ROS for Human-Robot Interaction
This work aims to standardize human representation and social perception components for the HRI community, facilitating development and interoperability of HRI software tools.
This paper addresses the challenge of integrating complex social signal processing into robotic systems for human-robot interaction (HRI). It introduces a set of conventions and standard interfaces for HRI scenarios, designed for use with the Robot Operating System (ROS), to promote interoperability and re-usability of HRI-related software tools.
Integrating real-time, complex social signal processing into robotic systems -- especially in real-world, multi-party interaction situations -- is a challenge faced by many in the Human-Robot Interaction (HRI) community. The difficulty is compounded by the lack of any standard model for human representation that would facilitate the development and interoperability of social perception components and pipelines. We introduce in this paper a set of conventions and standard interfaces for HRI scenarios, designed to be used with the Robot Operating System (ROS). It directly aims at promoting interoperability and re-usability of core functionality between the many HRI-related software tools, from skeleton tracking, to face recognition, to natural language processing. Importantly, these interfaces are designed to be relevant to a broad range of HRI applications, from high-level crowd simulation, to group-level social interaction modelling, to detailed modelling of human kinematics. We demonstrate these interface by providing a reference pipeline implementation, packaged to be easily downloaded and evaluated by the community.