An Intent-based Task-aware Shared Control Framework for Intuitive Object Telemanipulation

Shared control in teleoperation for providing robot assistance to accomplish object manipulation is a new challenging problem. This has unique challenges, on top of teleoperation challenges in general, due to difficulties of physical discrepancy between human hands and robot hands as well as the fine motion constraints to constitute task success. In this work we are interested in the scientific underpinnings of robot assistance for telemanipulation by defining an arbitration strategy for a physically discrepant robot hand structure which flexibly reproduce actions that accommodate the operator's motion inputs as well as autonomously regulate the actions to compensate task constraints that facilitate subsequent manipulation. The overall objective is to present a control strategy where the focus is on generating poses which are better suited for human perception of successful teleoperated object manipulation and feeling of being in control of the robot, rather than developing objective stable grasp configurations for task success. Identifying the commonalities between human and robot feature sets enable the accommodation for the arbitration framework to indicate and appear to intuitively follow the user. Additionally, it is imperative to understand how users perceive good arbitration in object telemanipulation. We have also conducted a user study to analyze the effect of factors including task predictability, perceived following, and user preference.