Kinematics Decoupling of Mobile Robot Based on RBF Neural Network and Genetic Algorithm

The mobile manipulator is a multivariable and non-linear system, so the research about the kinematics decoupling of mobile manipulator is important, especially the control methods based on neural network. To solve the deficiency of neural network such as decision of structure and adjustment of parameters in hidden-unit, genetic algorithm based on RBF neural network is presented to deal with kinematics decoupling of mobile manipulator. The centers and widths of hidden layer and the weights of the output layer are coded into one chromosome. It strengthens the cooperation between the hidden layer and the output layer, and avoids the risk of getting stuck into a local minimum. RBF neural network using genetic algorithm is established for kinematics decoupling which brought by coordinated motion between the manipulator and mobile platform of mobile robot system. The experimental results show the method reasonable and effective.

[1]  Lalit M. Patnaik,et al.  Adaptive probabilities of crossover and mutation in genetic algorithms , 1994, IEEE Trans. Syst. Man Cybern..

[2]  Yangmin Li,et al.  Hybrid kinematics and dynamics analysis for a mobile modular manipulator , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[3]  Yi Huang,et al.  RBF Neural Network Based on Genetic Algorithm Used in Line Loss Calculation for Distribution Network , 2007, Third International Conference on Natural Computation (ICNC 2007).

[4]  Lipo Wang,et al.  Genetic algorithms for optimal channel assignment in mobile communications , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[5]  Lipo Wang,et al.  Genetic Algorithms with Stochastic Ranking for Optimal Channel Assignment in Mobile Communications , 2004, CIS.