Forward kinematic analysis of planar parallel robots using a neural network-based approach optimized by machine learning

The forward kinematic problem of parallel robots is always considered as a challenge in the field of parallel robots due to the obtained nonlinear system of equations. In this paper, the forward kinematic problem of planar parallel robots in their workspace is investigated using a neural network based approach. In order to increase the accuracy of this method, the workspace of the parallel robot is divided into a number of smaller subspaces using the classifier and the boundary overlap method. After estimating the corresponding subspace, two separate neural networks are used in each subspace to determine the position and orientation of the moving platform. This approach is implemented on a 3-PRR planar parallel robot and its results are compared with the results obtained from the MLP, WaveNet, GMDH, Dual and Independent neural networks. Moreover, in order to evaluate the efficiency of the proposed method, a circular motion path is simulated using this approach and its performance is compared with the five mentioned methods. The results obtained from the implementation of this approach and comparison with the conventional methods indicates that the proposed method analyzes the forward kinematic problem of planar parallel robot with proper accuracy.