LEARNING APPROXIMATION OF FEEDFORWARD CONTROL DEPENDENCE ON THE TASK PARAMETERS WITH APPLICATION TO DIRECT-DRIVE MANIPULATOR TRACKING

This paper presents a new paradigm for model-free design of a trajecto ry tracking controller and its experimental implementation in control of a direct-drive manipulator, In accordance with the paradigm, a nonl inear approximation for the feedforward control is used, The input to the approximation scheme are task parameters that define the trajector y to be tracked. The initial data for the approximation is obtained by performing learning control iterations for a number of selected tasks , The paper develops and implements practical approaches to both the a pproximation and learning control. As the initial feedforward data nee ds to be obtained for many different tasks, it is important to have fa st and robust convergence of the learning control iterations, To satis fy this requirement, we propose a new learning control algorithm based on the on-line Levenberg-Marquardt minimization of a regularized trac king error index, The paper demonstrates an experimental application o f the paradigm to trajectory tracking control of fast (1.25 s) motions of a direct-drive industrial robot AdeptOne. In our experiments, the learning control converges in five to six iterations for a given set o f the task parameters. Radial Basis Function approximation based on th e learning results for 45 task parameter vectors brings an average imp rovement of four times in the tracking accuracy for all motions in the robot workspace, The high performance of the designed approximation-b ased controller is achieved despite nonlinearity of the system dynamic s and large Coulomb friction. The results obtained open an avenue for industrial applications of the proposed approach in robotics and elsew here.