Human directability of agents

Abstract

Many potential applications for agent technology require humans and agents to work together in order to achieve complex tasks effectively. In contrast, much of the work in the agents community to date has focused on technologies for fully autonomous agent systems. This paper presents a framework for the directability of agents, in which a human supervisor can define policies to influence agent activities at execution time. The framework focuses on the concepts of adjustable autonomy for agents (ie, varying the degree to which agents make decisions without human intervention) and strategy preference (ie, recommending how agents should accomplish assigned task). The directability framework has been implemented within a PRS environment, and applied to a multiagent intelligence-gathering domain.