Title: Skill-based Shared Control
Abstract: Many industrial tasks require a human to teleoperate a robot as part of a construction or manufacturing project. Performing and maintaining motion patterns – referred to as skills – (e.g. wave, spiral, sweeping motions) is often an integral part of the process requiring expert operators. In this work, we propose a novel skill-based shared control framework for incorporating the notion of skill assistance that assists operators to sustain these motion patterns whilst adhering to environmental constraints. Our method uses streaming joystick data to estimate parameters that describe operator’s intention. We introduce a novel parametrization for state and control that combines skill and underlying trajectory models, leveraging a special type of curve known as Clothoids. This new parameterization allows for efficient computation, enabling the use of a Model Predictive Control (MPC) loop.
Please see our latest publication at R:SS 2021: http://www.roboticsproceedings.org/rss17/p028.pdf