Muutke küpsiste eelistusi

Mobile Robots: The Evolutionary Approach 2007 ed. [Kõva köide]

Edited by
  • Formaat: Hardback, 223 pages, kõrgus x laius: 297x210 mm, kaal: 1160 g, XXI, 223 p., 1 Hardback
  • Sari: Studies in Computational Intelligence 50
  • Ilmumisaeg: 08-Mar-2007
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3540497196
  • ISBN-13: 9783540497196
Teised raamatud teemal:
  • Kõva köide
  • Hind: 95,02 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 111,79 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Mobile Robots: The Evolutionary Approach 2007 ed.Suurem pilt
  • Formaat: Hardback, 223 pages, kõrgus x laius: 297x210 mm, kaal: 1160 g, XXI, 223 p., 1 Hardback
  • Sari: Studies in Computational Intelligence 50
  • Ilmumisaeg: 08-Mar-2007
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3540497196
  • ISBN-13: 9783540497196
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783540497196.html
Märksõnad:
Mobile robotic is a recent ?eld that has roots in many engineering and science disciplines such as mechanical, electrical, mechatronics, cognitive and social sciences just to name few. A mobile robot needs e cient mechanisms of lo- motion, kinematics, sensors data, localization, planning and navigation that enable it to travel throughout its environment. Scientists have been fascinated by conception of mobile robots for many years. Machines have been designed withwheelsandtracksorotherlocomotion devicesand/orlimbs topropelthe unit. When the environment is well ordered these machines can function well. Mobile robots have demonstrated strongly their ability to carry out useful work. Intelligent robots have become the focus of intensive research in the last decade. The ?eld of intelligent mobile robotics involves simulations and re- world implementations of robots which adapt themselves to their partially unknown, unpredictable and sometimes dynamic environments. The design and control of autonomous intelligent mobile robotic systems operatinginunstructuredchangingenvironmentsincludesmanyobjectived- ?culties. There are several studies about the ways in which, robots exhibiting some degree of autonomy, adapt themselves to ?t in their environments. The application and use of bio-inspired techniques such as reinforcement lea- ing, arti cial neural networks, evolutionary computation, swarm intelligence and fuzzy systems in the design and improvement of robot designs is an em- gentresearchtopic. Researchershaveobtainedrobotsthatdisplayanamazing slew of behaviours and perform a multitude of tasks.
Part I Evolutionary Mobile Robots
1 Differential Evolution Approach Using Chaotic Sequences Applied to Planning of Mobile Robot in a Static Environment with Obstacles
Leandro dos Santos Coelho, Nadia Nedjah, Luiza de Macedo Mourelle
3
1.1 Introduction
4
1.2 Differential Evolution
5
1.3 New Approach of Differential Evolution Combined with Chaos Theory
7
1.4 Planning of Mobile Robots
11
1.5 Simulation Results
13
1.5.1 Case study 1: Environment with 7 obstacles
13
1.5.2 Case study 2: Environment with 14 obstacles
15
1.6 Summary
16
References
19
2 Evolving Modular Robots for Rough Terrain Exploration
Olivier Chocron
23
2.1 Introduction
23
2.2 Means and Goals
25
2.2.1 Modular Robotic Systems
25
2.2.2 Evolutionary Optimization
26
2.2.3 Dynamic Simulation
27
2.3 Evolutionary Task-Based Design
29
2.3.1 Genotype Encoding: Incidence Matrix
29
2.3.2 Topology Operators
31
2.3.3 Command operators
34
2.3.4 Phenotype Evaluation
35
2.4 Simulation Results
36
2.4.1 Experimental setup
36
2.4.2 Task 1: Speed up
38
2.4.3 Task 2: Reaching a goal
39
2.4.4 Task 3: Getting altitude
39
2.4.5 Task 4: Increasing angular velocity
41
2.5 Summary and Conclusions
43
References
44
3 Evolutionary Navigation of Autonomous Robots Under Varying Terrain Conditions
Terrence P. Fries
47
3.1 Introduction
47
3.2 Problem Formulation
50
3.2.1 Environment Grid
50
3.2.2 Genetic Algorithms
51
3.3 Motion Planning Algorithm
53
3.3.1 Encoding the Chromosome
53
3.3.2 Initial Population
54
3.3.3 Genetic operators and parameters
54
3.3.4 Fitness function
54
3.3.5 Dynamic Environment
56
3.4 Test Results
56
3.5 Conclusions
60
References
61
4 Aggregate Selection in Evolutionary Robotics
Andrew L. Nelson, Edward Grant
63
4.1 Introduction
64
4.1.1 Evolutionary Robotics Process Overview
65
4.1.2 Bias
66
4.1.3 Fitness Functions
66
4.2 Evolutionary Robotics So Far
70
4.3 Evolutionary Robotics and Aggregate Fitness
73
4.4 Making Aggregate Selection Work
74
4.5 Aggregate Selection and Competition
75
4.6 Conclusion
83
References
85
5 Evolving Fuzzy Classifier for Novelty Detection and Landmark Recognition by Mobile Robots
Plamen Angelov, Xiaowei Zhou
89
5.1 Introduction
89
5.2 Landmark Recognition in Mobile Robotics
91
5.3 Evolving Fuzzy Rule-Based Classifier (eClass)
92
5.3.1 The Informative Data Density and Proximity Measure
93
5.3.2 Landmark Classifier Generation and Evolution
94
5.3.3 Landmark Recognition (real-time classification)
96
5.3.4 Learning of eClass
98
5.4 Case Study: Corner Recognition
99
5.4.1 The Mobile Robotic Platform
100
5.4.2 Experiment Settings
103
5.4.3 Program Structure
104
5.4.4 Results and Analysis
105
5.5 Further Investigations and Conclusion
109
5.5.1 Using Different Devices and Selecting Features
109
5.5.2 Rules Aggregation
110
5.5.3 Applying Variable Radius
111
5.6 Summary
112
References
112
Bibliography
112
Appendix: C++ Class EvolvingClassifier
115
Part II Learning Mobile Robots
6 Reinforcement Learning for Autonomous Robotic Fish
Jindong Liu, Lynne E. Parker, Raj Madhavan
121
6.1 Introduction
121
6.2 Introduction of Robotic Fish-Aifi
123
6.3 Policy Gradient Learning in Swim Pattern Layer
124
6.4 State-based Reinforcement Learning in Cognitive Layer
127
6.4.1 Action Space and State Space
128
6.4.2 Markov Decision Process Model
128
6.5 Experimental Results
129
6.5.1 Policy Gradient Learning for Sharp- Turning Swim Pattern
129
6.5.2 Q-learning for Tank Border Exploration Task
130
6.6 Summary
133
References
133
7 Module-based Autonomous Learning for Mobile Robots
Esther L. Colombini, Carlos H.C. Ribeiro
137
7.1 Introduction
138
7.1.1 Bibliography Review
138
7.2 Reinforcement Learning
140
7.2.1 Markovian Decision Processes
140
7.2.2 Q-learning
141
7.2.3 Features
142
7.2.4 Module-based RL
142
7.3 Generalisation
144
7.3.1 Cerebellar Model Articulation Controller (CMAC)
144
7.4 Experiments
147
7.4.1 Environment
147
7.4.2 Tasks
148
7.4.3 Behaviours
148
7.4.4 Space Discretisation
148
7.4.5 Hand-crafted Policy
149
7.4.6 Learned Policies
149
7.4.7 Results
150
7.4.8 CMAC Experiments
154
7.5 Conclusions
156
References
157
8 A Hybrid Adaptive Architecture for Mobile Robots Based on Reactive Behaviours
Antonio Henrique Pinto Selvatici, Anna Helena Reali Costa
161
8.1 Introduction
161
8.2 Agent Architectures
163
8.2.1 Simple Reflex Agents
163
8.2.2 Model-Based Reflex Agents
163
8.2.3 Goal-Based Agents
164
8.2.4 Utility-Based Agents
165
8.2.5 Learning Agents
165
8.3 AAREACT
166
8.4 Reactive Layer
168
8.5 Coordination Layer
170
8.5.1 SARSA Algorithm
170
8.5.2 Definition of the Situation Space
172
8.5.3 Definition of the Weights Sets
173
8.5.4 The Reinforcement Function
174
8.6 Experiments with AAREACT
175
8.6.1 The Robot Model
175
8.6.2 Initial Learning Phase
176
8.6.3 Scenario Changing Experiments
177
8.7 Related Work
178
8.8 Conclusion
182
References
183
9 Collaborative Robots for Infrastructure Security Applications
Yi Guo, Lynne E. Parker, Raj Aladhavan
185
9.1 Introduction
185
9.2 Infrastructure Security Scenario and Research Problems
187
9.3 Multi-Robot Positioning and Mapping using Distributed Sensing
188
9.3.1 Heterogeneous Distributed Multi-Robot Localization
188
9.3.2 Terrain Mapping
191
9.4 Dynamic Multi-Robot Motion Planning
192
9.4.1 Area Partition
193
9.4.2 Initial Distribution
193
9.4.3 Complete Coverage Patrolling
194
9.4.4 Point Convergence
196
9.5 System Integration Towards Proof of Principle Demonstration
197
9.6 Conclusions
198
References
199
10 Imitation Learning: An Application in a Micro Robot Soccer Game
Dennis Barrios-Aranibar and Pablo Javier Alsina
201
10.1 Introduction
201
10.2 Case Study and Control Architecture
204
10.3 Situations Recognition
206
10.4 Behaviors Patterns Recognition
212
10.5 Experimental Results
213
10.6 Conclusions and Future Works
217
References
218
Index 221
Author Index 223