A Data-Driven Approach for Online Path Correction of Industrial Robots Using Modified Flexible Dynamics Model and Disturbance State Observer

Abstract

The typical industrial robots, though highly repeatable, have relatively low path accuracy. As the main source of the path deviations, joint flexibility-induced position errors between motor and link called joint position errors (JPEs) are difficult to compensate directly in the robot controller due to the lack of link-side encoders for most industrial robots. This limits the development of industrial robots to high-accuracy applications greatly. To solve this problem, this article presents a data-driven approach for online path correction of industrial robots. The proposed approach combines a novel link state estimator designed based on a modified flexible dynamics model called flexible-dynamics-based disturbance state observer with a locally weighted projection regression-based JPE prediction scheme to provide the accurate JPE estimation to the robot controller for direct compensation. Simulations and experiments, obtained on a six-axis industrial robot, demonstrate the feasibility and effectiveness of the proposed approach. Experimental results show significant improvement (>80%) in the path accuracy of a standard circular motion corrected using the proposed approach.