Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling

A new method is presented for extending an incomplete mathematical model - in this case a dynamic model of a six degrees of freedom robotic manipulator. A nonlinear multivariate calibration of input-output training data from several typical motion trajectories is carried out with the aim of predicting the model systematic output error at time (t+1) from known input reference up till and including time (t). A new partial least squares regression (PLSR) based method, nominal PLSR with interactions was developed and used to handle, unmodelled nonlinearities. The performance of the new method is compared with least squares (LS). Different cross-validation schemes were compared in order to assess the sampling of the state space based on conventional trajectories. The method developed in the paper can be used as fault monitoring mechanism and early warning system for sensor failure. The results show that the suggested methods improves trajectory tracking performance of the robotic manipulator by extending the initial dynamic model of the manipulator.