Evolving Robot Behaviours with Diffusing Gas Networks

This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Using Jakobi's radical minimal simulations, successful behaviours have been consistently evolved in far fewer evaluations than were needed when using more conventional connectionist style networks. Indeed the reduction is by a factor of roughly one order of magnitude.

[1]  Stefano Nolfi,et al.  Evolving Artificial Neural Networks that Develop in Time , 1995, ECAL.

[2]  Christopher G. Langton,et al.  Artificial Life III , 2000 .

[3]  Giles Mayley,et al.  Landscapes, Learning Costs, and Genetic Assimilation , 1996, Evolutionary Computation.

[4]  Rodney A. Brooks,et al.  Coherent behavior from many adaptive processes , 1994 .

[5]  D. Cliff.  From animals to animats 3 : proceedings of the Third International Conference on Simulation of Adaptive Behavior , 1994 .

[6]  Inman Harvey,et al.  The use of genetic algorithms for the development of sensorimotor control systems , 1994, Proceedings of PerAc '94. From Perception to Action.

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

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

[9]  Nick Jakobi,et al.  Minimal simulations for evolutionary robotics , 1998 .

[10]  J. Garthwaite.  Glutamate, nitric oxide and cell-cell signalling in the nervous system , 1991, Trends in Neurosciences.

[11]  Phil Husbands,et al.  Distributed Coevolutionary Genetic Algorithms for Multi-Criteria and Multi-Constraint Optimisation , 1994, Evolutionary Computing, AISB Workshop.

[12]  M. Boden.  The Philosophy of Artificial Life , 1996 .

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

[14]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[15]  Rodney A. Brooks,et al.  Challenges for complete creature architectures , 1991 .

[16]  Nick Jakobi,et al.  Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis , 1997, Adapt. Behav..

[17]  Inman Harvey,et al.  Evolutionary robotics and SAGA: The case for hill crawling and tournament selection , 1994 .