Abstract. Agent-based applications have the potential to assist humans in their lifestyle change, for instance eliminating addictive behaviours or adopting new healthy behaviours. In order to provide adequate support, agents should take into consideration the main mechanisms underlying behaviour formation and change. Within this process habits play a crucial role: automatic behaviours that are developed unconsciously and may persist without the presence of any goals. Inspired by elements from neurological literature, a computational model of habit formation and change was developed as a basis for support agents able to assist humans in lifestyle and behaviour change. Simulations are presented showing that the model exhibits realistic human-like behaviour.

Abstract. Human task performance may vary depending on the characteristics of the human, the task and the environment over time. To ensure high effectiveness and efficiency of the execution of tasks, automated personal assistance may be provided to task performers. A personal assistant agent may constantly monitor the human’s state and task execution, analyse the state of the human and task, and intervene when a problem is detected. This paper proposes a generic design for a Personal Assistant agent model which can be deployed in a variety of domains. Application of the Personal Assistant model is illustrated by a case study from the naval domain. 1

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 presented 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 show that the support system increases performance with around 13%, and that it enhances the feeling of control of the situation.