Muutke küpsiste eelistusi

Obstacle Avoidance In Multi-robot Systems, Experiments In Parallel Genetic Algorithms [Kõva köide]

(University Of Western Australia, Australia), (University Of Sydney, Australia)
Teised raamatud teemal:
Obstacle Avoidance In Multi-robot Systems, Experiments In Parallel Genetic AlgorithmsSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9789810234232.html
Obstacle Avoidance in Multi-robot Systems: Experiments in Parallel Genetic Algorithms offers a novel framework for solving the path planning problem for robot manipulators. Simple and efficient solutions are proposed for the path planning problem based on genetic algorithms. One of the attractive features of genetic algorithms is their ability to solve formidable problems in a robust and straightforward manner. Moreover, genetic algorithms are inherently parallel in nature, which makes them ideal candidates for parallel computing implementations.By combining the robustness of genetic algorithms with the power of parallel computers, this book provides an effective and practical approach to solving path planning problems. The book gives details of implementations that allow a better understanding of the complexities involved in the development of parallel path planning algorithms. The material presented is interdisciplinary in nature it combines topics from robotics, genetic algorithms, and parallel processing. The book can be used by practitioners and researchers in computer science and engineering.
Preface v(3)
Abbreviations viii
1. Overview
1(7)
1.1 Introduction
1(1)
1.2 Robotics
1(3)
1.3 Path Planning, Genetic Algorithms and Parallel Processing
4(1)
1.4 Motivation for this Work
4(1)
1.5 Contribution of this Work
5(1)
1.6 Work Organization
6(2)
2. Parallel Computing
8(22)
2.1 Introduction
8(1)
2.2 Parallel Processing
9(13)
2.2.1 Parallel Classification
11(2)
2.2.1.1 SISD Machines
13(1)
2.2.1.2 SIMD Machines
13(1)
2.2.1.3 MISD Machines
14(1)
2.2.1.4 MIMD Machines
14(2)
2.2.2 Network Topologies
16(1)
2.2.3 Performance Measures
17(1)
2.2.3.1 Speed-Up
18(1)
2.2.3.2 Maximum Speed-Up
18(1)
2.2.3.3 Communication Penalty
19(1)
2.2.3.4 Efficiency
19(1)
2.2.3.5 Utilization Factor
19(1)
2.2.4 Parallel Algorithms
19(1)
2.2.5 Real-Time Systems
20(2)
2.3 Master/Slave MIMD Implementation
22(4)
2.4 Transputers
26(3)
2.5 Summary
29(1)
3. Path Planning
30(22)
3.1 Introduction
30(3)
3.2 Defining Terms
33(3)
3.3 Classification of Motion Planning Probems
36(1)
3.4 Classification of Motion Planning Algorithms
37(1)
3.5 Path Planning
38(8)
3.5.1 Configuration Space Representation
40(1)
3.5.2 Object Representation
41(4)
3.5.3 Motion Planning Method
45(1)
3.5.4 Search Techniques
46(1)
3.6 Survey of Previous Work
46(5)
3.7 Summary
51(1)
4. Search Techniques
52(14)
4.1 Introduction
52(2)
4.2 Genetic Algorithms
54(10)
4.2.1 Population Statistics
57(1)
4.2.2 Reproduction Operator
58(2)
4.2.3 Crossover Operator
60(1)
4.2.4 Mutation Operator
60(1)
4.2.5 Genetic Algorithm Example
61(2)
4.2.6 Parallel Genetic Algorithms
63(1)
4.2.7 Parallel Implementation
64(1)
4.3 Summary
64(2)
5. Inverse Kinematics
66(17)
5.1 Introduction
66(1)
5.2 Denavit and Hartenberg Notation
66(6)
5.3 GA Search
72(3)
5.4 Results and Examples
75(7)
5.5 Conclusions
82(1)
6. Collision Detection
83(32)
6.1 Introduction
83(1)
6.2 Modelling of Manipulator and Obstacles
84(2)
6.3 Preliminary Calculations
86(13)
6.3.1 Preliminary Calculations for Lines
87(1)
6.3.1.1 Point and a Line
88(1)
6.3.1.2 Point and a Line Segment
89(1)
6.3.1.3 Sphere and Line Segment
89(1)
6.3.1.4 Two Non-Parallel Lines
90(2)
6.3.1.5 Two Parallel Lines
92(1)
6.3.2 Minimum Distance Between Two Line Segments
92(1)
6.3.2.1 Two Non-Parallel Line Segments
93(1)
6.3.2.2 Two Parallel Line Segments
93(1)
6.3.3 Definitions and Preliminary Calculations for Planes
94(1)
6.3.3.1 Plane and a Parallel Line (Segment)
95(2)
6.3.3.2 Line and Plane Intersection
97(1)
6.3.3.3 Projecting a Point onto a Plane
98(1)
6.4 Algorithm
99(3)
6.5 Results and Examples
102(11)
6.6 Conclusions
113(2)
7. Collision Avoidance
115(19)
7.1 Particle Motion Through Space
115(10)
7.2.1 Potential Field
115(5)
7.2.2 Cell Decomposition
120(5)
7.3 Manipulator Implementation
125(8)
7.3.1 Potential Field Approach
128(1)
7.3.2 Cell Decomposition Approach
128(3)
7.3.3 Genetic Algorithm Details
131(2)
7.4 Conclusions
133(1)
8. Examples
134(21)
8.1 Introduction
134(1)
8.2 Serial Examples
134(13)
8.2.1 Example 1
139(1)
8.2.2 Example 2
139(1)
8.2.3 Example 3
139(6)
8.2.4 Example 4
145(1)
8.2.5 Example 5
145(1)
8.2.6 Example 6
146(1)
8.3 Parallel Example
147(6)
8.4 Conclusions
153(2)
9. Discussion, Conclusions and Future Work
155(6)
9.1 Introduction
155(1)
9.2 Summary of Results and Discussion
155(2)
9.3 Limitations
157(2)
9.4 Future Work
159(1)
9.5 Conclusions
159(2)
References 161(16)
Appendix 1 Parallel Line Proof 177(2)
Appendix 2 Polynomial Method 179(2)
Index 181