DocumentCode :
412621
Title :
Truck backing up neural network controller optimized by genetic algorithms
Author :
Ho, M.L. ; Chan, P.T. ; Rad, A.B. ; Mak, C.H.
Author_Institution :
Dept. of Electr. Eng., Hong Kong Polytech. Univ., China
Volume :
2
fYear :
2003
fDate :
8-12 Dec. 2003
Firstpage :
944
Abstract :
Jenkins-Yuhas network has been applied successfully to solve the trailer-truck backing up problem. Genetic algorithms (GA) is used to train the Jenkins-Yuhas network controller. The integration of genetic algorithms and neural networks training avoids complicated formulation of derivative function that required in conventional error back propagation techniques (gradient descent). In addition, it can avoid trapping in local minimum point. The performance of GA trained neural network controller is evaluated via simulation studies. It has been demonstrated that the controller can successfully control trailer-truck for different initial parking conditions, i.e. with same set of trained weights, to the loading dock.
Keywords :
backpropagation; genetic algorithms; neurocontrollers; GA; Jenkins-Yuhas network controller; derivative function; error back propagation technique; genetic algorithm; loading dock; neural networks training; optimization; parking conditions; trailer-truck backing up problem; Control systems; Genetic algorithms; Mathematical model; Multi-layer neural network; Neural networks; Neurons; Nonlinear control systems; Optimization methods; System analysis and design; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 2003. CEC '03. The 2003 Congress on
Print_ISBN :
0-7803-7804-0
Type :
conf
DOI :
10.1109/CEC.2003.1299768
Filename :
1299768
Link To Document :
بازگشت