Evolution and development of neural controllers for 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 recurrent neural networks that control the behavior of simulated insects. This paradigm is characterized by an encoding scheme, by an evolutionary algorithm, by syntactic constraints, and by an incremental strategy that are described in turn. The additional use of an insect model equipped with six legs and two antennae made it possible to generate control modules that allowed it 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.

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

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

[3]  R. Dawkins The Blind Watchmaker , 1986 .

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

[5]  Rodney A. Brooks,et al.  A Robot that Walks; Emergent Behaviors from a Carefully Evolved Network , 1989, Neural Computation.

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

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

[8]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

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

[10]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  A. P. Wieland,et al.  Evolving neural network controllers for unstable systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[12]  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.

[13]  Idan Segev Single neurone models: oversimple, complex and reduced , 1992, Trends in Neurosciences.

[14]  George W. Irwin,et al.  Neural networks for control and systems , 1992 .

[15]  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.

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

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

[18]  H. Spitzer,et al.  A model for detection of spatial and temporal edges by a single X cell , 1993, Vision Research.

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

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

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

[22]  P. S. Shcherbakov,et al.  Learning in neural networks and stochastic approximation methods with averaging , 1994 .

[23]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

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

[25]  Inman Harvey,et al.  Seeing the Light: Artiicial Evolution, Real Vision Seeing the Light: Artiicial Evolution, Real Vision , 1994 .

[26]  Jan Paredis,et al.  Coevolutionary computation , 1995 .

[27]  Barak A. Pearlmutter Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[28]  David B. Fogel,et al.  Evolving Neural Control Systems , 1995, IEEE Expert.

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

[30]  Vasant Honavar,et al.  Evolutionary Design of Neural Architectures -- A Preliminary Taxonomy and Guide to Literature , 1995 .

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

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

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

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

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

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

[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]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.

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

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

[44]  William R. Softky,et al.  Single-cell models , 1998 .

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