DocumentCode :
2918189
Title :
Evolutionary spiking neural networks as racing car controllers
Author :
Yee, Elias ; Teo, Jason
Author_Institution :
Sch. of Eng. & Inf. Technol., Univ. Malaysia Sabah, Kota Kinabalu, Malaysia
fYear :
2011
fDate :
5-8 Dec. 2011
Firstpage :
411
Lastpage :
416
Abstract :
The Izhikevich spiking neural network model is investigated as a method to develop controllers for a simple, but not trivial, car racing game, called TORCS. The controllers are evolved using Evolutionary Programming, and the performance of the best individuals is compared with the hand-coded controller included with the Simulated Car Racing Championship API. The results are promising, indicating that this neural network model can be applied to other games or control problems.
Keywords :
automobiles; evolutionary computation; neurocontrollers; API; Izhikevich spiking neural network model; TORCS; car racing game; evolutionary programming; evolutionary spiking neural network; hand-coded controller; racing car controller; simulated car racing championship; Biological neural networks; Biological system modeling; Computational modeling; Electric potential; Games; Mathematical model; Neurons; Izhikevich neuron model; Spiking neural networks; TORCS; car racing; evolutionary programming; games;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Hybrid Intelligent Systems (HIS), 2011 11th International Conference on
Conference_Location :
Melacca
Print_ISBN :
978-1-4577-2151-9
Type :
conf
DOI :
10.1109/HIS.2011.6122141
Filename :
6122141
Link To Document :
بازگشت