E-Book, Englisch, 243 Seiten
Filipe / Ferrier / Cetto Informatics in Control, Automation and Robotics II
1. Auflage 2007
ISBN: 978-1-4020-5626-0
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark
E-Book, Englisch, 243 Seiten
ISBN: 978-1-4020-5626-0
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark
This book is a collection of the best papers presented at the 2nd International Conference on Informatics in Control, Automation and Robotics (ICINCO). ICINCO brought together researchers, engineers and practitioners interested in the application of informatics to Control, Automation and Robotics. The research papers focused on real world applications, covering three main themes: Intelligent Control Systems, Optimization, Robotics and Automation and Signal Processing, Systems Modeling and Control.
Autoren/Hrsg.
Weitere Infos & Material
1;TABLE OF CONTENTS;5
2;PREFACE;9
3;CONFERENCE COMMITTEE;11
4;INVITED SPEAKERS;15
5;Invited Speakers;17
5.1;COMBINING HUMAN & MACHINE BRAINS;18
5.1.1;1 INTRODUCTION;18
5.1.2;2 AUGMENTATION;20
5.1.3;3 EXPERIMENTATION;21
5.1.4;4 CONCLUSIONS;22
5.1.5;ACKNOWLEDGEMENTS;23
5.1.6;REFERENCES;23
5.1.7;BRIEF BIOGRAPHY;23
5.2;REDUNDANCY: THE MEASUREMENT CROSSING CUTTING-EDGE TECHNOLOGIES;26
5.2.1;1 WIDE ASSORTMENT OF MATHEMATICAL EXPRESSIONS;26
5.2.2;2 PRELIMINARIES;27
5.2.3;3 REDUNDANT IS ABUNDANT;28
5.2.4;4 REDUNDANCY IN DIGITAL TECHNIQUES;29
5.2.5;5 CONCLUSIONS;30
5.2.6;REFERENCES;31
5.2.7;BRIEF BIOGRAPHY;31
5.3;HYBRID DYNAMIC SYSTEMS;32
5.3.1;1 INTRODUCTION;32
5.3.2;2 VERIFICATION OF HYBRID SYSTEMS;33
5.3.3;3 HYBRID REACHABILITY;35
5.3.4;4 DISCRETE EVENT ABSTRACTION;37
5.3.5;5 CONTINUOUS EXPANSION COMPUTATION;38
5.3.6;6 CONCLUSIONS;39
5.3.7;REFERENCES;40
5.3.8;BRIEF BIOGRAPHY;41
5.4;TARGET LOCALIZATION USING MACHINE LEARNING;42
5.4.1;1 INTRODUCTION TO SENSOR NETWORKS;42
5.4.2;2 LOCALIZATION IN SENSOR NETWORKS;43
5.4.3;REFERENCES;47
5.4.4;BRIEF BIOGRAPHY;48
6;PART 1 Intelligent Control Systems and Optimization;50
6.1;MODEL PREDICTIVE CONTROL FOR DISTRIBUTED PARAMETER SYSTEMS USING RBF NEURAL NETWORKS;52
6.1.1;1 INTRODUCTION;52
6.1.2;2 RBF NEURAL NETWORKS FOR MODELING DISTRIBUTED PARAMETER SYSTEMS;53
6.1.3;3 NONLINEAR MPC FOR DPS;54
6.1.4;4 APPLICATION;54
6.1.5;5 CONCLUSIONS;56
6.1.6;REFERENCES;57
6.2;FUZZY DIAGNOSIS MODULE BASED ON INTERVAL FUZZY LOGIC: OIL ANALYSIS APPLICATION;58
6.2.1;1 INTRODUCTION;58
6.2.2;2 THE FUZZY CONDITION MONITORING MODULE;59
6.2.3;3 OIL ANALYSIS APPLICATION;62
6.2.4;4 CONCLUSIONS;64
6.2.5;ACKNOWLEDGEMENTS;64
6.2.6;REFERENCES;64
6.3;DERIVING BEHAVIOR FROM GOAL STRUCTURE FOR THE INTELLIGENT CONTROL OF PHYSICAL SYSTEMS;66
6.3.1;1 INTRODUCTION;66
6.3.2;2 FOUNDATIONS FOR THE MODELLING OF CONTROL SYSTEMS RELATED TO ENGINEERING PROCESSES;67
6.3.3;3 THE TARGET APPLICATION;69
6.3.4;4 THE CONCEPTUAL GOAL HIERARCHY;69
6.3.5;5 BEHAVIOR REPRESENTATION;70
6.3.6;6 RELATED WORK;72
6.3.7;7 CONCLUSIONS;72
6.3.8;REFERENCES;72
6.4;EVOLUTIONARY COMPUTATION FOR DISCRETE AND CONTINUOUS TIME OPTIMAL CONTROL PROBLEMS;74
6.4.1;1 INTRODUCTION;74
6.4.2;2 OPTIMAL CONTROL OF DISCRETE TIME NONLINEAR SYSTEMS;75
6.4.3;3 VELOCITY DIRECTION CONTROL OF A BODY IN A VISCOUS FLUID;77
6.4.4;4 EVOLUTIONARY APPROACH TO OPTIMAL CONTROL;79
6.4.5;5 NONLINEAR CONTINUOUS TIME OPTIMAL CONTROL;80
6.4.6;6 GODDARD’S OPTIMAL CONTROL PROBLEM IN ROCKET DYNAMICS;81
6.4.7;7 CONCLUSIONS;82
6.4.8;REFERENCES;83
6.5;CONTRIBUTORS TO A SIGNAL FROM AN ARTIFICIAL CONTRAST;86
6.5.1;1 INTRODUCTION;86
6.5.2;2 CONTROL REGION DESIGN;87
6.5.3;3 CONTRIBUTORS TO A SIGNAL;88
6.5.4;4 ILLUSTRATIVE EXAMPLE;89
6.5.5;5 MANUFACTURING EXAMPLE;91
6.5.6;6 CONCLUSIONS;92
6.5.7;REFERENCES;93
6.6;REAL-TIME TIME-OPTIMAL CONTROL FOR A NONLINEAR CONTAINER CRANE USING A NEURAL NETWORK;94
6.6.1;1 INTRODUCTION;94
6.6.2;2 CRANE MODEL;94
6.6.3;3 TIME-OPTIMAL CONTROL;95
6.6.4;4 NEURAL NETWORK;97
6.6.5;5 DISCUSSION;98
6.6.6;REFERENCES;98
7;PART 2 Robotics and Automation;101
7.1;IMAGE-BASED AND INTRINSIC-FREE VISUAL NAVIGATION OF A MOBILE ROBOT DEFINED AS A GLOBAL VISUAL SERVOING TASK;102
7.1.1;1 INTRODUCTION;102
7.1.2;2 AUTONOMOUS NAVIGATION USING VISUAL SERVOING TECHNIQUES;102
7.1.3;3 DISCONTINUITIES IN VISUAL NAVIGATION;103
7.1.4;4 CONTINUOUS CONTROL LAW FOR NAVIGATION;104
7.1.5;5 EXPERIMENTS IN A VIRTUAL INDOOR ENVIRONMENT;106
7.1.6;6 CONCLUSIONS;107
7.1.7;ACKNOWLEDGEMENTS;107
7.1.8;REFERENCES;108
7.2;SYNTHESIZING DETERMINISTIC CONTROLLERS IN SUPERVISORY CONTROL;110
7.2.1;1 INTRODUCTION;110
7.2.2;2 SUPERVISORY CONTROL THEORY;111
7.2.3;3 CONTROLLER SYNTHESIS;113
7.2.4;4 CONTROLLER SYNTHESIS ALGORITHM;114
7.2.5;5 CONCLUSION;117
7.2.6;REFERENCES;117
7.3;AN UNCALIBRATED APPROACH TO TRACK TRAJECTORIES USING VISUAL–FORCE CONTROL;118
7.3.1;1 INTRODUCTION;118
7.3.2;2 NOTATION;119
7.3.3;3 VISUAL TRACKING OF TRAJECTORIES;119
7.3.4;4 FUSION VISUAL-FORCE CONTROL;119
7.3.5;5 MANAGING CONTRADICTORY CONTROL ACTIONS;120
7.3.6;6 AUTOCALIBRATION;121
7.3.7;7 RESULTS;122
7.3.8;8 CONCLUSIONS;123
7.3.9;REFERENCES;123
7.4;A STRATEGY FOR BUILDING TOPOLOGICAL MAPS THROUGH SCENE OBSERVATION;124
7.4.1;1 INTRODUCTION;124
7.4.2;2 OVERALL LEARNING SYSTEM;125
7.4.3;3 EXPERIMENTAL RESULTS;128
7.4.4;4 ENLARGING THE MAP;129
7.4.5;5 CONCLUSIONS AND FUTURE WORK;129
7.4.6;REFERENCES;130
7.5;A SWITCHING ALGORITHM FOR TRACKING EXTENDED TARGETS;132
7.5.1;1 INTRODUCTION AND RELATED WORK;132
7.5.2;2 THE MATHEMATICAL BACKGROUD OF THE ALGORITHMS;133
7.5.3;3 EVALUATION OF THE ALGORITHMS;135
7.5.4;4 THE PROBLEM OF CROSSING TARGETS;138
7.5.5;5 A NEW SWITCHING ALGORITHM;140
7.5.6;6 THE SWITCHING ALGORITHM COMPARED TO THE SJPDAF;141
7.5.7;7 CONCLUSIONS;142
7.5.8;REFERENCES;143
7.6;SFM FOR PLANAR SCENES: A DIRECT AND ROBUST APPROACH;144
7.6.1;1 INTRODUCTION;144
7.6.2;2 BACKGROUND;144
7.6.3;3 A TWO-STEP APPROACH;145
7.6.4;4 A ONE-STEP APPROACH;147
7.6.5;5 THE DERIVATIVES;147
7.6.6;6 EXPERIMENTS;148
7.6.7;7 CONCLUSION;150
7.6.8;REFERENCES;150
7.7;COMBINING TWO METHODS TO ACCURATELY ESTIMATE DENSE DISPARITY MAPS;152
7.7.1;1 INTRODUCTION;152
7.7.2;2 GRAPH-CUTS METHOD;152
7.7.3;3 ENERGY BASED METHOD;153
7.7.4;4 COMBINING GRAPH-CUTS AND STEREOFLOWMETHOD;153
7.7.5;5 EXPERIMENTAL RESULTS;154
7.7.6;6 CONCLUSIONS;157
7.7.7;ACKNOWLEDGEMENTS;158
7.7.8;REFERENCES;158
7.8;PRECISE DEAD-RECKONING FOR MOBILE ROBOTS USING MULTIPLE OPTICAL MOUSE SENSORS;160
7.8.1;1 INTRODUCTION;160
7.8.2;2 OPTICAL MOUSE SENSOR;161
7.8.3;3 DEAD-RECKONING BASED ON OPTICAL MOUSE SENSORS;161
7.8.4;4 EXPERIMENTS;162
7.8.5;5 CONCLUSION;166
7.8.6;REFERENCES;166
7.9;IMAGE BINARISATION USING THE EXTENDED KALMAN FILTER;168
7.9.1;1 INTRODUCTION;168
7.9.2;2 BINARISATION TECHNIQUES;168
7.9.3;3 LINE TRACKING;170
7.9.4;4 TESTING AND RESULTS;172
7.9.5;5 CONCLUSION;177
7.9.6;ACKNOWLEDGEMENTS;177
7.9.7;REFERENCES;177
7.10;LOWER LIMB PROSTHESIS: FINAL PROTOTYPE RELEASE AND CONTROL SETTING METHODOLOGIES;178
7.10.1;1 INTRODUCTION;178
7.10.2;2 DESIGN METHOD OF THE M-LEG SYSTEM;179
7.10.3;3 ACTUAL RELEASE OF ARTIFICIAL LIMB PROSTHESIS. FROM DESIGN METHOD TO COMPONENT DESIGN;180
7.10.4;4 CONTROL STATEMENTS METHODOLOGY;182
7.10.5;5 CONCLUSIONS;187
7.10.6;ACKNOWLEDGEMENTS;187
7.10.7;REFERENCES;187
7.11;DIRECT GRADIENT-BASED REINFORCEMENT LEARNING FOR ROBOT BEHAVIOR LEARNING;190
7.11.1;1 INTRODUCTION;190
7.11.2;2 THE RLDPS ALGORITHM;191
7.11.3;3 CASE TO STUDY: TARGET FOLLOWING;193
7.11.4;4 SIMULATED RESULTS;194
7.11.5;ACKNOWLEDGEMENTS;196
7.11.6;REFERENCES;196
8;PART 3 Signal Processing, Systems Modeling and Control;199
8.1;PERFORMANCE ANALYSIS OF TIMED EVENT GRAPHS WITH MULTIPLIERS USING (Min, +) ALGEBRA;200
8.1.1;1 INTRODUCTION;200
8.1.2;2 RECURRENT EQUATIONS OF TEGM’s;201
8.1.3;3 LINEARIZATION OF TEGM’S;202
8.1.4;4 PERFORMANCE EVALUATION;203
8.1.5;5 CONCLUSION;204
8.1.6;REFERENCES;204
8.2;MODELING OF MOTOR NEURONAL STRUCTURES VIA TRANSCRANIAL MAGNETIC STIMULATION;206
8.2.1;1 INTRODUCTION;206
8.2.2;2 DATA ANALYSIS;207
8.2.3;3 NEURONAL MODELS;209
8.2.4;4 MODEL VALIDATION;210
8.2.5;5 CONCLUSIONS;211
8.2.6;ACKNOWLEDGEMENTS;212
8.2.7;REFERENCES;212
8.3;ANALYSIS AND SYNTHESIS OF DIGITAL STRUCTURE BY MATRIX METHOD;214
8.3.1;1 INTRODUCTION;214
8.3.2;2 ANALYSIS OF THE SECOND ORDER STATE-SPACE DIGITAL FILTER;215
8.3.3;3 DESIGN OF THE THIRD ORDER STATE-SPACE STRUCTURE;216
8.3.4;4 EXAMPLES;217
8.3.5;5 CONCLUSION;221
8.3.6;REFERENCES;221
8.4;ANN-BASED MULTIPLE DIMENSION PREDICTOR FOR SHIP ROUTE PREDICTION;222
8.4.1;1 INTRODUCTION;222
8.4.2;2 PRINCIPLE OF ANN-BASED PREDICTOR;223
8.4.3;3 DRNN PREDICTIVE MODELS;224
8.4.4;4 PDRNN BASED MULTIPLE DIMENSION PREDICTOR;225
8.4.5;5 THE LEARNING ALGORITHM;227
8.4.6;6 SIMULATIONS AND APPLICATION;228
8.4.7;7 CONCLUSIONS;229
8.4.8;REFERENCES;229
8.5;A PARAMETERIZED POLYHEDRA APPROACH FOR THE EXPLICIT ROBUST MODEL PREDICTIVE CONTROL;232
8.5.1;1 INTRODUCTION;232
8.5.2;2 ROBUST MPC FORMULATION;233
8.5.3;3 ROBUST MPC AS A MULTI-PARAMETRIC OPTIMIZATION;234
8.5.4;4 THE EXPLICIT SOLUTION;235
8.5.5;5 EXAMPLE;238
8.5.6;6 CONCLUSION;240
8.5.7;REFERENCES;240
8.6;A NEW HIERARCHICAL CONTROL SCHEME FOR A CLASS OF CYCLICALLY REPEATED DISCRETE-EVENT SYSTEMS;242
8.6.1;1 INTRODUCTION;242
8.6.2;2 SUPERVISORY LEVEL;243
8.6.3;3 C/D BLOCK;246
8.6.4;4 IMPLEMENTATION LEVEL;246
8.6.5;5 RAIL TRAFFIC CASE STUDY;247
8.6.6;6 CONCLUSION;248
8.6.7;REFERENCES;248
8.7;WAVELET TRANSFORM MOMENTS FOR FEATURE EXTRACTION FROM TEMPORAL SIGNALS;250
8.7.1;1 INTRODUCTION;250
8.7.2;2 PREHENSILE EMGS;251
8.7.3;3 EXPERIMENTAL SETUP;251
8.7.4;4 DISCRETE WAVELET TRANSFORM;251
8.7.5;5 WAVELET PACKET TRANSFORM;252
8.7.6;6 DWT AND WPT MOMENTS1;252
8.7.7;7 THE SVM CLASSIFIER;253
8.7.8;8 COMPUTATIONAL COMPLEXITY;253
8.7.9;9 EXPERIMENTAL EVALUATION;254
8.7.10;10 THE RESULTS;255
8.7.11;11 CONCLUSIONS;256
8.7.12;REFERENCES;256
9;AUTHOR INDEX;258
COMBINING HUMAN & MACHINE BRAINS (p. 3)
Practical Systems in Information & Control
Kevin Warwick
Department of Cybernetics, University of Reading, Reading, RG6 6AY, United Kingdom
Keywords:
Artificial intelligence, Biological systems, Implant technology, Feedback control.
Abstract:
In this paper a look is taken at how the use of implant technology can be used to either increase the range of the abilities of a human and/or diminish the effects of a neural illness, such as Parkinson’s Disease. The key element is the need for a clear interface linking the human brain directly with a computer.
The area of interest here is the use of implant technology, particularly where a connection is made between technology and the human brain and/or nervous system. Pilot tests and experimentation are invariably carried out apriori to investigate the eventual possibilities before human subjects are themselves involved. Some of the more pertinent animal studies are discussed here.
The paper goes on to describe human experimentation, in particular that carried out by the author himself, which led to him receiving a neural implant which linked his nervous system bi-directionally with the internet. With this in place neural signals were transmitted to various technological devices to directly control them. In particular, feedback to the brain was obtained from the fingertips of a robot hand and ultrasonic (extra) sensory input. A view is taken as to the prospects for the future, both in the near term as a therapeutic device and in the long term as a form of enhancement.
1 INTRODUCTION
Research is presently being carried out in which biological signals of some form are measured, are acted upon by some appropriate signal processing technique and are then employed either to control a device or as an input to some feedback mechanism (e.g. Penny et al., 2000).
In most cases the signals are measured externally to the body, thereby imposing errors into the situation due to problems in understanding intentions and removing noise – partly due to the compound nature of the signals being measured. Many problems also arise when attempting to translate electrical energy from the computer to the electronic signals necessary for stimulation within the human body.
For example, when only external stimulation is employed then it is extremely difficult, if not impossible, to select unique sensory receptor channels, due to the general nature of the stimulation.
Wearable computer and virtual reality techniques provide one route for creating a human-machine link. In the last few years items such as shoes and glasses have been augmented with microprocessors, but perhaps of most interest is research in which a miniature computer screen was fitted onto an otherwise standard pair of glasses in order to give the wearer a remote visual experience in which additional information about an external scene could be relayed (Mann, 1997).
In general though, despite being positioned adjacent to the human body, and even though indications such as stress and alertness can be witnessed, to an extent at least, wearable computers and virtual reality systems require significant signal conversion to take place in order to interface human sensory receptors with technology.
