Learning of inverse kinematics using a neural network with efficient weights tuning ability

Generally, in making a neural network learn nonlinear relations properly, desired training set are used. The training set consists of multiple pairs of an input vector and an output one. Each input vector is given to the input layer for forward calculation, and the corresponding output vector is compared with the vector yielded from the output layer. Also, weights are updated using a back propagation algorithm in backward calculation. The time required for the learning process of the neural network depends on the number of total weights in the neural network and the one of the input-output pairs in the training set. In the proposed learning process, after the learning is progressed e.g., 200 iterations, input-output pairs having had worse errors are extracted from the original training set and form a new temporary set. From the next iteration, the temporary set is applied instead of the original set. In this case, only pairs with worse errors are used for updating the weights until the mean value of errors reduces to a level. After the learning conducted using the temporary set, the original set is applied again instead of the temporary set. It is expected by alternately applying the above two types of sets for iterative learning that the convergence time can be efficiently reduced. The effectiveness is proved through simulation experiments using a kinematic model of a leg with four-DOFs.