Super-lampreys and wave energy: Optimised control of artificially-evolved, simulated swimming lamprey

Propulsion in the lamprey, an eel-like fish, is governed by activity in its spinal neural network (called a central pattern generator (CPG)). This CPG is simulated, in accordance with Ekeberg's original model, and optimised alternatives are generated with genetic algorithms (GAs). A two-phase GA is adopted: (1) to evolve neuron-descriptive parameters and synaptic weights of the neural oscillator for a single lamprey segment, (2) to generate interconnections between segments. Results demonstrate that Ekeberg's prototype is not a unique solution and that simpler versions with wider operational ranges can be generated. Evolved solutions outperform the swimming capabilities of a modelled biological organism, as an initial step in understanding how to control wave power devices, with similar motion to the lamprey.

[1]  S. Grillner,et al.  Newly identified 'glutamate interneurons' and their role in locomotion in the lamprey spinal cord. , 1987, Science.

[2]  C. Rovainen.  Neurobiology of lampreys. , 1979, Physiological reviews.

[3]  S. Grillner,et al.  Neuronal network generating locomotor behavior in lamprey: circuitry, transmitters, membrane properties, and simulation. , 1991, Annual review of neuroscience.

[4]  C von Euler,et al.  On the central pattern generator for the basic breathing rhythmicity. , 1983, Journal of applied physiology: respiratory, environmental and exercise physiology.

[5]  D. Willshaw,et al.  Artificial Lampreys: Comparing Naturally and Artificially Evolved Swimming Controllers , 1997 .

[6]  P.C. Loizou,et al.  A neural network model for optimizing vowel recognition by cochlear implant listeners , 2001, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  Meng Joo Er,et al.  An intelligent adaptive control scheme for postsurgical blood pressure regulation , 2005, IEEE Transactions on Neural Networks.

[8]  John Hallam,et al.  Causal Neural Control of a Latching Ocean Wave Point Absorber , 2005, ICANN.

[9]  G. Ermentrout,et al.  Modelling of intersegmental coordination in the lamprey central pattern generator for locomotion , 1992, Trends in Neurosciences.

[10]  A. Murray,et al.  Increased swimming control with evolved lamprey CPG controllers , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[11]  T. Williams.  Phase coupling by synaptic spread in chains of coupled neuronal oscillators. , 1992, Science.

[12]  Herbert L. Roitblat,et al.  NEURAL NETWORK MODELING OF A DOLPHIN'S SONAR DISCRIMINATION CAPABILITIES , 1994 .

[13]  Örjan Ekeberg,et al.  A combined neuronal and mechanical model of fish swimming , 2005, Biological Cybernetics.

[14]  J. Ayers.  Underwater walking. , 2004, Arthropod structure & development.

[15]  Azim Eskandarian,et al.  Unobtrusive drowsiness detection by neural network learning of driver steering , 2001 .

[16]  P. Meyrand,et al.  In Vivo Modulation of Interacting Central Pattern Generators in Lobster Stomatogastric Ganglion: Influence of Feeding and Partial Pressure of Oxygen , 1998, The Journal of Neuroscience.

[17]  Paul F. M. J. Verschure,et al.  Collision avoidance using a model of the locust LGMD neuron , 2000, Robotics Auton. Syst..

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

[19]  Frank Kirchner,et al.  Ambulating Robots for Exploration in Rough Terrain on Future Extraterrestial Missions , 2004 .

[20]  S. Grillner,et al.  N-methyl-d-aspartate (NMDA), kainate and quisqualate receptors and the generation of fictive locomotion in the lamprey spinal cord , 1985, Brain Research.

[21]  Carl E. Rasmussen,et al.  Occam's Razor , 2000, NIPS.

[22]  P E Nachtigall,et al.  Neural network modeling of a dolphin's sonar discrimination capabilities. , 1995, The Journal of the Acoustical Society of America.

[23]  Örjan Ekeberg,et al.  A computer based model for realistic simulations of neural networks , 1991, Biological Cybernetics.

[24]  U. Bässler,et al.  Pattern generation for stick insect walking movements—multisensory control of a locomotor program , 1998, Brain Research Reviews.

[25]  S. Grillner,et al.  Activation of NMDA-receptors elicits "fictive locomotion" in lamprey spinal cord in vitro. , 1981, Acta physiologica Scandinavica.

[26]  S. Grillner,et al.  Neural networks for vertebrate locomotion. , 1996, Scientific American.

[27]  S. Grillner,et al.  A computer-based model for realistic simulations of neural networks. II. The segmental network generating locomotor rhythmicity in the lamprey. , 1992 .

[28]  D. A. Helweg,et al.  Classification of Aspect-Dependent Targets by a Biomimetic Neural Network. , 1997 .

[29]  P. Wallén,et al.  The neuronal correlate of locomotion in fish , 1980, Experimental Brain Research.

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

[31]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[32]  Auke Jan Ijspeert,et al.  Design of artificial neural oscillatory circuits for the control of lamprey- and salamander-like locomotion using evolutionary algorithms , 1998 .