AAAI Fall Symposium on

Caring Machines: AI in Eldercare

November 3-6 2005, Washington DC

 

Motivation

Much has been published on the looming demographic crisis in the U.S., with the number of older adults skyrocketing while the number of human caretakers (both informal and professional) dwindle. Combined with a strong desire by aging individuals to remain independent in their homes as long as possible, these conditions motivate technological solutions to human care-giving.

While this situation has inspired many research projects in AI, HCI and robotics over the last decade, most of these component solutions have addressed only very narrow aspects of the total care-giving needs of an older individual living alone or with an older spouse. Social psychologists have identified a number of types of social support that people provide for each other, and this taxonomy may be useful in grasping the entire range of needs that an individual may have. Instrumental support provides material aid for individuals, such as help with shopping or household chores, and may require robotic assistance to effect. Informational and cognitive support provides advice, suggestions, and information that a person can use to address problems, and may require proactive reminding and intervention for individuals with cognitive impairments, common in the elderly. Emotional and appraisal support involve the provision of empathy to both help individuals manage their adverse emotional states and provide feedback that is useful for self-evaluation, and help address loneliness and depression. Social network support helps an individual maintain an active social network, and can be provided by systems that introduce elders to others with similar interests or proactively take steps to maintain existing friendships. Altogether these systems provide autonomy support by helping individuals stay independent as long as possible.

The goal of this symposium is to bring together researchers in AI—including computational linguistics, planning, user modeling, social agents, robotics, intelligent sensing and machine learning—with researchers in gerontology, health communication, public health, geriatrics and other medical sciences. The overall focus will be the design, implementation and evaluation of integrated intelligent support systems for older adults, and cover topics such as:
• Frameworks for integrating assistive and supportive technologies for older adults.
• Approaches to maintaining trust and engagement between support systems and elders over years of use, while avoiding user complacency and over-reliance.
• User modeling and system adaptation over time.
• Recognition, display or management of affect to support system goals.
• Uses and comparisons of different HCI modalities for older adults, including text, audio, embodied agents or robots, and other human factors issues.
• Ethical and privacy issues.
• Approaches to evaluation of these systems and results from studies and clinical trials.

The format will include keynote talks and individual paper presentations, and encourage discussion and group participation through panel discussions and challenge problems covering both implemented systems and work in progress.

Keynote Talks

Jeffrey Elias, Ph.D., of the National Institute on Aging's Behavioral and Social Research Program will talk about needs in eldercare that AI technology can address.

AAAI Fall Symposium Series

The AAAI 2005 Fall Symposium Series will be held in November 4-6, 2005. The Symposia will be preceded by a one-day AI funding seminar, which will be open to all registered attendees of the fall symposium series. Information on the Series and the other concurrent Symposia are available on the AAAI website.

Important Dates

Deadline for all submissions
EXTENDED!

June 1, 2005
Notification of acceptance
July 1, 2005
Deadline for final versions of abstracts and papers
September 13, 2005
AI Funding Workshop
November 3, 2005
Symposium
November 4-6, 2005

Contact Information

Send your submission or any questions to bickmore@bu.edu.

Organizing Committee

Timothy Bickmore (chair), Boston University School of Medicine
Karen Haigh, Honeywell Laboratories
Stephen Intille, House_n, Massachusetts Institute of Technology
Henry Kautz, Dept. of Computer Science & Engineering, University of Washington
Rosalind Picard, MIT Media Laboratory
Richard Simpson, School of Health and Rehabilitation Sciences, University of Pittsburgh