Learning Temporal Plans from Observation of Human Collaborative Behavior

Abstract

The objective of our research effort is to enable robots to engage in complex collaborative tasks with human-robot interaction. To function as a reliable assistant or teammate, the robot must be able to adapt to the ac-tions of its human partner and respond to temporal vari-ations in its own and its partner’s actions. Dynamic plan execution algorithms provide a fast and robust method of executing collaborative multi-robot tasks in the pres-ence of temporal uncertainty. However, current state of the art algorithms, rely on hand-crafted plans, pro-viding no means of generating plans for new tasks. In this paper, we outline our approach for learning a model of collaborative robot behavior by observing human-human interaction of the target task. Through statistical analysis of the recorded human behavior we extract pat-terns of common behavior, and use the resulting model to learn a temporal plan. The result is a learning frame-work that automatically produces temporal plans for use with dynamic planning that model human collaborative behavior and produce human-like behavior in the robot. In this paper, we present our current progress in the de-velopment of this learning framework.