000 10531cam a2200409 i 4500
005 20221102155329.0
008 110403s2011 gw a b 100 0 eng d
011 _aBIB MATCHES WORLDCAT
020 _a3642182712
_qhbk.
020 _a9783642182716
_qhbk.
035 _a(ATU)b1192133x
035 _a(OCoLC)706920676
040 _aATU
_beng
_erda
_cATU
_dATU
082 0 4 _a629.892
_222
100 1 _aDoncieux, Stéphane,
_eauthor.
_9273883
245 1 0 _aNew horizons in evolutionary robotics :
_bextended contributions from the 2009 EvoDeRob workshop /
_cStéphane Doncieux, Nicolas Bredèche and Jean-Baptiste Mouret (eds.).
264 1 _aBerlin ;
_aHeidelberg :
_bSpringer-Verlag,
_c2011.
300 _axv, 225 pages :
_billustrations ;
_c24 cm.
336 _atext
_btxt
_2rdacontent
337 _aunmediated
_bn
_2rdamedia
338 _avolume
_bnc
_2rdacarrier
490 1 _aStudies in computational intelligence ;
_v341
504 _aIncludes bibliographical references.
505 0 0 _gPart I.
_tIntroduction: --
_g1.
_tEvolutionary Robotics: Exploring New Horizons /
_rStephane Doncieux, Jean-Baptiste Mouret, Nicolas Bredeche, Vincent Padois --
_g1.1.
_tIntroduction --
_g1.2.
_tA Brief Introduction to Evolutionary Computation --
_g1.3.
_tWhen to Use ER Methods? --
_g1.3.1.
_tAbsence of "Optimal" Method --
_g1.3.2.
_tKnowledge of Fitness Function Primitives --
_g1.3.3.
_tKnowledge of Phenotype Primitives --
_g1.4.
_tWhere and How to Use EA in the Robot Design Process? --
_g1.4.1.
_tMature Techniques: Parameter Tuning --
_g1.4.2.
_tCurrent Trend: Evolutionary Aided Design --
_g1.4.3.
_tCurrent Trend: Online Evolutionary Adaptation --
_g1.4.4.
_tLong Term Research: Automatic Synthesis --
_g1.5.
_tFrontiers of ER and Perspectives --
_g1.5.1.
_tReality Gap --
_g1.5.2.
_tFitness Landscape and Exploration --
_g1.5.3.
_tGenericity of Evolved Solutions --
_g1.6.
_tA Roboticist Point of View --
_g1.7.
_tDiscussion --
_g1.7.1.
_tGood Robotic Engineering Practices --
_g1.7.2.
_tGood Experimental Sciences Practices --
_gPart II.
_tInvited Position Papers: --
_g2.
_tThe 'What', 'How' and the 'Why' of Evolutionary Robotics /
_rJosh Bongard --
_g2.1.
_tThe What of Embodiment --
_g2.2.
_tThe How of Embodiment --
_g2.3.
_tThe Why of Embodiment --
_g2.4.
_tWhy Consider Topological Change to a Robot's Body Plan? --
_g2.5.
_tWhy Evolve Robot Body Plans Initially at a Low Resolution? --
_g2.6.
_tWhy Allow Body Plans to Change during Behavior Optimization? --
_g3.
_tWhy Evolutionary Robotics Will Matter /
_rKenneth O. Stanley --
_g3.1.
_tJoining the Mainstream --
_g3.2.
_tBridging the Gap --
_g3.3.
_tRealizing the Promise --
_g4.
_tEvolutionary Algorithms in the Design of Complex Robotic Systems /
_rPhilippe Bidaud --
_g4.1.
_tIntroduction --
_g4.2.
_tParticularities of the Robotic System Design --
_g4.3.
_tParameters and Evaluation of Robotic Systems --
_g4.4.
_tEvolutionary Algorithms in the Robotic System Design --
_g4.4.1.
_tKinematic Design of Robot Manipulators --
_g4.4.2.
_tModular Locomotion System Design --
_g4.4.3.
_tInverse Model Synthesis --
_g4.4.4.
_tMulti-objective Task Based Design of Redundant Systems --
_g4.4.5.
_tFlexible Building Block Design of Compliant Mechanisms --
_g4.5.
_tConclusion --
_gPart III.
_tRegular Contributions: --
_g5.
_tEvolving Monolithic Robot Controllers through Incremental Shaping /
_rJoshua E. Auerbach, Josh C. Bongard --
_g5.1.
_tIntroduction --
_g5.2.
_tLearning Multiple Behaviors with a Monolithic Controller --
_g5.3.
_tSpecialization in a Morphologically Homogeneous Robot --
_g6.
_tEvolutionary Algorithms to Analyse and Design a Controller for a Flapping Wings Aircraft /
_rStephane Doncieux, Mohamed Hamdaoui --
_g6.1.
_tIntroduction --
_g6.2.
_tMethod --
_g6.3.
_tExperimental Setup --
_g6.4.
_tResults --
_g6.5.
_tDiscussion and Future Work --
_g6.6.
_tConclusions --
_g7.
_tOn Applying Neuroevolutionary Methods to Complex Robotic Tasks /
_rYohannes Kassahun, Jose de Gea, Jakob Schwendner, Frank Kirchner --
_g7.1.
_tIntroduction --
_g7.2.
_tCase Study 1: Augmented Neural Network with Kalman Filter (ANKF) --
_g7.2.1.
_tThe ass Filter --
_g7.2.2.
_tEvolving ANKF --
_g7.2.3.
_tComparison of Number of Parameters to be Optimized for ANKF and Recurrent Neural Networks --
_g7.2.4.
_tResults Obtained for ANKF on the Double Pole Balancing without Velocities Benchmark --
_g7.3.
_tCase Study 2: Incremental Modification of Fitness Function --
_g7.3.1.
_tQuadrocopter --
_g7.3.2.
_tControl Architecture Developed for the Quadrocopter Using the Principles of Behavior Based Systems --
_g7.3.3.
_tIncremental Modification of Fitness Function --
_g7.3.4.
_tExperiments and Results --
_g7.3.5.
_tTask Decomposition with a Definition of a Single Global Fitness Function Is Not Necessarily Sufficient for Solving Complex Robot Tasks --
_g7.4.
_tConclusion --
_g8.
_tEvolutionary Design of a Robotic Manipulator for a Highly Constrained Environment /
_rS. Rubrecht, E. Singla, V. Padois, P. Bidaud, M. de Broissia --
_g8.1.
_tIntroduction --
_g8.2.
_tCase Study --
_g8.3.
_tGenetic Algorithm and Implementation --
_g8.3.1.
_tGenetic Algorithm --
_g8.3.2.
_tGenome --
_g8.3.3.
_tTrajectory Tracking --
_g8.3.4.
_tControl Law --
_g8.3.5.
_tIndicators --
_g8.4.
_tResults --
_g8.4.1.
_tDesign with Simple Trajectory --
_g8.4.2.
_tDesign with Complex Trajectory --
_g8.5.
_tConclusions and Future Works --
_g8.5.1.
_tConclusions --
_g8.5.2.
_tFuture Works --
_g9.
_tA Multi-cellular Based Self-organizing Approach for Distributed Multi-Robot Systems /
_rYan Meng, Hongliang Guo, Yaochu Jin --
_g9.1.
_tIntroduction --
_g9.2.
_tBiological Background --
_g9.3.
_tThe Approach --
_g9.3.1.
_tThe GRN-Based Dynamics --
_g9.3.2.
_tConvergence Analysis of System Dynamics --
_g9.3.3.
_tThe Evolutionary Algorithm for Parameter Tuning --
_g9.4.
_tSimulation and Results --
_g9.4.1.
_tCase Study 1: Multi-robots Forming a Unit Circle --
_g9.4.2.
_tCase Study 2: Multi-robots Forming a Unit Square --
_g9.4.3.
_tCase Study 3: Self-reorganization --
_g9.4.4.
_tCase Study 4: Robustness Tests to Sensory Noise --
_g9.4.5.
_tCase Study 5: Self-adaptation to Environmental Changes --
_g9.5.
_tConclusion and Future Works --
505 8 0 _g10.
_tNovelty-Based Multiobjectivization /
_rJean-Baptiste Mouret --
_g10.1.
_tIntroduction --
_g10.2.
_tRelated Work --
_g10.2.1.
_tNovelty Search --
_g10.2.2.
_tMulti-Objective Evolutionary Algorithms --
_g10.2.3.
_tMultiobjectivization --
_g10.3.
_tMethod --
_g10.3.1.
_tExperiment --
_g10.3.2.
_tFitness Function and Distance between Behaviors --
_g10.3.3.
_tVariants --
_g10.3.4.
_tExpected Results --
_g10.3.5.
_tExperimental Parameters --
_g10.4.
_tResults --
_g10.4.1.
_tAverage Fitness --
_g10.4.2.
_tConvergence Rate --
_g10.4.3.
_tExploration --
_g10.5.
_tConclusion and Discussion --
_g11.
_tEmbedded Evolutionary Robotics: The (1+1)-Restart-Online Adaptation Algorithm /
_rJean-Marc Montanier, Nicolas Bredeche --
_g11.1.
_tIntroduction --
_g11.2.
_tExtending the (1+1)-Online EA --
_g11.2.1.
_tLimits of (1+1)-Online --
_g11.2.2.
_tThe (1+1)-Restart-Online Algorithm --
_g11.3.
_tExperiments and Results --
_g11.3.1.
_tHardware Set-Up --
_g11.3.2.
_tExperimental Set-Up --
_g11.3.3.
_tExperimental Results --
_g11.3.4.
_tHall-of-Fame Analysis --
_g11.3.5.
_tReal Robot Experiment --
_g11.4.
_tConclusion and Perspectives --
_g12.
_tAutomated Planning Logic Synthesis for Autonomous Unmanned Vehicles in Competitive Environments with Deceptive Adversaries /
_rPetr Svec, Satyandra K. Gupta --
_g12.1.
_tIntroduction --
_g12.2.
_tUSV System Architecture --
_g12.2.1.
_tUSV Virtual Sensor Models --
_g12.2.2.
_tPlanning Architecture --
_g12.3.
_tPlanning Logic Synthesis --
_g12.3.1.
_tTest Mission --
_g12.3.2.
_tSynthesis Scheme --
_g12.3.3.
_tPlanning Logic Components Evolution --
_g12.4.
_tComputational Experiments --
_g12.4.1.
_tGeneral Setup --
_g12.4.2.
_tResults --
_g12.5.
_tConclusions --
_g13.
_tMajor Feedback Loops Supporting Artificial Evolution in Multi-modular Robotics /
_rThomas Schmickl, Jurgen Stradner, Heiko Hamann, Lutz Winkler, Karl Crailsheim --
_g13.1.
_tIntroduction --
_g13.2.
_tArtificial Homeostatic Hormone System --
_g13.2.1.
_tArtificial Genome --
_g13.3.
_tFeedback 1: Classic Control --
_g13.4.
_tFeedback 2: Learning --
_g13.5.
_tFeedback 3: Evolution --
_g13.6.
_tFeedback 4: Controller Morphogenesis --
_g13.7.
_tFeedback 5: Robot Organism Morphogenesis --
_g13.8.
_tFeedback 6: Body Motion --
_g13.8.1.
_tStep 1: The First Oscillator --
_g13.8.2.
_tStep 2: Motion of Bigger Organisms --
_g13.8.3.
_tStep 3: Motion of More Complex Organisms --
_g13.9.
_tDiscussion --
_g14.
_tEvolutionary Design and Assembly Planning for Stochastic Modular Robots /
_rMichael T. Tolley, Jonathan D. Hiller, Hod Lipson --
_g14.1.
_tIntroduction --
_g14.2.
_tTarget Structure Evolution --
_g14.3.
_tStochastic Fluidic Assembly System Model --
_g14.4.
_tAssembly Algorithm --
_g14.5.
_tConclusion.
520 _a"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."--Publisher's website.
588 _aMachine converted from AACR2 source record.
650 0 _aEvolutionary robotics
_9337777
700 1 _aBredeche, Nicolas.
_91085518
700 1 _aMouret, Jean-Baptiste,
_eauthor.
711 2 _aEvoDeRob Workshop
_d(2009 :
_cSt. Louis, Mo.)
830 0 _aStudies in computational intelligence ;
_v341.
_9292380
907 _a.b1192133x
_b22-08-17
_c27-10-15
942 _cB
945 _a629.892 NEW
_g1
_iA502072B
_j0
_lcmain
_o-
_p$157.19
_q-
_r-
_s-
_t0
_u1
_v0
_w0
_x0
_y.i13126593
_z29-10-15
998 _a(2)b
_a(2)c
_b06-04-16
_cm
_da
_feng
_ggw
_h0
999 _c1220568
_d1220568