KQML as an agent communication language
CIKM '94 Proceedings of the third international conference on Information and knowledge management
AgentSpeak(L): BDI agents speak out in a logical computable language
MAAMAW '96 Proceedings of the 7th European workshop on Modelling autonomous agents in a multi-agent world : agents breaking away: agents breaking away
Representing agent interaction protocols in UML
First international workshop, AOSE 2000 on Agent-oriented software engineering
Programming Multi-Agent Systems in AgentSpeak using Jason (Wiley Series in Agent Technology)
Programming Multi-Agent Systems in AgentSpeak using Jason (Wiley Series in Agent Technology)
Developing Multi-Agent Systems with JADE (Wiley Series in Agent Technology)
Developing Multi-Agent Systems with JADE (Wiley Series in Agent Technology)
Multi-Agent Programming: Languages, Tools and Applications
Multi-Agent Programming: Languages, Tools and Applications
Towards Dynamic Agent Interaction Support in Open Multiagent Systems
Proceedings of the 2010 conference on Artificial Intelligence Research and Development: Proceedings of the 13th International Conference of the Catalan Association for Artificial Intelligence
Hi-index | 0.00 |
Agent communication is a core issue when studying all possible ways for agents to organize and collaborate to achieve their goals. We can count on communication standards, as the FIPA Interaction Protocols. On the other hand we can count on high level agent programming languages, like AgentSpeak, which allow us to model and represent the agent and its knowledge and behavior. In this paper we present a proposal to add to Jason (an interpreter of an extended version of AgentSpeak) a new level of abstraction in the task of programming conversations between agents. The agent communication follows the FIPA interaction protocols. A new entity called Communicator Manager acts as an interface between the agent programming language (Jason) and the platform communication facilities (Magentix 2). This approach allows the programmer to focus on programming the agent knowledge and reasoning parts instead of the interaction protocols. An agent can call the communication manager to start a conversation. The communication manager will control the different steps of the conversation and will modify the agent belief base to represent the results of the different steps of the conversation protocol. Therefore, the agents can use this knowledge in its reasoning process. This approach can be easily transfered to others agent programming languages and platforms.