Flexible problem-solving roles for autonomous agents

Agent-based technologies can be applied to many aspects of manufacturing. T he need for responsive, flexible agents is pervasive in manufacturing envir onments due to the complex, dynamic nature of manufacturing problems. One c ritical aspect of agent flexibility is the ability to adapt decision-making interactions to various situations during system operation. This issue is addressed by research on Sensible Agents, capable of Dynamic Adaptive Auton omy. In Sensible Agent based systems, agent problem-solving roles describe the decision-making interaction styles adopted by agents. An agent's level of autonomy arises from the problem-solving role it has adopted. These leve ls of autonomy are defined along a spectrum ranging from command-driven, to consensus, to locally autonomous/master. Dynamic Adaptive Autonomy allows Sensible Agents to change problem-solving roles during system operation to meet the needs of a particular problem-solving situation. The foundation of Dynamic Adaptive Autonomy is the specification of these problem-solving ro les. This article focuses primarily on defining four representational const ructs (planning-responsibility authority-over, commitment, and independence ) that specify agent problem-solving roles.