Preliminary Study on Slack-Free Model Predictive Control of Twisted String-Based Antagonistic Joints

Abstract

In this work, we propose a model predictive controller (MPC) for simultaneous position and tension tracking in twisted string actuator-based antagonistic joints. The proposed controller takes into account unidirectional nature of the cables and minimize trajectory tracking error as well as control effort. The approach has been evaluated numerically in a series of simulations that demonstrated its feasibility and highlighted its advantage over the unconstrained controller, with position tracking accuracy improved by a factor of 10. The proposed MPC can be generalized and serve as the starting point for antagonistic control in multiple-degree-of-freedom systems based on twisted string actuators.