Cyberinfrastructure for Human-Robot Interaction Research

Carnegie Mellon University, Pittsburgh PA

Investigators

Abstract

PUBLIC ABSTRACT Proposal Number: CBET-0742350 Principal Investigator: Hansen, Jeffery Affiliation: Carnegie-Mellon University Proposal Title: Cyberinfrastructure for Human-Robot Interaction Research This project addresses weaknesses in the field of human-robot interaction (HRI) by introducing an integrated cyberinfrastructure (CI) designed to facilitate research collaboration. Existing CI technologies and application domain code are available, but currently lack the tight integration and key features needed by the community. This Engineering Virtual Organization (EVO) project attempts to close the gap between what is currently available and the CI that is needed to enhance collaboration and data sharing to advance HRI research. Early in the development of many research fields, researchers often utilize incomparable metrics due the lack of formal or informal standards. But, such common metrics are desirable as they can lead to common evaluation concepts and enhance clarity in the field's literature. Without pressure or facilitation, common metrics develop slowly, thus impeding research advances. Also, fields that have a moderate cost of entry for data collection tend not to develop collaborative CIs and many researchers are placed at a disadvantage. This project seeks to improve and integrate (i) high dimensional data analysis and visualization tools, (ii) off-the-shelf collaboration and data storage tools, and (iii) an existing simulation tool, USARSim, to establish a cyberinfrastructure for documentation of evaluation metrics, data collection, data sharing, and cross-study comparisons. The project is expected to develop and deploy a prototype CI to instantiate and anchor a collaborative research virtual organization for the field of human-robot interaction. The metrics and CI will be disseminated through an outreach effort involving metric and code dissemination, a data repository, and regular academic dissemination avenues. Learning opportunities will be provided to graduate and undergraduate students and the investigators will promote the use of the CI in related educational activities. This project has the potential to have direct value towards system design, validation, and evaluation of implementations where humans and robots interact. Also, the intent is that the collaboration and data repository components will be reusable by other virtual organizations, thus leveraging the work in this project to aid other researchers, businesses, and fields.