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

Authors: Tibor Bosse; Fiemke Both; Rob Duell; Mark Hoogendoorn; Michel C.A. Klein; Rianne Van Lambalgen; Andy Van Der Mee; Rogier Oorburg; Alexei Sharpanskykh; Jan Treur; Michael De Vos

Addresses: Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' Ministry of Defense, c/o Vogelzand 2639, 1788 GS Julianadorp, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' CAMS-Force Vision, MPC 10A, P.O. Box 10.000, 1780 CA Den Helder, The Netherlands ' CAMS-Force Vision, MPC 10A, P.O. Box 10.000, 1780 CA Den Helder, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' Agent Systems Research Group, Vrije Universiteit Amsterdam, De Boelelaan 1081, 1081 HV Amsterdam, The Netherlands ' CAMS-Force Vision, MPC 10A, P.O. Box 10.000, 1780 CA Den Helder, The Netherlands

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.

Keywords: ambient intelligence; personal assistant agents; human functional state; human task performance; multi-agent systems; MAS; agent-based systems; task execution monitoring; dynamic modelling; work pressure; exhaustion.

DOI: 10.1504/IJIIDS.2013.051735

International Journal of Intelligent Information and Database Systems, 2013 Vol.7 No.1, pp.3 - 33

Received: 18 May 2011
Accepted: 25 Nov 2011
Published online: 31 Mar 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article