Model‐based control of industrial manipulators: An experimental analysis

Abstract

Abstract Model‐based control techniques for industrial robotic manipulators were experimentally analyzed. The case study for the analysis was the first three joints of a PUMA‐560. Development of an advanced control evaluation environment removed the computational restrictions of previous studies. The specific issues of: incomplete and/or asynchronous dynamic compensation, feedback paradigm selection, payload sensitivity, and drive systems effects were experimentally analyzed. Evaluation results clearly demonstrate that the performance improvement capability of model‐based control is not restricted to research robots. A model‐based controller with complete feedforward compensation and sliding mode feedback reduced the maximum tracking error by at least a factor of five when compared to feedback alone. End‐effector payload invariant tracking only requires mass information. Tracking performance is not dependent on dynamic compensation at the servo rate. Evaluation results provide insight for adaptive control law design and a baseline to compare their performance against.