Kudos to Ryan Shaw, associate professor, and his team for the submission of his subcontract proposal to the University of Illinois Urbana-Champaign on the ongoing Shaw-Hauser TRINA project entitled: ”Customizing Semi-Autonomous Nursing Robots using Human Expertise." This proposal requests funds for an 18 month period with a start date of March 1, 2020.

In prior work, the PIs developed a robot, named TRINA (Tele-Robotic Intelligent Nursing Assistant) that functions in a quarantine area or isolation room alongside an infectious patient while a human nurse safely controls it from outside. In proof-of-concept testing, TRINA has shown promise in nurse-patient communication, mobility, food and medicine delivery, cleaning, biological specimen collection, and sensing of patient vital signs. But piloting the robot has a steep learning curve. The goal of this project is to achieve push-button autonomy in which a nurse can command routine medium- to high-level tasks, such as measuring vital signs, deactivating false alarms, bodily fluid cleanup, or specimen transport with a single button press, while also being able to assume low-level control when necessary.

This proposal continues a productive interdisciplinary collaboration with the Duke University School of Nursing (DUSON) on the TRINA project. Research will be conducted in three thrust areas: 1) smart human operator interfaces for supervised autonomy that learn mappings between multimodal sensor input streams to provide simple, interpretable task options and status feedback; 2) hierarchical task learning algorithms for helping human experts train novel composite tasks; and 3) real world evaluation of human-robot system speed, reliability, operator workload, and operator learning curve on simulated clinical tasks in nurse training environments.