The Tele-Robotic Intelligent Nursing Assistant (TRINA)

Jane Li, Peter Moran, Carrina Dong, Ryan Shaw, Kris Hauser


During outbreaks of contagious diseases, healthcare workers are at high risk for infection due to routine interaction with patients, handling of contaminated materials, and challenges associated with safely removing protective gear. This project is developing the Tele-Robotic Intelligent Nursing Assistant (TRINA), a remote-controlled robot to address these challenges. Such robots could perform common nursing duties inside hazardous clinical areas, which could reduce infection risk to healthcare workers by minimizing exposure to contagions and other biohazards.

TRINA consists of a mobile manipulator robot, a human operator's console, and software for connecting the operator's input to the robot. Ideally, the robot should act as a "surrogate body" so that the operator can perform any task that he/she could normally perform. However, robot actuation and sensing hardware is far from the capabilities of the human body. There are a number of ongoing research challenges including hardware that provides human-level strength, dexterity, perceptual sensitivity, and situational awareness. Moreover, TRINA has 28 independently controllable degrees-of-freedom, and coordinating these movements can be quite challenging.

Recent tests show the robot successfully completing approximately 60% of nursing tasks at an average of 20x slower than human performance. Enhancing the capability of the robot and its intuitiveness for the operator is a major effort and poses engineering, scientific and clinical application challenges.

The group is investigating several aspects of the tele-robotic nursing problem, including intuitive input devices, improved contextual awareness, and operator assistance algorithms that automate or partially-automate tedious and error-prone tasks. External collaborators are also studying the use of mobile sensors for providing rich information to the nurse, methods for enhancing the robot's manipulation capabilities, and designing disposable protective coverings.

Video showing the capabilities of TRINA v1.0, as tested in a nursing simulation lab at Duke University School of Nursing.
Image of TRINA v1.0
TRINA v1.0 as shown in the nursing simulation lab at Duke University School of Nursing
Image of TRINA v1.0 operator's console
TRINA v1.0 operator's console, showing dual haptic input devices, game pad, several camera streams, and 3D visualization of robot.
Several tasks on which TRINA has been evaluated
TRINA has been evaluated on 26 common nursing tasks and is able to complete many of them. We show a human nurse in the frames corresponding to tasks that TRINA is not currently able to complete.