Evolving behavioral specialization in robot teams to solve a collective construction task

This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective NeuroEvolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors.

[1]  Alan C. Schultz,et al.  Heterogeneity in the Coevolved Behaviors of Mobile Robots: The Emergence of Specialists , 2001, IJCAI.

[2]  J. Deneubourg,et al.  Emergent polyethism as a consequence of increased colony size in insect societies. , 2002, Journal of theoretical biology.

[3]  Dario Floreano,et al.  Effects of Group Composition and Level of Selection in the Evolution of Cooperation in Artificial Ants , 2003, ECAL.

[4]  W. Hamilton.  The genetical evolution of social behaviour. II. , 1964, Journal of theoretical biology.

[5]  Dario Floreano,et al.  Neuroevolution: from architectures to learning , 2008, Evol. Intell..

[6]  Robert E. Page,et al.  Genotypic variability in age polyethism and task specialization in the honey bee, Apis mellifera (Hymenoptera: Apidae) , 2004, Behavioral Ecology and Sociobiology.

[7]  A. E. Eiben,et al.  Introduction to Evolutionary Computing , 2003, Natural Computing Series.

[8]  W. Hamilton.  The genetical evolution of social behaviour. I. , 1964, Journal of theoretical biology.

[9]  Michael G. Dyer,et al.  Goal Sequencing for Construction Agents in a Simulated Environment , 2002, ICANN.

[10]  Takashi Gomi,et al.  Book Review: Evolutionary Robotics: the Biology, Intelligence, and Technology of Self-Organizing Machines , 2003, Genetic Programming and Evolvable Machines.

[11]  Barbara Webb,et al.  Swarm Intelligence: From Natural to Artificial Systems , 2002, Connect. Sci..

[12]  A. E. Eiben,et al.  Parameter tuning for configuring and analyzing evolutionary algorithms , 2011, Swarm Evol. Comput..

[13]  Fabrice R. Noreils,et al.  Toward a Robot Architecture Integrating Cooperation between Mobile Robots: Application to Indoor Environment , 1993, Int. J. Robotics Res..

[14]  Yaochu Jin,et al.  A cellular mechanism for multi-robot construction via evolutionary multi-objective optimization of a gene regulatory network , 2009, Biosyst..

[15]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[16]  Tamio Arai,et al.  Distributed Autonomous Robotic Systems 3 , 1998 .

[17]  Jacek M. Zurada,et al.  Swarm and Evolutionary Computation , 2012, Lecture Notes in Computer Science.

[18]  Peter Stone,et al.  Layered Learning in Multiagent Systems , 1997, AAAI/IAAI.

[19]  G. Nitschke.  Neuro-Evolution for Emergent Specialization in Collective Behavior Systems , 2009 .

[20]  G Theraulaz,et al.  Coordination in Distributed Building , 1995, Science.

[21]  E. Bonabeau,et al.  Fixed response thresholds and the regulation of division of labor in insect societies , 1998 .

[22]  C. Dunnett.  A Multiple Comparison Procedure for Comparing Several Treatments with a Control , 1955 .

[23]  José del R. Millán,et al.  Learning Signaling Behaviors and Specialization in Cooperative Agents , 1996, Adapt. Behav..

[24]  Mitchell A. Potter,et al.  The design and analysis of a computational model of cooperative coevolution , 1997 .

[25]  Stefano Nolfi,et al.  Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines , 2000 .

[26]  Radhika Nagpal,et al.  Extended stigmergy in collective construction , 2006, IEEE Intelligent Systems.

[27]  Sean Luke,et al.  MASON: A Multiagent Simulation Environment , 2005, Simul..

[28]  César Hervás-Martínez,et al.  Cooperative coevolution of artificial neural network ensembles for pattern classification , 2005, IEEE Transactions on Evolutionary Computation.

[29]  William H. Press,et al.  Numerical recipes , 1990 .

[30]  Gary B. Parker,et al.  Competing sample sizes for the co-evolution of heterogeneous agents , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[31]  Francesco Mondada,et al.  Mobile Robot Miniaturisation: A Tool for Investigation in Control Algorithms , 1993, ISER.

[32]  David J. Hawthorne,et al.  Genetic linkage of ecological specialization and reproductive isolation in pea aphids , 2001, Nature.

[33]  Risto Miikkulainen,et al.  Coevolution of Role-Based Cooperation in Multiagent Systems , 2009, IEEE Transactions on Autonomous Mental Development.

[34]  Domenico Parisi,et al.  How can we explain the emergence of a language that benefits the hearer but not the speaker? , 2005, Connect. Sci..

[35]  Risto Miikkulainen,et al.  Incremental Evolution of Complex General Behavior , 1997, Adapt. Behav..

[36]  D. Floreano,et al.  Division of labour and colony efficiency in social insects: effects of interactions between genetic architecture, colony kin structure and rate of perturbations , 2006, Proceedings of the Royal Society B: Biological Sciences.

[37]  Lynne E. Parker,et al.  Multi-Robot Systems: From Swarms to Intelligent Automata , 2002, Springer Netherlands.

[38]  Jean-Arcady Meyer,et al.  From Animals to Animats: Proceedings of The First International Conference on Simulation of Adaptive Behavior (Complex Adaptive Systems) , 1990 .

[39]  James A. Hendler,et al.  Co-evolving Soccer Softbot Team Coordination with Genetic Programming , 1997, RoboCup.

[40]  L. Keller,et al.  The evolution of cooperation and altruism – a general framework and a classification of models , 2006, Journal of evolutionary biology.

[41]  Michael G. Dyer,et al.  Construction in a Simulated Environment Using Temporal Goal Sequencing and Reinforcement Learning , 2009, Adapt. Behav..

[42]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[43]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[44]  Geoff S. Nitschke,et al.  Neuro-Evolution Methods for Gathering and Collective Construction , 2009, ECAL.

[45]  Rudolf Paul Wiegand,et al.  An analysis of cooperative coevolutionary algorithms , 2004 .

[46]  S. Nolfi.  Evorobot 1 . 1 User Manual , 2000 .

[47]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation (3rd Edition) , 2007 .

[48]  E. Bonabeau,et al.  Quantitative study of the fixed threshold model for the regulation of division of labour in insect societies , 1996, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[49]  Guy Theraulaz,et al.  Adaptive Task Allocation Inspired by a Model of Division of Labor in Social Insects , 1997, BCEC.

[50]  Luca Maria Gambardella,et al.  Collaboration Through the Exploitation of Local Interactions in Autonomous Collective Robotics: The Stick Pulling Experiment , 2001, Auton. Robots.

[51]  Kagan Tumer,et al.  Efficient Evaluation Functions for Multi-rover Systems , 2004, GECCO.

[52]  Radhika Nagpal,et al.  Three-Dimensional Construction with Mobile Robots and Modular Blocks , 2008, Int. J. Robotics Res..

[53]  Nicholas H Barton,et al.  SPECIATION THROUGH COMPETITION: A CRITICAL REVIEW , 2005, Evolution; international journal of organic evolution.

[54]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[55]  Mark Wineberg,et al.  The Underlying Similarity of Diversity Measures Used in Evolutionary Computation , 2003, GECCO.

[56]  David B. Fogel,et al.  Evolving neural networks to play checkers without relying on expert knowledge , 1999, IEEE Trans. Neural Networks.

[57]  Risto Miikkulainen,et al.  Neuroevolution for adaptive teams , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[58]  Risto Miikkulainen,et al.  Robust non-linear control through neuroevolution , 2003 .

[59]  Sean Luke,et al.  Genetic Programming Produced Competitive Soccer Softbot Teams for RoboCup97 , 1998 .

[60]  Dario Floreano,et al.  Genetic Team Composition and Level of Selection in the Evolution of Cooperation , 2009, IEEE Transactions on Evolutionary Computation.

[61]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[62]  H. Seligmann,et al.  Resource partition history and evolutionary specialization of subunits in complex systems. , 1999, Bio Systems.

[63]  Eduardo F. Morales,et al.  An Introduction to Reinforcement Learning , 2011 .

[64]  Gaurav S. Sukhatme,et al.  Spreading Out: A Local Approach to Multi-robot Coverage , 2002, DARS.

[65]  Ling Li,et al.  Learning and Measuring Specialization in Collaborative Swarm Systems , 2004, Adapt. Behav..

[66]  Daniele Nardi,et al.  Multirobot systems: a classification focused on coordination , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[67]  Andrew B. Williams,et al.  Multirobot task allocation in lunar mission construction scenarios , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[68]  Mitchel Resnick,et al.  Turtles, termites, and traffic jams - explorations in massively parallel microworlds , 1994 .

[69]  Luc Steels,et al.  Towards a theory of emergent functionality , 1991 .

[70]  Gerardo Beni,et al.  From Swarm Intelligence to Swarm Robotics , 2004, Swarm Robotics.

[71]  Stefano Nolfi,et al.  Coordination and Behaviour Integration in Cooperating Simulated Robots , 2004 .

[72]  Martijn C. Schut,et al.  Collective neuro-evolution for evolving specialized sensor resolutions in a multi-rover task , 2010, Evol. Intell..