Simulated 3D biped walking with an evolution-strategy tuned spiking neural network

Title:

Simulated 3D biped walking with an evolution-strategy tuned spiking neural network

Creator:

Wiklendt, Lukasz, Chalup, Stephan K. , and Seron , María M.

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:2091dafe-91bc-47ca-a656-8890433b7444
uuid:2091dafe-91bc-47ca-a656-8890433b7444

Subject:

Spiking neurons, evolution strategy, and biped locomotion

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

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 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 within about seven thousand generations the biped is able to acquire a dynamic walk which allows it to walk upright for several metres.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2009 Volume:19 | Number:2

Harvested from:

CDK

Metadata only:

false