Abstract:
The research and development of socially interactive robots is a complex challenge due to the diverse range of capabilities required for effective human-robot interactions (HRI). While state-of-the-art methods and solutions exist for individual capabilities such as perception, dialogue, and control, integrating these into a cohesive and seamless interaction remains an open challenge.
This paper introduces HARMONI, a multi-modal, open-source tool designed for rapid social HRI development and deployment. HARMONI is built around a ROS package that facilitates interaction development, including decision management and node orchestration. It systematically integrates various functionalities necessary for meaningful social HRI, such as external cloud services, AI models, and modules for sensing, planning, and acting on a variety of platforms.
HARMONI was implemented on the QTrobot platform, and usability tests were conducted to assess the ease and speed of development and deployment. This paper details the architecture and design of HARMONI and reports the results of a pilot study involving novice users.
Reference:
Spitale, Micol, et al. “Composing harmoni: An open-source tool for human and robot modular open interaction.” 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021.