NRI: FND: Human-Robot Collaboration with Distributed and Embodied Intelligence

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

This award supports research on the issue of intelligence re-embodiment in robots. The fundamental question to be addressed is whether robots should be designed so that different synthetic intelligences can take over. A smart phone can be repurposed to serve different users by swapping chips. Should robots with much higher functionality be designed so that they operate in a suitably similar way? The goal of this project is to answer this question along with a number of related questions including the following. Should robots be designed so different intelligences can take over? Where does the locus of intelligence sit? How does the user understand where it is and who or what is in control? How does re-embodiment impact issues of privacy? To answer these questions, this research effort will adopt a mixed-methods approach including surveys, fieldwork, simulations, and on-site testing of a robot operating system module. The findings of this work are expected to have direct value to robot developers and other researchers. Other impacts include interdisciplinary training of PhD students, and creating research opportunities for undergraduates. Team members plan to use the results of this research to enrich courses on human-robot interactions, and in outreach activities to engage non-academic audiences. This research project uses a variety of methods to study the issue of intelligence re-embodiment in robots. Team members will conduct online surveys to systematically assess factors related to re-embodiment. They will engage in fieldwork to investigate current practices of people working and living in environments with several intelligent systems. These findings will in turn be used to inform a user enactment study that will create simulations of real-world contexts and test participants' reactions to different robot behaviors. Team members will also extract and evaluate a set of generalized interaction principles using a second online study. In addition, they will develop a robot operating system (ROS) module to enable re-embodiment of robots by a cloud-based intelligence; the module will be used to assess reactions of business owners and other stakeholders interacting with these systems. The results of these research components will advance knowledge on how people understand re-embodiment. They will serve to map out a set of design recommendations, design features, and the corresponding interaction patterns that do not yet exist around robot behavior in different contexts. They will also lead to the production of software components that support re-embodiment by remote intelligences. More generally, they will help achieve a vision of fully collaborative, ubiquitous, interconnected co-robot systems.