An open agent architecture for assisting elder independence

We are building an agent-oriented system to aid elderly people to live longer in their homes, increasing the duration of their independence from round-the-clock care while maintaining important social connectedness and reducing caregiver burden. The Independent LifeStyle Assistant^ TM (I.L.S.A.) is a multiagent system that incorporates a unified sensing model, probabilistically derived situation awareness, hierarchical task network response planning, real-time action selection control, complex coordination, and machine learning. This paper describes the problem, our reasoning for selecting an agent-based approach, and the architecture of the system.