Human-Augmented Robotic Intelligence (HARI) for Human-Robot Interaction

摘要

This paper provides a system design framework for a human-robot interaction system. The design introduces a human-augmented robotic intelligence embedded in a human-robot interaction system. The motivations behind the system design are spoken dialogue systems, Wizard-of-OZ framework, and existing HRI designs for socially intelligent robots. In this work, we explain how artificial intelligence of human-robot interaction system is enhanced by human intelligence through collaboration. The collaborative artificial intelligence enables the system to learn from demonstration. The main objective and the gradual progression from this paper is to build an iterative interactive system that is capable of achieving human-robot interaction similar to the nuances of human-human interaction.