| Description |
ix, 288 pages : illustrations ; 24 cm |
| Series |
Lecture notes in computer science ; 2048 |
|
Lecture notes in computer science ; 2048
|
| Contents |
1. Introduction -- Need for New-Generation Robot Systems -- Paradigms of Computer Vision (CV) and Robot Vision (RV) -- Robot Systems versus Autonomous Robot Systems -- Important Role of Demonstration and Learning -- 2. Compatibilities for Object Boundary Detection -- Geometric/Photometric Compatibility Principles -- Compatibility-Based Structural Level Grouping -- Compatibility-Based Assembly Level Grouping -- Visual Demonstrations for Learning Degrees of Compatibility -- 3. Manifolds for Object and Situation Recognition -- Learning Pattern Manifolds with GBFs and PCA -- GBF Networks for Approximation of Recognition Functions -- Sophisticated Manifold Approximation for Robust Recognition -- 4. Learning-Based Achievement of RV Competences -- Integrating Deliberate Strategies and Visual Feedback -- Treatment of an Exemplary High-Level Task -- Basic Mechanisms for Camera-Robot Coordination -- 5. Summary and Discussion -- Developing Camera-Equipped Robot Systems -- Rationale for the Contents of This Work -- Proposals for Future Research Topics. App. 1. Ellipsoidal Interpolation -- App. 2. Further Behavioral Modules |
| Summary |
"This book provides the background and introduces a practical methodology for developing autonomous camera equipped robot systems which solve deliberate tasks in open environments based on skills acquired from training, interaction, and learning in the real task relevant world; visual demonstration and neural network learning form the backbone for acquiring these skills. The author verifies the practicability of the proposed methodology by presenting a structured application scenario which includes high-level sub-tasks such as localizing, approaching, grasping, and carrying objects."--BOOK JACKET |
| Bibliography |
Includes bibliographical references |
| Notes |
Also available in print |
|
Mode of access: World Wide Web |
|
Lecture notes in computer science no:2048 0302-9743 |
| Subject |
Robot vision.
|
|
Robots -- Control systems.
|
| LC no. |
2001032281 |
| ISBN |
3540421084 paperback |
|
