Towards a real-time BDI model for ROS 2

In the race for automation, electronic devices are required to become more and more intelligent in order to make the correct choices in unforeseen situations without any need of human intervention. AI proposes basically two different approaches: machine learning algorithms and multi-agent systems. While the former perform very well when dealing with single, independent, computing units, multi-agent systems are more suitable in case of different components interacting with one another. In this paper, we propose a real-time multi-agent approach to improve practical reasoning, integrating the Belief-Desire-Intention model into one of the most popular robotics framework, ROS 2.