Evolution and Development of Neural Networks Controlling Locomotion, Gradient-Following, and Obstacle-Avoidance in Artificial Insects

This paper describes how the SGOCE paradigm has been used to evolve developmental programs capable of generating neural networks that control the behavior of simulated insects. This paradigm is characterized by an encoding scheme, by an evolutionary algorithm, and by an incremental strategy that are described in turn. The additional use of an insect model equipped with 6 legs and two antennae made it possible to generate control modules that allowed to successively add gradient-following and obstacle-avoidance capacities to walking behavior. The advantages of this evolutionary approach, together with directions for future work, are discussed. Keywords— SGOCE Paradigm, Recurrent Neural Networks, Leaky Integrators, Genetic Programming, Animats.

[1]  C. Gallistel.  The Organization of Action: A New Synthesis , 1982 .

[2]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[3]  Clive Richards,et al.  The Blind Watchmaker , 1987, Bristol Medico-Chirurgical Journal.

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Darrell Whitley,et al.  Applying genetic algorithms to neural network learning , 1989 .

[6]  Rodney A. Brooks,et al.  A robot that walks; emergent behaviors from a carefully evolved network , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

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

[8]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[9]  R. Beer,et al.  Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology , 1990 .

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

[11]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[12]  H. D. Garis.  Brain Building - The Genetic Programming of Artificial Nervous Systems and Artificial Embryos , 1991 .

[13]  Andrew H. Fagg,et al.  Genetic programming approach to the construction of a neural network for control of a walking robot , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[14]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[15]  Randall D. Beer,et al.  Evolving Dynamical Neural Networks for Adaptive Behavior , 1992, Adapt. Behav..

[16]  Inman Harvey,et al.  Explorations in Evolutionary Robotics , 1993, Adapt. Behav..

[17]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[18]  Graham F. Spencer,et al.  Automatic Generation of Programs for Crawling and Walking , 1993, International Conference on Genetic Algorithms.

[19]  Craig W. Reynolds.  Evolution of corridor following behavior in a noisy world , 1994 .

[20]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

[21]  Frédéric Gruau,et al.  Automatic Definition of Modular Neural Networks , 1994, Adapt. Behav..

[22]  Inman Harvey,et al.  Seeing the light: artificial evolution, real vision , 1994 .

[23]  Jeffrey Meyer.  The animat approach to cognitive science , 1994 .

[24]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex adaptive systems.

[25]  Frederic Gruau.  Synthèse de réseaux de neurones par codage cellulaire et algorithmes génétiques , 1994 .

[26]  Vasant Honavar,et al.  Evolutionary Design of Neural Architectures , 1995 .

[27]  Frédéric Gruau.  Artificial Cellular Development in Optimization and Compilation , 1995, Towards Evolvable Hardware.

[28]  J. Urgen Branke.  Evolutionary Algorithms for Neural Network Design and Training , 1995 .

[29]  Richard K. Belew,et al.  Methods for Competitive Co-Evolution: Finding Opponents Worth Beating , 1995, ICGA.

[30]  Randall D. Beer,et al.  On the Dynamics of Small Continuous-Time Recurrent Neural Networks , 1995, Adapt. Behav..

[31]  Jean-Arcady Meyer,et al.  Evolution and development of control architectures in animats , 1995, Robotics Auton. Syst..

[32]  Jan Paredis,et al.  Coevolutionary Computation , 1995, Artificial Life.

[33]  Maja J. Matarić,et al.  A Developmental Model for the Evolution of Complete Autonomous Agents , 1996 .

[34]  Jean-Arcady Meyer,et al.  Artificial Life and the Animat Approach to Artificial Intelligence , 1996, Artificial Intelligence.

[35]  John Hallam,et al.  A hybrid GP/GA approach for co-evolving controllers and robot bodies to achieve fitness-specified tasks , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[36]  Pattie Maes,et al.  Dynamics of Co-evolutionary Learning , 1996 .

[37]  Takashi Gomi,et al.  Evolutionary robotics-an overview , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[38]  Dave Cliff,et al.  Challenges in evolving controllers for physical robots , 1996, Robotics Auton. Syst..

[39]  Pattie Maes,et al.  Co-evolution of Pursuit and Evasion II: Simulation Methods and Results , 1996 .

[40]  John Hallam,et al.  Applying genetic programming to evolve behavior primitives and arbitrators for mobile robots , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[41]  Jean-Arcady Meyer,et al.  From natural to artificial life: Biomimetic mechanisms in animat designs , 1997, Robotics Auton. Syst..

[42]  Jean-Arcady Meyer,et al.  Evolution and Development of Modular Control Architectures for 1D Locomotion in Six-legged Animats , 1998, Connect. Sci..