The design and control of autonomous intelligent mobile robotic systems operating in unstructured changing environments includes many objective difficulties. There are several studies about the ways in which, robots exhibiting some degree of autonomy, adapt themselves to fit in their environments. The application and use of bio-inspired and intelligent techniques such as reinforcement learning, artificial neural networks, evolutionary computation and so forth in the design and improvement of robot designs is an emergent research topic. Researchers have obtained robots that display an amazing slew of behaviours and perform a multitude of tasks. These include perception of environment, planning and navigation in rough terrain, pushing boxes, negotiating an obstacle course, etc.
This volume offers a wide spectrum of sample works developed in leading research throughout the world about evolutionary mobile robotics and demonstrates the success of the technique in evolving efficient and capable mobile robots.
Author(s): Leandro dos Santos Coelho
Series: Studies in Computational Intelligence
Edition: 1
Publisher: Springer
Year: 2007
Language: English
Pages: 238
3540497196......Page 1
Contents......Page 11
Part I: Evolutionary Mobile Robots......Page 21
1. Differential Evolution Approach Using Chaotic Sequences Applied to Planning of Mobile Robot in a Static Environment with Obstacles......Page 22
1.1 Introduction......Page 23
1.2 Differential Evolution......Page 24
1.3 New Approach of Differential Evolution Combined with Chaos Theory......Page 26
1.4 Planning of Mobile Robots......Page 30
1.5 Simulation Results......Page 32
1.6 Summary......Page 35
References......Page 38
2.1 Introduction......Page 42
2.2 Means and Goals......Page 44
2.3 Evolutionary Task-Based Design......Page 48
2.4 Simulation Results......Page 55
2.5 Summary and Conclusions......Page 62
References......Page 63
3.1 Introduction......Page 66
3.2 Problem Formulation......Page 69
3.3 Motion Planning Algorithm......Page 72
3.4 Test Results......Page 75
3.5 Conclusions......Page 79
References......Page 80
4. Aggregate Selection in Evolutionary Robotics......Page 82
4.1 Introduction......Page 83
4.2 Evolutionary Robotics So Far......Page 89
4.3 Evolutionary Robotics and Aggregate Fitness......Page 92
4.4 Making Aggregate Selection Work......Page 93
4.5 Aggregate Selection and Competition......Page 94
4.6 Conclusion......Page 102
References......Page 104
5.1 Introduction......Page 108
5.2 Landmark Recognition in Mobile Robotics......Page 110
5.3 Evolving Fuzzy Rule-Based Classifier (eClass)......Page 111
5.4 Case Study: Corner Recognition......Page 118
5.5 Further Investigations and Conclusion......Page 128
References......Page 131
Appendix: C++ Class EvolvingClassifier......Page 134
Part II: Learning Mobile Robots......Page 138
6.1 Introduction......Page 139
6.2 Introduction of Robotic Fish-Aifi......Page 141
6.3 Policy Gradient Learning in Swim Pattern Layer......Page 142
6.4 State-based Reinforcement Learning in Cognitive Layer......Page 145
6.5 Experimental Results......Page 147
References......Page 151
7. Module-based Autonomous Learning for Mobile Robots......Page 154
7.1 Introduction......Page 155
7.2 Reinforcement Learning......Page 157
7.3 Generalisation......Page 161
7.4 Experiments......Page 164
7.5 Conclusions......Page 173
References......Page 174
8.1 Introduction......Page 177
8.2 Agent Architectures......Page 179
8.3 AAREACT......Page 182
8.4 Reactive Layer......Page 184
8.5 Coordination Layer......Page 186
8.6 Experiments with AAREACT......Page 191
8.7 Related Work......Page 194
8.8 Conclusion......Page 198
References......Page 199
9.1 Introduction......Page 201
9.2 Infrastructure Security Scenario and Research Problems......Page 203
9.3 Multi-Robot Positioning and Mapping using Distributed Sensing......Page 204
9.4 Dynamic Multi-Robot Motion Planning......Page 208
9.5 System Integration Towards Proof of Principle Demonstration......Page 213
9.6 Conclusions......Page 214
References......Page 215
10.1 Introduction......Page 217
10.2 Case Study and Control Architecture......Page 220
10.3 Situations Recognition......Page 222
10.4 Behaviors Patterns Recognition......Page 228
10.5 Experimental Results......Page 229
10.6 Conclusions and Future Works......Page 233
References......Page 234
L......Page 236
W......Page 237
Author Index......Page 238
