Atnaujinkite slapukų nuostatas

El. knyga: New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob Workshop

Edited by , Edited by , Edited by
  • Formatas: PDF+DRM
  • Serija: Studies in Computational Intelligence 341
  • Išleidimo metai: 14-Feb-2011
  • Leidėjas: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • Kalba: eng
  • ISBN-13: 9783642182723
Kitos knygos pagal šią temą:
New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob WorkshopDidesnis paveikslėlis
  • Formatas: PDF+DRM
  • Serija: Studies in Computational Intelligence 341
  • Išleidimo metai: 14-Feb-2011
  • Leidėjas: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • Kalba: eng
  • ISBN-13: 9783642182723
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

This book offers extended contributions from the workshop "New Horizons in Evolutionary Design of Robots" that brought together researchers from Computer Science and Robotics during the International Conference on Intelligent Robots and Systems (IROS-2009).



Evolutionary Algorithms (EAs) now provide mature optimization tools that have successfully been applied to many problems, from designing antennas to complete robots, and provided many human-competitive results. In robotics, the integration of EAs within the engineer’s toolbox made tremendous progress in the last 20 years and proposes new methods to address challenging problems in various setups: modular robotics, swarm robotics, robotics with non-conventional mechanics (e.g. high redundancy, dynamic motion, multi-modality), etc.

This book takes its roots in the workshop on "New Horizons in Evolutionary Design of Robots" that brought together researchers from Computer Science and Robotics during the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-2009) in Saint Louis (USA). This book features extended contributions from the workshop, thus providing various examples of current problems and applications, with a special emphasis on the link between Computer Science and Robotics. It also provides a comprehensive and up-to-date introduction to Evolutionary Robotics after 20 years of maturation as well as thoughts and considerations from several major actors in the field.

This book offers a comprehensive introduction to the current trends and challenges in Evolutionary Robotics for the next decade.
Part I Introduction
1 Evolutionary Robotics: Exploring New Horizons
3(26)
Stephane Doncieux
Jean-Baptiste Mouret
Nicolas Bredeche Vincent Padois
1.1 Introduction
3(1)
1.2 A Brief Introduction to Evolutionary Computation
4(2)
1.3 When to Use ER Methods?
6(2)
1.3.1 Absence of "Optimal" Method
7(1)
1.3.2 Knowledge of Fitness Function Primitives
7(1)
1.3.3 Knowledge of Phenotype Primitives
7(1)
1.4 Where and How to Use EA in the Robot Design Process?
8(5)
1.4.1 Mature Techniques: Parameter Tuning
9(1)
1.4.2 Current Trend: Evolutionary Aided Design
10(1)
1.4.3 Current Trend: Online Evolutionary Adaptation
11(1)
1.4.4 Long Term Research: Automatic Synthesis
12(1)
1.5 Frontiers of ER and Perspectives
13(3)
1.5.1 Reality Gap
13(1)
1.5.2 Fitness Landscape and Exploration
14(1)
1.5.3 Genericity of Evolved Solutions
15(1)
1.6 A Roboticist Point of View
16(1)
1.7 Discussion
16(13)
1.7.1 Good Robotic Engineering Practices
18(1)
1.7.2 Good Experimental Sciences Practices
19(1)
References
20(9)
Part II Invited Position Papers
2 The `What', `How' and the `Why' of Evolutionary Robotics
29(8)
Josh Bongard
2.1 The What of Embodiment
29(1)
2.2 The How of Embodiment
30(1)
2.3 The Why of Embodiment
31(1)
2.4 Why Consider Topological Change to a Robot's Body Plan?
31(1)
2.5 Why Evolve Robot Body Plans Initially at a Low Resolution?
32(2)
2.6 Why Allow Body Plans to Change during Behavior Optimization?
34(3)
References
35(2)
3 Why Evolutionary Robotics Will Matter
37(6)
Kenneth O. Stanley
3.1 Joining the Mainstream
37(1)
3.2 Bridging the Gap
38(1)
3.3 Realizing the Promise
39(4)
References
40(3)
4 Evolutionary Algorithms in the Design of Complex Robotic Systems
43(12)
Philippe Bidaud
4.1 Introduction
43(1)
4.2 Particularities of the Robotic System Design
44(1)
4.3 Parameters and Evaluation of Robotic Systems
45(2)
4.4 Evolutionary Algorithms in the Robotic System Design
47(4)
4.4.1 Kinematic Design of Robot Manipulators
47(1)
4.4.2 Modular Locomotion System Design
48(1)
4.4.3 Inverse Model Synthesis
49(1)
4.4.4 Multi-objective Task Based Design of Redundant Systems
49(2)
4.4.5 Flexible Building Block Design of Compliant Mechanisms
51(1)
4.5 Conclusion
51(4)
References
52(3)
Part III Regular Contributions
5 Evolving Monolithic Robot Controllers through Incremental Shaping
55(12)
Joshua E. Auerbach
Josh C. Bongard
5.1 Introduction
55(1)
5.2 Learning Multiple Behaviors with a Monolithic Controller
56(4)
5.3 Specialization in a Morphologically Homogeneous Robot
60(7)
References
64(3)
6 Evolutionary Algorithms to Analyse and Design a Controller for a Flapping Wings Aircraft
67(18)
Stephane Doncieux
Mohamed Hamdaoui
6.1 Introduction
67(2)
6.2 Method
69(2)
6.3 Experimental Setup
71(2)
6.4 Results
73(7)
6.5 Discussion and Future Work
80(1)
6.6 Conclusions
81(4)
References
82(3)
7 On Applying Neuroevolutionary Methods to Complex Robotic Tasks
85(24)
Yohannes Kassahun
Jose de Gea
Jakob Schwendner
Frank Kirchner
7.1 Introduction
85(3)
7.2 Case Study 1: Augmented Neural Network with Kalman Filter (ANKF)
88(8)
7.2.1 The αβ Filter
89(1)
7.2.2 Evolving ANKF
90(2)
7.2.3 Comparison of Number of Parameters to be Optimized for ANKF and Recurrent Neural Networks
92(2)
7.2.4 Results Obtained for ANKF on the Double Pole Balancing without Velocities Benchmark
94(2)
7.3 Case Study 2: Incremental Modification of Fitness Function
96(10)
7.3.1 Quadrocopter
97(1)
7.3.2 Control Architecture Developed for the Quadrocopter Using the Principles of Behavior Based Systems
98(2)
7.3.3 Incremental Modification of Fitness Function
100(1)
7.3.4 Experiments and Results
100(5)
7.3.5 Task Decomposition with a Definition of a Single Global Fitness Function Is Not Necessarily Sufficient for Solving Complex Robot Tasks
105(1)
7.4 Conclusion
106(3)
References
106(3)
8 Evolutionary Design of a Robotic Manipulator for a Highly Constrained Environment
109(14)
S. Rubrecht
E. Singla
V. Padois
P. Bidaud
M. de Broissia
8.1 Introduction
109(2)
8.2 Case Study
111(1)
8.3 Genetic Algorithm and Implementation
112(4)
8.3.1 Genetic Algorithm
112(1)
8.3.2 Genome
113(1)
8.3.3 Trajectory Tracking
114(1)
8.3.4 Control Law
114(2)
8.3.5 Indicators
116(1)
8.4 Results
116(3)
8.4.1 Design with Simple Trajectory
117(2)
8.4.2 Design with Complex Trajectory
119(1)
8.5 Conclusions and Future Works
119(4)
8.5.1 Conclusions
119(1)
8.5.2 Future Works
120(1)
References
120(3)
9 A Multi-cellular Based Self-organizing Approach for Distributed Multi-Robot Systems
123(16)
Yan Meng
Hongliang Guo
Yaochu Jin
9.1 Introduction
123(2)
9.2 Biological Background
125(1)
9.3 The Approach
126(4)
9.3.1 The GRN-Based Dynamics
126(2)
9.3.2 Convergence Analysis of System Dynamics
128(1)
9.3.3 The Evolutionary Algorithm for Parameter Tuning
129(1)
9.4 Simulation and Results
130(5)
9.4.1 Case Study 1: Multi-robots Forming a Unit Circle
130(1)
9.4.2 Case Study 2: Multi-robots Forming a Unit Square
131(2)
9.4.3 Case Study 3: Self-reorganization
133(1)
9.4.4 Case Study 4: Robustness Tests to Sensory Noise
134(1)
9.4.5 Case Study 5: Self-adaptation to Environmental Changes
134(1)
9.5 Conclusion and Future Works
135(4)
References
136(3)
10 Novelty-Based Multiobjectivization
139(16)
Jean-Baptiste Mouret
10.1 Introduction
139(1)
10.2 Related Work
140(2)
10.2.1 Novelty Search
140(1)
10.2.2 Multi-Objective Evolutionary Algorithms
141(1)
10.2.3 Multiobjectivization
142(1)
10.3 Method
142(4)
10.3.1 Experiment
142(2)
10.3.2 Fitness Function and Distance between Behaviors
144(1)
10.3.3 Variants
144(1)
10.3.4 Expected Results
145(1)
10.3.5 Experimental Parameters
145(1)
10.4 Results
146(6)
10.4.1 Average Fitness
146(1)
10.4.2 Convergence Rate
147(3)
10.4.3 Exploration
150(2)
10.5 Conclusion and Discussion
152(3)
References
152(3)
11 Embedded Evolutionary Robotics: The (l+l)-Restart-Online Adaptation Algorithm
155(16)
Jean-Marc Montanier
Nicolas Bredeche
11.1 Introduction
155(3)
11.2 Extending the (l+l)-Online EA
158(2)
11.2.1 Limits of (l+l)-Online
158(1)
11.2.2 The (l+l)-Restart-Online Algorithm
159(1)
11.3 Experiments and Results
160(7)
11.3.1 Hardware Set-Up
160(2)
11.3.2 Experimental Set-Up
162(1)
11.3.3 Experimental Results
163(1)
11.3.4 Hall-of-Fame Analysis
164(1)
11.3.5 Real Robot Experiment
165(2)
11.4 Conclusion and Perspectives
167(4)
References
168(3)
12 Automated Planning Logic Synthesis for Autonomous Unmanned Vehicles in Competitive Environments with Deceptive Adversaries
171(24)
Petr Svec
Satyandra K. Gupta
12.1 Introduction
171(3)
12.2 USV System Architecture
174(7)
12.2.1 USV Virtual Sensor Models
175(1)
12.2.2 Planning Architecture
175(6)
12.3 Planning Logic Synthesis
181(4)
12.3.1 Test Mission
181(1)
12.3.2 Synthesis Scheme
182(1)
12.3.3 Planning Logic Components Evolution
183(2)
12.4 Computational Experiments
185(5)
12.4.1 General Setup
185(3)
12.4.2 Results
188(2)
12.5 Conclusions
190(5)
References
191(4)
13 Major Feedback Loops Supporting Artificial Evolution in Multi-modular Robotics
195(16)
Thomas Schmickl
Jurgen Stradner
Heiko Hamann
Lutz Winkler Karl Crailsheim
13.1 Introduction
195(3)
13.2 Artificial Homeostatic Hormone System
198(1)
13.2.1 Artificial Genome
198(1)
13.3 Feedback 1: Classic Control
199(1)
13.4 Feedback 2: Learning
200(1)
13.5 Feedback 3: Evolution
200(1)
13.6 Feedback 4: Controller Morphogenesis
201(1)
13.7 Feedback 5: Robot Organism Morphogenesis
202(2)
13.8 Feedback 6: Body Motion
204(1)
13.8.1 Step 1: The First Oscillator
204(1)
13.8.2 Step 2: Motion of Bigger Organisms
204(1)
13.8.3 Step 3: Motion of More Complex Organisms
205(1)
13.9 Discussion
205(6)
References
208(3)
14 Evolutionary Design and Assembly Planning for Stochastic Modular Robots
211(13)
Michael T. Tolley
Jonathan D. Hiller
Hod Lipson
14.1 Introduction
211(1)
14.2 Target Structure Evolution
212(4)
14.3 Stochastic Fluidic Assembly System Model
216(3)
14.4 Assembly Algorithm
219(5)
14.5 Conclusion
224(1)
References 224
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97836421827232e.html
Raktažodžiai: