Probabilistic control of human robot interaction: Experiments with a robotic assistant for Nursing Homes
Abstract
This paper describes an implemented robot system designed to assist nurses and elderly persons in institutionalized settings. The robot Pearl has been developed as a multi-functional robotic assistant. Its primary task involves guiding people through a nursing facility, reminding them of upcoming events and the need to take medication, and providing them with information very much like a mobile information kiosk. In the past 24 months, the robot has been deployed more than six times in an elderly care facility in Oakmont, PA. In this paper, we present three software modules relevant to ensure successful robot performance in a dynamic and interactive task domain: an automated reminder system; a people-tracking and detection system; and finally a high-level robot controller which performs planning under uncertainty by incorporating knowledge from low-level modules, and selecting appropriate courses of actions.
BibTeX
@workshop{Pineau-2002-8583,author = {Joelle Pineau and Michael Montemerlo and M. Pollack and Nicholas Roy and Sebastian Thrun},
title = {Probabilistic control of human robot interaction: Experiments with a robotic assistant for Nursing Homes},
booktitle = {Proceedings of 2nd IARP IEEE/RAS Joint Workshop on Technical Challenges for Dependable Robots in Human Environments (DRHE '02)},
year = {2002},
month = {October},
}