An ambient agent system assisting humans in complex tasks by analysis of a human's state and performance

Abstract

Human task performance varies depending on the task, environment, and states of the human over time. To ensure high effectiveness and efficiency in the execution of complex tasks, adaptive automated assistance of the human may be required. In this paper, a generic design for a multi-agent system architecture is presented and a personal assistant agent is described that makes use of the proposed architecture. The agent constantly monitors the task execution and well-being of the human via non-intrusive sensors, and intervenes when a problem is detected. A human is given a complex task, while the future performance is predicted using observations and a dynamical model for the human's work pressure and exhaustion. If the predicted exhaustion becomes too high, the ambient agent can assist the human in a number of ways. Experiments with humans show that the support system increases performance with around 13%, and that it enhances the feeling of control of the situation.