| Description |
1 online resource (132 pages) |
| Series |
SpringerBriefs in Applied Sciences and Technology |
|
SpringerBriefs in applied sciences and technology.
|
| Contents |
Preface; Acknowledgements; Contents; 1 Competition Aided with Discrete-Time Dynamic Feedback; 1.1 Introduction; 1.2 Problem Definition; 1.3 Model Formulation; 1.4 Theoretical Results; 1.5 Illustrative Examples; 1.5.1 Discrete-Time Static Competition; 1.5.2 Discrete-Time Dynamic Competition; 1.6 Summary; References; 2 Competition Aided with Continuous-Time Nonlinear Model; 2.1 Introduction; 2.2 The Model; 2.3 Theoretical Analysis and Results; 2.4 Illustrative Examples; 2.4.1 Static Competition; 2.4.2 Dynamic Competition; 2.5 Summary; References |
|
3 Competition Aided with Finite-Time Neural Network3.1 Introduction; 3.2 Model Description; 3.3 Convergence Analysis; 3.4 An Illustrative Example; 3.4.1 Accuracy; 3.4.2 Convergence Speed; 3.4.3 Comparisons on Computational Efficiency in Numerical Simulations; 3.4.4 Sensitivity to Additive Noise; 3.4.5 Robustness Against Time Delay; 3.4.6 Discussion; 3.5 Solving k-WTA with the Proposed Neural Network; 3.5.1 Quadratic Programming Formulation for k-TWA; 3.5.2 Theoretical Results for Solving k-WTA with the Proposed Neural Network; 3.5.3 k-WTA Simulations; 3.6 Summary; References |
|
4 Competition Based on Selective Positive-Negative Feedback4.1 Introduction; 4.2 Preliminaries; 4.3 The Winner-Take-All Neural Network; 4.3.1 The Neural Network Based Winner-Take-All Problem; 4.3.2 Neuro-Dynamics; 4.4 Convergence Results; 4.5 Discussion on One-Sided Competition Versus Closely-Matched Competition; 4.6 Simulation Examples; 4.6.1 Static Competition; 4.6.2 Dynamic Competition; 4.7 Summary; References; 5 Distributed Competition in Dynamic Networks; 5.1 Introduction; 5.2 Problem Definition: Distributed WTA on Graphs; 5.3 Distributed WTA Protocol; 5.3.1 Basic Properties |
|
5.4 Convergence Analysis5.4.1 Global Convergence to the Equilibrium Point Set; 5.4.2 Instability of Non-WTA Solutions; 5.4.3 Global Stability of the WTA Solution; 5.5 Numerical Validation; 5.6 Summary; References; 6 Competition-Based Distributed Coordination Control of Robots; 6.1 Introduction; 6.2 Preliminary and Problem Formulation; 6.2.1 Redundant Robot Manipulator; 6.2.2 Problem Definitions and Assumptions; 6.3 Dynamic Task Allocation with Limited Communications; 6.4 Illustrative Example; 6.5 Summary; References |
| Summary |
Focused on solving competition-based problems, this book designs, proposes, develops, analyzes and simulates various neural network models depicted in centralized and distributed manners. Specifically, it defines four different classes of centralized models for investigating the resultant competition in a group of multiple agents. With regard to distributed competition with limited communication among agents, the book presents the first distributed WTA (Winners Take All) protocol, which it subsequently extends to the distributed coordination control of multiple robots. Illustrations, tables, and various simulative examples, as well as a healthy mix of plain and professional language, are used to explain the concepts and complex principles involved. Thus, the book provides readers in neurocomputing and robotics with a deeper understanding of the neural network approach to competition-based problem-solving, offers them an accessible introduction to modeling technology and the distributed coordination control of redundant robots, and equips them to use these technologies and approaches to solve concrete scientific and engineering problems |
| Bibliography |
Includes bibliographical references |
| Notes |
Print version record |
| Subject |
Neural networks
|
|
Robotics.
|
|
Robotics
|
|
Robotics.
|
|
Artificial intelligence.
|
|
Mathematical modelling.
|
|
COMPUTERS -- General.
|
|
Neural networks (Computer science)
|
|
Robotics
|
| Form |
Electronic book
|
| Author |
Jin, Long
|
| ISBN |
9789811049477 |
|
9811049475 |
|
