Challenges of Linearization-based Control of Industrial Robots with Cycloidal Drives

Most industrial robots are still controlled with motor-side feedback. To increase the accuracy of industrial robots, controllers with joint-side feedback and explicit consideration of the joint elasticity, such as linearization-based controllers, are needed. The key issue for the performance of linearization-based controllers is a high-fidelity model. Today, the drivetrains installed in the joints of industrial robots of the high payload class usually consist of a permanent magnet synchronous machine and a cycloidal drive. Such robot joints are highly nonlinear due to effects like hysteresis, torque ripples and friction. Therefore, the drivetrain dynamics are crucial for the experimental performance of linearization-based controllers for industrial robots. This paper identifies the challenges in linearization-based control of industrial robots with such a drivetrain configuration based on experimental results on a KUKA KR-210-2. Using an exemplary approach, it is shown that a linearization-based controller does not provide the theoretical performance due to needed model simplifications. For this purpose, simulation and experimental results are compared to a linear robot controller with motor-side feedback. These results indicate why such controllers are still a valid alternative for the practical application of similar industrial robots.