Towards Automated Development of Multi-Agent Systems Using RADE

To facilitate the development of multi-agent systems and improve the reusability, robustness and feasibility of these systems, we proposed a role-based agent development framework (RADE). In this paper, we present more details on the design of agents and motivations within such framework. We introduce a practical approach to modeling agent’s motivation and specifying agent’s goals, where a role-mapping mechanism is developed based on this design. We also introduce the RTÆMS language based on the extension of TÆMS to model the plan tree for each goal. This representation is used to support the development of general planning/scheduling and collaboration/cooperation mechanisms.