Quadratic Leaky Integrate-and-Fire Neural Network Tuned with an Evolution-Strategy for a Simulated 3D Biped Walking Controller

This paper presents the results of experiments in applying a spiking neural network to control the locomotion of a simulated biped robot. The neural model used in simulations was developed to allow for an analytic solution to a neuron's fire time, while maintaining a non-instant post-synaptic potential rise time. The synaptic weights and delays were tuned using an evolution-strategy. Simulation experiments demonstrate that already within about two thousand generations the biped is able to acquire a dynamic walk which allows it to walk upright for several metres.

[1]  Manfred Hild,et al.  Evolution of Biped Walking Using Neural Oscillators and Physical Simulation , 2008, RoboCup.

[2]  Alex M. Andrew,et al.  Spiking Neuron Models: Single Neurons, Populations, Plasticity , 2003 .

[3]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[4]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[5]  Eduardo Ros,et al.  Event-Driven Simulation Scheme for Spiking Neural Networks Using Lookup Tables to Characterize Neuronal Dynamics , 2006, Neural Computation.

[6]  T. Makino.  A Discrete-Event Neural Network Simulator for General Neuron Models , 2003, Neural Computing & Applications.

[7]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[8]  Florentin Wörgötter,et al.  Correction: Adaptive, Fast Walking in a Biped Robot under Neuronal Control and Learning , 2007, PLoS Comput. Biol..

[9]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[10]  Ching-Long Shih,et al.  Asymptotically Stable Walking of a Simple Underactuated 3D Bipedal Robot , 2007, IECON 2007 - 33rd Annual Conference of the IEEE Industrial Electronics Society.

[11]  Jun Morimoto,et al.  Learning Biped Locomotion , 2007, IEEE Robotics & Automation Magazine.

[12]  Wolfgang Maass,et al.  An E cient Implementation of Sigmoidal Neural Nets in Temporal Coding with Noisy Spiking Neurons , 1995 .

[13]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[14]  Kazuhito Yokoi,et al.  Biped walking pattern generation by using preview control of zero-moment point , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[15]  Stephan K. Chalup,et al.  A small spiking neural network with LQR control applied to the acrobot , 2008, Neural Computing and Applications.