Generating Task-Oriented Interactions of Service Robots

Human-robot interaction (HRI) may play a key role in enhancing a robot's capability in practical service tasks, allowing productive human-robot collaboration. To obtain appropriate human aid for conducting tasks, a robot should be capable of generating meaningful questions regarding the task procedures in real time and applying the results to modify its task plans or behaviors. However, few studies on integrating robot task management and HRI in such high-level task planning exist. In this paper, we propose a new scheme of script-based task planning and HRI that supports the planning and is generated by it. The planning operates on a set of plain and easily writable task procedures, or scripts. The approach produces robust, practical, and easy-to-manipulate robot behavior. Based on the scripts, the system identifies plan ambiguities that require interaction with humans, and resolves them using the human response. The interaction thus generated is highly relevant and task-oriented. The robot learns from the interaction history to improve its subsequent planning in general, or personalize it. Two simulation cases, of a home service and a museum-guide robot, are presented to show how the robots lead appropriate interaction and smoothly adjust their task plans to user commands or responses. Such close integration of HRI and robot task planning is expected to advance the practicality of service robots.