Improving implicit communication in mixed human-robot teams with social force detection

Abstract

One of the hallmarks of development is the transition of an agent from novice learner to able partner to experienced instructor. While most machine learning approaches focus on the first transition, we are interested in building an effective learning and development system that allows for the complete range of transitions to occur. In this paper, we present a mechanism enabling such transitions within the context of collaborative social tasks. We present a cooperative robot system capable of learning a hierarchical task execution from an experienced human user, collaborating safely with a knowledgeable human peer, and instructing a novice user based on the explicit inclusion of a feature within the planning and skill execution subsystems we've termed social force. We conclude with an evaluation of this feature's flexibility within a collaborative construction task, changing a robot's behaviors between student, peer, and instructor through simple manipulations of this feature's treatment within the planning subsystem.