. Program Design -- 8.3.3. Analysis -- 8.4. Summary -- References -- 9. Robot Architectures -- 9.1. Behavior-Based Robotics -- 9.2. Static Behavior-Based Architecture -- 9.2.1. Partitioning -- 9.2.2. Program Design -- 9.2.3. Analysis -- 9.3. Dynamic Behavior-Based Architecture -- 9.3.1. Program Design -- 9.3.2. Analysis -- 9.4. Summary -- References -- Appendix I. Summary of OpenMPI Man Page for mpirun -- Appendix II. MPI Datatypes -- Appendix III. MPI Reduction Operations -- Appendix IV. MPI Application Programmer Interface -- Bibliography -- Index.