An Alternative Method to Approximate the Inverse Kinematics of Unknown Geometry Manipulators Using an RBFN with Regularly-Spaced Position Centres

This paper presents a novel solution using Radial Basis Function Networks (RBFNs) to approximate the inverse kinematics of unknown geometry manipulatos (e.g. a robot-vision system). This approach has two fundamental principles: centres of hidden-layer units are regularly distributed in the workspace and constrained training data is used where inputs are collected around the centre positions in the workspace. To verify the performance of the proposed approach, simulations in Matlab and practical experiment have been performed. The results of both the simulation and experiment prove that the proposed approach is effective.