Perception and Action Augmentation for Teleoperation Assistance in Freeform Tele-manipulation

Abstract

Teleoperation enables controlling complex robot systems remotely, providing the ability to impart human expertise from a distance. However, these interfaces can be complicated to use as it is difficult to contextualize information about robot motion in the workspace from the limited camera feedback. Thus, it is required to study the best manner in which assistance can be provided to the operator that reduces interface complexity and effort required for teleoperation. Some techniques that provide assistance to the operator while freeform teleoperating include: 1) perception augmentation, like augmented reality visual cues and additional camera angles, increasing the information available to the operator; 2) action augmentation, like assistive autonomy and control augmentation, optimized to reduce the effort required by the operator while teleoperating. In this paper we investigate: 1) which aspects of dexterous tele-manipulation require assistance; 2) the impact of perception and action augmentation in improving teleoperation performance; 3) what factors impact the usage of assistance and how to tailor these interfaces based on the operators’ needs and characteristics. The findings from this user study and resulting post-study surveys will help identify task based and user preferred perception and augmentation features for teleoperation assistance.