Automatic Generation of Controllers for Embodied Legged Organisms: A Pareto Evolutionary Multi-Objective Approach

In this paper, we investigate the use of a self-adaptive Pareto evolutionary multi-objective optimization (EMO) approach for evolving the controllers of virtual embodied organisms. The objective of this paper is to demonstrate the trade-off between quality of solutions and computational cost. We show empirically that evolving controllers using the proposed algorithm incurs significantly less computational cost when compared to a self-adaptive weighted sum EMO algorithm, a self-adaptive single-objective evolutionary algorithm (EA) and a hand-tuned Pareto EMO algorithm. The main contribution of the self-adaptive Pareto EMO approach is its ability to produce sufficiently good controllers with different locomotion capabilities in a single run, thereby reducing the evolutionary computational cost and allowing the designer to explore the space of good solutions simultaneously. Our results also show that self-adaptation was found to be highly beneficial in reducing redundancy when compared against the other algorithms. Moreover, it was also shown that genetic diversity was being maintained naturally by virtue of the system's inherent multi-objectivity.

[1]  Jeffrey L. Krichmar,et al.  Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines , 2001, Complex..

[2]  Richard K. Belew,et al.  Evolving networks: using the genetic algorithm with connectionist learning , 1990 .

[3]  Maciej Komosinski,et al.  From Directed to Open-Ended Evolution in a Complex Simulation Model , 2000 .

[4]  Maciej Komosinski,et al.  Comparison of Different Genotype Encodings for Simulated Three-Dimensional Agents , 2002, Artificial Life.

[5]  Rolf Pfeifer,et al.  A method for isolating morphological effects on evolved behaviour , 2002 .

[6]  Jordan B. Pollack,et al.  Evolutionary Techniques in Physical Robotics , 2000, ICES.

[7]  Moshe Sipper,et al.  Surprise versus unsurprise: Implications of emergence in robotics , 2001, Robotics Auton. Syst..

[8]  Stuart A. Kauffman,et al.  ORIGINS OF ORDER , 2019, Origins of Order.

[9]  John Hallam,et al.  Evolving sufficient robot controllers , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[10]  Hussein A. Abbass,et al.  An evolutionary artificial neural networks approach for breast cancer diagnosis , 2002, Artif. Intell. Medicine.

[11]  J. Teo,et al.  Coordination and synchronization of locomotion in a virtual robot , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[12]  Julian Francis Miller,et al.  Information Characteristics and the Structure of Landscapes , 2000, Evolutionary Computation.

[13]  Chandana Paul,et al.  Making Evolution an Offer It Can't Refuse: Morphology and the Extradimensional Bypass , 2001, ECAL.

[14]  T. Kellam,et al.  Artificial Minds , 1996, Inf. Process. Manag..

[15]  Hussein A. Abbass,et al.  TRADING-OFF MIND COMPLEXITY AND LOCOMOTION IN A PHYSICALLY SIMULATED QUADRUPED , 2002 .

[16]  Gregory S. Hornby,et al.  Body-brain co-evolution using L-systems as a generative encoding , 2001 .

[17]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[18]  Nick Jacobi,et al.  Running Across the Reality Gap: Octopod Locomotion Evolved in a Minimal Simulation , 1998, EvoRobot.

[19]  Isaac Meilijson,et al.  Localization of Function via Lesion Analysis , 2003, Neural Computation.

[20]  Chandana Paul,et al.  The road less travelled: morphology in the optimization of biped robot locomotion , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[21]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[22]  Torsten Reil,et al.  Biologically inspired control of physically simulated bipeds , 2001, Theory in Biosciences.

[23]  Chandana Paul,et al.  Investigating Morphological Symmetry and Locomotive Efficiency using Virtual Embodied Evolution , 2000 .

[24]  Colm Massey,et al.  Recent Developments in the Evolution of Morphologies and Controllers for Physically Simulated Creatures , 2000, Artificial Life.

[25]  R. Pfeifer,et al.  Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny , 2001 .

[26]  Hussein A. Abbass,et al.  The Pareto Differential Evolution Algorithm , 2002, Int. J. Artif. Intell. Tools.

[27]  Moshe Sipper,et al.  An Introduction To Articial Life , 1995 .

[28]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[29]  B. Grzimek,et al.  Grzimek's Animal Life Encyclopedia , 1984 .

[30]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[31]  D. Floreano,et al.  Synthesis of autonomous robots through evolution , 2002, Trends in Cognitive Sciences.

[32]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[33]  Christoph Endres,et al.  Introduction to Artificial Life , 2000, Künstliche Intell..

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

[35]  Stephen Jones,et al.  Mutualism Promotes Diversity and Stability in a Simple Artificial Ecosystem , 2002, Artificial Life.

[36]  Josh Bongard,et al.  Evolving modular genetic regulatory networks , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[37]  Dario Floreano,et al.  Evolutionary Robotics: The Next Generation , 2000 .

[38]  Eytan Ruppin,et al.  Patterns of Functional Damage in Neural Network Models of Associative Memory , 1995, Neural Computation.

[39]  Simon Parsons,et al.  Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines by Stefano Nolfi and Dario Floreano, MIT Press, 320 pp., $28.00, ISBN 0-262-14070-5 , 2004, Knowledge engineering review (Print).

[40]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[41]  Akio Ishiguro,et al.  Evolving an adaptive controller for a quadruped-robot with dynamically-rearranging neural networks , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[42]  Jordan B. Pollack,et al.  Automatic design and manufacture of robotic lifeforms , 2000, Nature.

[43]  H. Abbass,et al.  PDE: a Pareto-frontier differential evolution approach for multi-objective optimization problems , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[44]  Hussein A. Abbass,et al.  Multiobjectivity and complexity in embodied cognition , 2005, IEEE Transactions on Evolutionary Computation.

[45]  Richard Walker,et al.  Genetic Redundancy in Evolving Populations of Simulated Robots , 2002, Artificial Life.

[46]  Phil Husbands,et al.  Better Living Through Chemistry: Evolving GasNets for Robot Control , 1998, Connect. Sci..

[47]  Hussein A. Abbass,et al.  Multi-objectivity for brain-behavior evolution of a physically-embodied organism , 2002 .

[48]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[49]  Thomas S. Ray.  Aesthetically Evolved Virtual Pets , 2001, Leonardo.

[50]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

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

[52]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[53]  Maciej Komosinski,et al.  The World of Framsticks: Simulation, Evolution, Interaction , 2000, Virtual Worlds.

[54]  John Hallam,et al.  An evolutionary approach to quantify internal states needed for the woods problem , 2002 .

[55]  J. Bongard.  Evolved Sensor Fusion and Dissociation in an Embodied Agent , 2002 .

[56]  H. Abbass.  The self-adaptive Pareto differential evolution algorithm , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[57]  Hussein A. Abbass,et al.  A Memetic Pareto Evolutionary Approach to Artificial Neural Networks , 2001, Australian Joint Conference on Artificial Intelligence.

[58]  Stefano Nolfi,et al.  Learning and Evolution , 1999, Auton. Robots.

[59]  Phil Husbands,et al.  Fitness Landscapes and Evolvability , 2002, Evolutionary Computation.

[60]  David W. Corne,et al.  Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy , 2000, Evolutionary Computation.

[61]  Francesco Mondada,et al.  Evolutionary neurocontrollers for autonomous mobile robots , 1998, Neural Networks.

[62]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[63]  John R. Koza,et al.  Genetic generation of both the weights and architecture for a neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[64]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .

[65]  Phil Husbands,et al.  Evolution of central pattern generators for bipedal walking in a real-time physics environment , 2002, IEEE Trans. Evol. Comput..

[66]  John S. McCaskill,et al.  From Directed to Open-Ended Evolution in a Complex Simulation Model , 2000 .

[67]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[68]  Hussein A. Abbass,et al.  Speeding Up Backpropagation Using Multiobjective Evolutionary Algorithms , 2003, Neural Computation.

[69]  Eckart Zitzler,et al.  Evolutionary algorithms for multiobjective optimization: methods and applications , 1999 .

[70]  Hussein A. Abbass,et al.  Searching under Multi-evolutionary Pressures , 2003, EMO.

[71]  Karl Sims,et al.  Evolving 3D Morphology and Behavior by Competition , 1994, Artificial Life.

[72]  Sung-Bae Cho,et al.  A Comprehensive Overview of the Applications of Artificial Life , 2006, Artificial Life.

[73]  Karl Sims,et al.  Evolving virtual creatures , 1994, SIGGRAPH.

[74]  Stefano Nolfi,et al.  Power and the limits of reactive agents , 2002, Neurocomputing.