Szuster / Hendzel Intelligent Optimal Adaptive Control for Mechatronic Systems

1. Auflage 2018
ISBN: 978-3-319-68826-8
Verlag: Springer Nature Switzerland
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 120, 387 Seiten

Reihe: Studies in Systems, Decision and Control

The book deals with intelligent control of mobile robots, presenting the state-of-the-art in the field, and introducing new control algorithms developed and tested by the authors. It also discusses the use of artificial intelligent methods like neural networks and neuraldynamic programming, including globalised dual-heuristic dynamic programming, for controlling wheeled robots and robotic manipulators,and compares them to classical control methods.

Autoren/Hrsg.

Szuster, Marcin

Hendzel, Zenon

Inhaltsverzeichnis

1;Contents;7
2;1 Introduction;12
2.1;1.1 Artificial Intelligence and Neural Networks;15
2.2;1.2 Learning with a Critic;16
2.3;1.3 Scope of Study;17
2.4;References;20
3;2 Object of Research;22
3.1;2.1 Two-Wheeled Mobile Robot;22
3.1.1;2.1.1 Description of the Kinematics of a Mobile Robot;23
3.1.2;2.1.2 Description of the Dynamics of a Mobile Robot;32
3.2;2.2 Robotic Manipulator;42
3.2.1;2.2.1 Description of the Kinematics of a Robotic Manipulator;43
3.2.2;2.2.2 Description of the Dynamics of a Robotic Manipulator;52
3.3;References;60
4;3 Intelligent Control of Mechatronic Systems;62
4.1;3.1 Methods for Control of Nonlinear Systems;62
4.2;3.2 Neural Control;65
4.2.1;3.2.1 Random Vector Functional Link Neural Network;67
4.2.2;3.2.2 Neural Network with Gaussian-Type Activation Functions;68
4.3;References;69
5;4 Optimal Control Methods for Mechatronic Systems;71
5.1;4.1 Bellman's Dynamic Programming;71
5.2;4.2 Linear-Quadratic Regulator;75
5.3;4.3 Pontryagin's Maximum Principle;81
5.4;4.4 Summary;90
5.5;References;93
6;5 Learning Methods for Intelligent Systems;94
6.1;5.1 Supervised Learning;94
6.1.1;5.1.1 Steepest Descent Algorithm;95
6.1.2;5.1.2 Variable Metric Algorithm;96
6.1.3;5.1.3 Levenberg--Marquardt Algorithm;97
6.1.4;5.1.4 Conjugate Gradient Method;98
6.2;5.2 Learning with a Critic;99
6.2.1;5.2.1 Q-Learning Algorithm;101
6.3;5.3 Learning Without a Teacher;102
6.3.1;5.3.1 Winner-Take-All Networks;102
6.3.2;5.3.2 Winner-Take-Most Networks;103
6.4;References;104
7;6 Adaptive Dynamic Programming - Discrete Version;105
7.1;6.1 Neural Dynamic Programming;105
7.2;6.2 Model-Based Learning Methods;109
7.2.1;6.2.1 Heuristic Dynamic Programming;110
7.2.2;6.2.2 Dual-Heuristic Dynamic Programming;114
7.2.3;6.2.3 Global Dual-Heuristic Dynamic Programming;125
7.3;6.3 Model-Free Learning Methods;128
7.3.1;6.3.1 Action-Dependent Heuristic Dynamic Programming;128
7.4;References;131
8;7 Control of Mechatronic Systems;135
8.1;7.1 Tracking Control of a WMR and a RM with a PD Controller;137
8.1.1;7.1.1 Synthesis of PD-Type Control;138
8.1.2;7.1.2 Simulation Tests;138
8.1.3;7.1.3 Conclusions;148
8.2;7.2 Adaptive Tracking Control of a WMR;148
8.2.1;7.2.1 Synthesis of an Adaptive Control Algorithm;149
8.2.2;7.2.2 Simulation Tests;152
8.2.3;7.2.3 Conclusions;156
8.3;7.3 Neural Tracking Control of a WMR;156
8.3.1;7.3.1 Synthesis of a Neural Control Algorithm;156
8.3.2;7.3.2 Simulation Tests;160
8.3.3;7.3.3 Conclusions;164
8.4;7.4 Heuristic Dynamic Programming in Tracking Control of a WMR;164
8.4.1;7.4.1 Synthesis of HDP-Type Control;165
8.4.2;7.4.2 Simulation Tests;171
8.4.3;7.4.3 Conclusions;182
8.5;7.5 Dual-Heuristic Dynamic Programming in Tracking Control of a WMR and a RM;183
8.5.1;7.5.1 Synthesis of DHP-Type Control;183
8.5.2;7.5.2 Simulation Tests;190
8.5.3;7.5.3 Conclusions;203
8.6;7.6 Globalised Dual-Heuristic Dynamic Programming in Tracking Control of a WMR and a RM;203
8.6.1;7.6.1 Synthesis of GDHP-Type Control;204
8.6.2;7.6.2 Simulation Tests;210
8.6.3;7.6.3 Conclusions;222
8.7;7.7 Action Dependent Heuristic Dynamic Programming in Tracking Control of a WMR;222
8.7.1;7.7.1 Synthesis of ADHDP-type Control;223
8.7.2;7.7.2 Simulation Tests;226
8.7.3;7.7.3 Conclusions;231
8.8;7.8 Behavioural Control of WMR's Motion;232
8.8.1;7.8.1 Behavioural Control Synthesis;236
8.8.2;7.8.2 Simulation Tests;242
8.8.3;7.8.3 Conclusions;249
8.9;7.9 Summary;250
8.9.1;7.9.1 Selection of Value of the Future Reward Discount Factor ?;256
8.10;References;257
9;8 Reinforcement Learning in the Control of Nonlinear Continuous Systems;262
9.1;8.1 Classical Reinforcement Learning;263
9.1.1;8.1.1 Control Synthesis, Stability of a System, Reinforcement Learning Algorithm;263
9.1.2;8.1.2 Simulation Tests;268
9.1.3;8.1.3 Conclusions;273
9.2;8.2 Approximation of Classical Reinforcement Learning;273
9.2.1;8.2.1 Control System Synthesis, Stability of the System, Reinforcement Learning Algorithm;274
9.2.2;8.2.2 Simulation Tests;276
9.2.3;8.2.3 Conclusions;277
9.3;8.3 Reinforcement Learning in the Actor-Critic Structure;278
9.3.1;8.3.1 Synthesis of Control System, System Stability, Reinforcement Learning Algorithm;279
9.3.2;8.3.2 Simulation Tests;284
9.3.3;8.3.3 Conclusions;287
9.4;8.4 Reinforcement Learning of Actor-Critic Type in the Optimal Adaptive Control;287
9.4.1;8.4.1 Control Synthesis, Stability of a System, Reinforcement Learning Algorithm;287
9.4.2;8.4.2 Simulation Tests;291
9.4.3;8.4.3 Conclusions;293
9.5;8.5 Implementation of Critic's Adaptive Structure in Optimal Control;294
9.5.1;8.5.1 Control Synthesis, Critic's Learning Algorithm, Stability of a System;294
9.5.2;8.5.2 Simulation Tests;299
9.5.3;8.5.3 Conclusions;302
9.6;References;303
10;9 Two-Person Zero-Sum Differential Games and Hinfty Control;305
10.1;9.1 Hinfty control;305
10.2;9.2 A Two-Person Zero-Sum Differential Game;307
10.3;9.3 Application of a Two-Person Zero-Sum Differential Game in Control of the Drive Unit of a WMR;308
10.3.1;9.3.1 Simulation Tests;309
10.3.2;9.3.2 Conclusions;314
10.4;9.4 Application of a Neural Network in the Two-Person Zero-Sum Differential Game in WMR Control;314
10.4.1;9.4.1 Simulation Tests;318
10.4.2;9.4.2 Conclusions;321
10.5;References;322
11;10 Experimental Verification of Control Algorithms;323
11.1;10.1 Description of Laboratory Stands;323
11.1.1;10.1.1 WMR Motion Control Stand;323
11.1.2;10.1.2 RM Motion Control Stand;325
11.2;10.2 Analysis of the PD Control;327
11.2.1;10.2.1 Analysis of the WMR Motion Control;327
11.2.2;10.2.2 Analysis of the RM Motion Control;332
11.2.3;10.2.3 Conclusions;334
11.3;10.3 Analysis of the Adaptive Control;335
11.3.1;10.3.1 Analysis of the WMR Motion Control;335
11.3.2;10.3.2 Conclusions;339
11.4;10.4 Analysis of the Neural Control;339
11.4.1;10.4.1 Analysis of the WMR Motion Control;339
11.4.2;10.4.2 Conclusions;343
11.5;10.5 Analysis of the HDP Control;343
11.5.1;10.5.1 Analysis of the WMR Motion Control;343
11.5.2;10.5.2 Conclusions;352
11.6;10.6 Analysis of the DHP Control;353
11.6.1;10.6.1 Analysis of the WMR Motion Control;353
11.6.2;10.6.2 Analysis of the RM Motion Control;358
11.6.3;10.6.3 Conclusions;363
11.7;10.7 Analysis of the GDHP Control;363
11.7.1;10.7.1 Analysis of the WMR Motion Control;364
11.7.2;10.7.2 Conclusions;368
11.8;10.8 Analysis of the ADHDP Control;368
11.8.1;10.8.1 Analysis of the WMR Motion Control;368
11.8.2;10.8.2 Conclusions;372
11.9;10.9 Analysis of Behavioral Control;372
11.9.1;10.9.1 Analysis of the WMR Motion Control;374
11.9.2;10.9.2 Conclusions;378
11.10;10.10 Summary;379
11.11;References;385
12;11 Summary;386