Sign In

Communications of the ACM

ACM TechNews

Role For Robots: Helping Elderly at Home

View as: Print Mobile App Share:
UIC engineers Milos Zefran, Jezekiel Ben-Arie and Barbara Di Eugenio

University of Illinois at Chicago Associate Professor Milos Zefran, Professor Jezekiel Ben-Arie and Associate Professor Barbara Di Eugenio are working on software that would let the elderly communicate with robotic caregivers.

Credit: Roberta Dupuis-Devlin / UIC

Three University of Illinois at Chicago (UIC) engineers and a Rush University nursing specialist have been awarded a three-year, $989,000 National Science Foundation grant to develop robots that can help care for the elderly and people with limited mobility. "We want to help elderly people communicate with robots, to tell them what they need, and to perform physical activities," says UIC professor Milos Zefran, the project's lead investigator.

The researchers plan to create software that will enable the elderly to communicate with robots capable of responding to a variety of verbal language and non-verbal gestures and touch commands. Zefran says helping the elderly stay in their own homes will improve their health outlook and relieve the burden on family members and health care providers. The researchers are developing communication interface software that will feature a novel adaptive and reliable recognition methodology known as Recognition by Indexing and Sequencing (RISq). RISq will enable robots to comprehend speech even if it is altered by impairments.

Techniques from natural language processing and haptics will allow the robot to understand and respond to various forms of human touch, and help it know how to respond to the user safely when performing chores such as cooking or making a bed. "We'll identify what kind of language, physical interactions, and non-verbal interactions are used," Zefran says. "Then we'll develop a mathematical framework to model this interaction so it can be treated by the robot as a single way of communicating."

From UIC News
View Full Article


Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account