Human-Robot Interaction via a Joint-Initiative Supervised Autonomy (JISA) Framework

Abstract

In this paper, we propose and validate a Joint-Initiative Supervised Autonomy (JISA) framework for Human-Robot Interaction (HRI). Through JISA, a robot maintains a measure of its self-confidence (SC) while performing a task, and only prompts the human supervisor for help when its SC drops. At the same time, a human supervisor can intervene in the tasks being performed, based on his/her Situation Awareness (SA). This paper outlines JISA, presents a guideline for defining the tasks to be supervised, and defines the robot SC and human SA attributes. The paper presents a generic block-diagram to apply JISA in various autonomous systems, and provides detailed proof-of-concept (POC) examples for applying JISA. The selected POCs aim to prove the applicability and utility of JISA through two different applications: grid-based collaborative simultaneous localization and mapping (SLAM) and automated jigsaw puzzle reconstruction. In both POCs, the robot SC and human SA attributes are defined in accordance with JISA’s guidelines. In addition, augmented reality (AR) and two-dimensional graphical user interfaces (GUI) are custom-designed to enhance the human SA and allow intuitive interaction between the human and the agent. The superiority of the JISA framework over existing full-autonomy approaches is demonstrated in experiments. In SLAM, JISA eliminates the need for post processing of SLAM maps and reduces the required mapping time by \({\sim }50\%\). In automated puzzle reconstruction, JISA outperforms two solutions: full autonomy and on-demand human intervention prompted by the agent, reaching a reconstruction accuracy of 97.2%.