ANNOUNCEMENT

NOBEL PRIZE 2026

This year's laureates, their fields, and the discoveries that earned them the prize.Live nowSee the winners
Moonbase
← Back to Awards
NSFI-Corps

I-Corps: Translation Potential of Assistive Robots for Healthcare Facilities

Active
Institution
University of Maryland, College Park, MD
Principal investigator
Pratap Tokekar
Funding
$50K
Duration
2025–2027
Open portfolio

Moonbase score

Still being scored

Abstract

The broader impact of this I-Corps project is based on the development of a robotic-assistive technology designed to ease the workload of healthcare staff by automating routine and complex tasks in healthcare settings. As the world's elderly population grows, increasing long-term care needs and rising patient-to-nurse ratios are putting a strain on healthcare systems. These pressures can lead to nurse burnout, diminished quality of care, and a higher rate of patient readmissions within 30 days. The technology aims to alleviate these pressures by performing both direct patient-facing tasks such as assistive feeding and indirect tasks like the delivery of medicines and room turnover. The solution promises to return valuable time to healthcare staff, enabling them to manage more patients efficiently and improve the overall quality of care. This innovation holds commercial potential in a healthcare industry increasingly reliant on technological solutions to meet growing demands, thereby enhancing the sustainability of healthcare systems and improving patient outcomes. This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. The solution is based on the development of advanced artificial intelligence technologies integrated into a mobile, robotic-assistive technology platform capable of adaptive, responsive interactions within varied healthcare environments. The intellectual merit of this project lies in its novel application of Learning from Demonstration (LfD) algorithms, which are tailored for dexterous, long-horizon manipulation tasks requiring minimal human intervention. These algorithms enable the robotic-assistive technology to quickly learn and adapt to new tasks from limited demonstrations. Additionally, the integration of Large Language Models facilitates natural interactions between healthcare workers and the robotic-assistive technology, ensuring ease of use and enhancing operational effectiveness. The initial focus has been on assistive feeding, with demonstrated ability to handle a range of food consistencies to serve a variety of patient feeding needs. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

LOADING MOONBASE SCORE

I-CorpsDirectorate for Technology, Innovation, and PartnershipsHUMAN-ROBOT INTERACTIONassistivetaskshealthcarehealthcare systemstranslation potentialquality carefeedingpressures

Questions for University of Maryland, College Park

Answered by the team behind this research.

Same researchers, same institution, same topic, scored first.