Screen LibraryReliable plan selection by intelligent machines /
This book derives techniques which allow reliable plans to be automatically selected by Intelligent Machines. It concentrates on the uncertainty analysis of candidate plans so that a highly reliable candidate may be identified and used. For robotic components, such as a particular vision algorithm f...
Saved in:
| Main Authors: | |
|---|---|
| Corporate Authors: | |
| Group Author: | ; |
| Published: |
World Scientific Pub. Co.,
|
| Publisher Address: | Singapore : |
| Publication Dates: | 1995. |
| Literature type: | eBook |
| Language: | English |
| Series: |
Series in intelligent control and intelligent automation ;
vol. 1 |
| Subjects: | |
| Online Access: |
http://www.worldscientific.com/worldscibooks/10.1142/2819#t=toc |
| Summary: |
This book derives techniques which allow reliable plans to be automatically selected by Intelligent Machines. It concentrates on the uncertainty analysis of candidate plans so that a highly reliable candidate may be identified and used. For robotic components, such as a particular vision algorithm for pose estimation or a joint controller, methods are explained for directly calculating the reliability. However, these methods become excessively complex when several components are used together to complete a plan. Consequently, entropy minimization techniques are used to estimate which complex tasks will perform reliably. The book first develops tools for directly calculating the reliability of sub-systems, and methods of using entropy minimization to greatly facilitate the analysis are explained. Since these sub-systems are used together to accomplish complex tasks, the book then explains how complex tasks can be efficiently evaluated. |
| Carrier Form: | 1 online resource (ix,154pages) : illustrations. |
| Bibliography: | Includes bibliographical references (pages 147-152) and index. |
| ISBN: | 9789812830791 |
| Index Number: | TJ217 |
| CLC: | TP242.602 |
| Contents: | 1. Selecting reliable plans: An introduction. 1.1. Motivation. 1.2. The theory of intelligent machines. 1.3. Overview of the approach. 1.4. Book organization -- 2. Calculating reliability in multi-dimensional systems. 2.1. Calculation of reliability terms. 2.2. Monte Carlo simulation. 2.3. Maximum likelihood estimation. 2.4. Computation of a reliability index. 2.5. Converting tolerance specifications to quadratic specifications. 2.6. Calculation of reliability bounds. 2.7. Covariance matrix propagation -- 3. A review of entropy methods. 3.1. Entropy concepts. 3.2. Jaynes' principle of maximum entropy. 3.3. Entropy in intelligent control. 3.4. Entropy invariant features. 3.5. Selecting reliable sub-plans -- 4. Application to pose algorithms. 4.1. Introduction. 4.2. Problem definition. 4.3. An algorithm for pose selection. 4.4. Case study. 4.5. Conclusions -- 5. Reliability optimization of single-input control systems. 5.1. Introduction. 5.2. Reliability as a performance measure. 5.3. Reliability optimization for single-input linear discrete-time systems. 5.4. Reliability optimization for single-input linear continuous-time systems. 5.5. Examples. 5.6. Conclusion -- 6. Reliability eestimation techniques. 6.1. Justification for estimation techniques. 6.2. Entropy as a reliability estimate. 6.3. The lower-bound method. 6.4. The loose-bound method. 6.5. Discussion of the proposed method -- 7. Reliability estimation for complex tasks and systems. 7.1. Combination of reliability measures. 7.2. Combination of entropy measures. 7.3. Formulation of reliability-based control. 7.4. Search techniques using the entropy measures -- 8. Case study: Robotic assembly system. 8.1. Intelligent control of a PUMA 560. 8.2. Alternative plan generation. 8.3. Intelligent controller operation. 8.4. Application of reliability improvement techniques. 8.5. Summary of the case study -- 9. Reflections on the state of the art. 9.1. The scope of current research. 9.2. Limitations of current research and suggested directions. 9.3. Conclusions. |