A multi-agent framework that facilitates decoupled agent functioning

Abstract

Society is becoming more aware of the impact of Artificial Intelligence and its relevance in everyday scenarios, from search engines to mobile phone assistants. Intelligent agents focus on agents as entities that can act on environments. These agents demonstrate qualities such as autonomy, situational awareness, embodiment, and flexibility. A challenge faced is creating a mechanism for artificial intelligent agents to cross-communicate in a world where technology is disparate and always changing. This constant change leads to numerous problems, from changing protocols and deprecated communication endpoints to information or functionality loss. The research investigates existing frameworks leveraged in agent programming and the standards in place such as the Foundation for Intelligent Physical Agents standard, and the Mobile Agent System Interoperability Facility. The standards are detailed and expanded to leverage modern technologies. The investigation provides the Decoupled Environment Agent Model that abstracts agent functioning from environment execution that is based on the existing standards. In this model, components function as if the they are agents. The model focuses on common interfaces and mechanisms for communication and discovery. The Decoupled Environment Agent System is an implementation of the model that is used to test and provide a mechanism where the various components of the model behave in a consistent simple manner. The information gathered in the research, the model and the results collected identify whether an agent can effectively be loosely coupled from the environment. The implementation shows that it is possible to construct an agent that is decoupled from the functioning environment.