𝔖 Scriptorium
✦   LIBER   ✦

πŸ“

Evolutionary Robotics: From Algorithms to Implementations

✍ Scribed by Lingfeng Wang, Kay Chen Tan, Chee Meng Chew


Publisher
World Scientific Publishing Company
Year
2006
Tongue
English
Leaves
267
Series
World Scientific Series in Robotics and Intelligent Systems
Category
Library

⬇  Acquire This Volume

No coin nor oath required. For personal study only.

✦ Synopsis


This invaluable book comprehensively describes evolutionary robotics and computational intelligence, and how different computational intelligence techniques are applied to robotic system design. It embraces the most widely used evolutionary approaches with their merits and drawbacks, presents some related experiments for robotic behavior evolution and the results achieved, and shows promising future research directions. Clarity of explanation is emphasized such that a modest knowledge of basic evolutionary computation, digital circuits and engineering design will suffice for a thorough understanding of the material. The book is ideally suited to computer scientists, practitioners and researchers keen on computational intelligence techniques, especially the evolutionary algorithms in autonomous robotics at both the hardware and software levels.

✦ Table of Contents


Contents......Page 14
Preface......Page 8
1.1 Introduction......Page 20
1.2 Evolutionary Robotics......Page 23
1.3 Adaptive Autonomous Robot Navigation......Page 27
1.4 Artificial Evolution in Robot Navigation......Page 30
1.4.1 Neural Networks......Page 31
1.4.2 Evolutionary Algorithms......Page 32
1.4.3 Fuzzy Logic......Page 35
1.4.4 Other Methods......Page 36
1.5.1 SAGA......Page 37
1.5.2 Combination of Evolution and Learning......Page 38
1.5.3 Inherent Fault Tolerance......Page 39
1.5.4 Hardware Evolution......Page 40
1.5.5 On-Line Evolution......Page 41
1.5.6 Ubiquitous and Collective Robots......Page 42
1.6 Summary......Page 43
Bibliography......Page 44
2.1 Introduction......Page 52
2.2.1 Basic Concept of EHW......Page 53
2.2.2.1 Artificial evolution and hardware device......Page 54
2.2.2.2 Evolution process......Page 56
2.2.2.4 Application areas......Page 58
2.3 Evolutionary Robotics......Page 59
2.4 Evolvable Hardware in Evolutionary Robotics......Page 61
2.5.1 Promises......Page 69
2.5.2 Challenges......Page 71
2.6 Summary......Page 72
Bibliography......Page 74
3.1 Introduction......Page 82
3.2.2 Evaluation Implementation......Page 85
3.2.3 Genotype Representation......Page 87
3.3.1 Novel Hardware Designs......Page 88
3.3.3 Speed of Execution......Page 90
3.4 EHW-Based Robotic Controller Design......Page 91
3.4.1 Evolvable Hardware......Page 92
3.4.2 Function Unit......Page 94
3.4.3 EHW-Based Robotic Controller Design......Page 95
3.4.3.1 Boolean function controller......Page 97
3.4.3.2 Chromosome representation......Page 98
3.4.3.3 Evolution and adaptation methodology......Page 99
3.5.1 Sensor Information......Page 101
3.5.2 FPGA Turret......Page 103
3.5.2.2 Architecture......Page 104
3.5.2.3 Configuration bits......Page 105
3.5.3 Hardware Configuration......Page 106
3.5.4 Development Platform......Page 108
3.6.1 Preliminary Investigation......Page 110
3.6.2.1 Software structure of light following task......Page 116
3.6.2.2 Program settings of light following task......Page 117
3.6.2.3 Implementation of light source following task......Page 120
3.6.3 Obstacle Avoidance using Robot with a Traction Fault......Page 122
3.6.3.2 Implementation of obstacle avoidance task......Page 125
3.7 Summary......Page 128
Bibliography......Page 132
4.1 Introduction......Page 136
4.2.1 The Khepera Robot and Webots Software......Page 139
4.2.2 Hybrid Architecture of the Controller......Page 142
4.2.3 Function Modules on Khepera Robot......Page 144
4.3.1 Feature-Based Object Recognition......Page 146
4.3.2 MSFL Inference System......Page 147
4.4.1 The World Model......Page 150
4.4.2 GMRPL......Page 151
4.5 Real-Time Implementation......Page 153
4.6 Summary......Page 154
Bibliography......Page 162
5.1 Introduction......Page 164
5.2.2 The AA-Learning......Page 167
5.2.3 Task Partition......Page 168
5.3.2 Classification Tree and HDR......Page 169
5.3.3 PHDR......Page 171
5.3.4 Amnesic Average......Page 173
5.4.1.1 Khepera robot......Page 174
5.4.1.2 Interface......Page 175
5.4.2 TODL Mapping Engine......Page 176
5.4.4.2 Objects identification......Page 177
5.4.4.3 PHDR representation of the sample task......Page 178
5.5 Discussions......Page 180
5.6 Summary......Page 181
Bibliography......Page 184
6.1 Introduction......Page 186
6.2 The Bipedal Systems......Page 188
6.3 Control Architecture......Page 189
6.4.1 Virtual Model Control......Page 191
6.4.2 Q-Learning......Page 192
6.4.3 Q-Learning Algorithm Using Function Approximator for Q-Factors......Page 193
6.5.1 Virtual Model Control Implementation......Page 195
6.5.2 Reinforcement Learning to Learn Key Swing Leg's Parameter......Page 196
6.5.2.1 State variables......Page 197
6.5.2.2 Reward function and reinforcement learning algorithm......Page 198
6.6.1 Effect of Local Speed Control on Learning Rate......Page 199
6.6.2 Generality of Proposed Algorithm......Page 203
6.7 Summary......Page 206
Bibliography......Page 210
7.1 Introduction......Page 214
7.2.1 Fuzzy Logic Control (FLC)......Page 216
7.2.2 Genetic Algorithms (GAs)......Page 217
7.2.3 GA Tuned FLC......Page 218
7.3 Linear Inverted Pendulum Model......Page 219
7.4 Proposed Bipedal Walking Control Architecture......Page 221
7.4.2 Intuitions of Bipedal Walking Control from Linear Inverted Pendulum Model......Page 222
7.4.3 Fuzzy Logic Controller (FLC) Structure......Page 223
7.4.4.1 Coding the information......Page 225
7.4.4.2 Evaluation......Page 226
7.4.4.3 Evolutionary operators......Page 227
7.5 Simulation Result......Page 229
7.6 Summary......Page 231
Bibliography......Page 236
8.1 Introduction......Page 238
8.2 Virtual Model Control......Page 239
8.3.1 GA's Operations......Page 243
8.3.2 GA's Parameters......Page 244
8.3.3 Fitness Function......Page 245
8.4.1 Convergence to Optimal Solution......Page 246
8.4.2 A Comparison with Solution Produced by Enumerative Method of Optimization......Page 248
8.4.3 The Effects of GA's Parameters......Page 249
8.5 Summary......Page 251
Bibliography......Page 254
9.1 Summary......Page 256
9.2.1 On-Line Evolution......Page 258
9.2.2 Inherent Fault Tolerance......Page 259
9.2.3 Swarm Robotics......Page 260
Index......Page 262

✦ Subjects


Автоматизация;РобототСхничСскиС систСмы (Π Π’Π‘);


πŸ“œ SIMILAR VOLUMES


Evolutionary Robotics: From Algorithms t
✍ Lingfeng Wang, Kay Chen Tan, Chee Meng Chew πŸ“‚ Library πŸ“… 2006 🌐 English

This invaluable book comprehensively describes evolutionary robotics and computational intelligence, and how different computational intelligence techniques are applied to robotic system design. It embraces the most widely used evolutionary approaches with their merits and drawbacks, presents some r

Evolutionary Computations: New Algorithm
✍ Prof. Keigo Watanabe, Prof. M. M. A. Hashem (auth.) πŸ“‚ Library πŸ“… 2004 πŸ› Springer-Verlag Berlin Heidelberg 🌐 English

<p><P>Evolutionary Computation, a broad field that includes Genetic Algorithms, Evolution Strategies, and Evolutionary Programming, has proven to offer well-suited techniques for industrial and management tasks - therefore receiving considerable attention fom scientists and engineers during the last

Learning Motor Skills: From Algorithms t
✍ Jens Kober, Jan Peters (auth.) πŸ“‚ Library πŸ“… 2014 πŸ› Springer International Publishing 🌐 English

<p><p>This book presents the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. It discusses recent approaches that allow robots to learn motor.</p><p>skills and presents tasks that need to take into account the dynamic behavior of the

Introduction to evolutionary algorithms
✍ Xinjie Yu, Mitsuo Gen (auth.) πŸ“‚ Library πŸ“… 2010 πŸ› Springer-Verlag London 🌐 English

<p>Evolutionary algorithms are becoming increasingly attractive across various disciplines, such as operations research, computer science, industrial engineering, electrical engineering, social science and economics. Introduction to Evolutionary Algorithms presents an insightful, comprehensive, and

Introduction to Evolutionary Algorithms
✍ Xinjie Yu, Mitsuo Gen (auth.) πŸ“‚ Library πŸ“… 2010 πŸ› Springer-Verlag London 🌐 English

<p>Evolutionary algorithms are becoming increasingly attractive across various disciplines, such as operations research, computer science, industrial engineering, electrical engineering, social science and economics. Introduction to Evolutionary Algorithms presents an insightful, comprehensive, and