A friendly reminder
Ann Arbor, MI, March 15, 2004 -- Professor Martha Pollack, University of Michigan Department of Electrical Engineering and Computer Science, and University of Pittsburgh and Carnegie Mellon collaborators, will demonstrate "Pearl," an artificial-intelligence robot designed to assist the elderly, and a handheld reminder device, during the Future of Aging Services Conference on Tuesday, March 16, 2004, 3:30 p.m., at the Dirksen Senate Office Building in Washington, D.C.
As baby boomers become senior citizens and health care costs continue to escalate, assistive technologies that enable greater self regulation are likely to become more prevalent.
Pearl, is capable of various caregiver tasks, such as escorting an elderly person to an appointment or reminding her of her daily schedule. Pearl is intended to assist caregivers not replace them. By taking on more mundane responsibilities of the caregiver and health professionals, those individuals have more time to focus on the tasks that require their high-level of training.
Visitors to the demo will be able to interact with Pearl to see how users will benefit.
Said Pollack about the demonstration, "Pearl will 'observe' where the participant goes--either to a simulated kitchen on one side of the booth or a simulated bathroom (for taking medicine) on the other--and provide reminders accordingly."
Pollack's recent research has focused on exploring non-robotic methods of deployment for places, people and situations in which a robot is not needed. For example, she is adapting the technology used in Pearl to provide timely reminders to Traumatic Brain Injury patients.
A handheld device with similar artificial-intelligence software as in Pearl also will be available for interactive demonstration. "The reminders will be posted both on the handheld device that the participant is using, as well as on the body of the robot for other participants to observe," added Pollack. The software can help users remember when to take medicines or eat meals. But unlike simpler reminder systems, it can also monitor the execution of those activities, detect discrepancies between what a person is expected to do and what he or she actually is doing and reason about whether and when to issue reminders--thus avoiding the annoyance of unnecessary messages.
Pollack is a Fellow of the American Association for Artificial Intelligence and a recipient of the Computers and Thought Award (1991), an NSF Young Investigator's Award (1992) and the University of Pittsburgh Chancellor's Distinguished Research Award (2000). She is currently serving as editor-in-chief of the Journal of Artificial Intelligence Research.
Source: Eurekalert & othersLast reviewed: By John M. Grohol, Psy.D. on 21 Feb 2009
Published on PsychCentral.com. All rights reserved.