Inverse kinematics solution of 3-DOF platform based on neural networks

Inverse kinematics solution is the basis of design and control of 3-DOF platform. The traditional numerical method is too complicated to be as a real time control algorithm. Methods based on BP neural network and RBF neural network were studied to solve inverse kinematics. The training samples were obtained through off-line numerical method with high precision. Using momentum technique, variable learning rate technique and conjugate gradient algorithm to accelerate the convergence speed of BP network. The RBF network trained by OLS algorithm can get smaller generalization error, it is more suitable for real time control.