Carlos Eduardo. Pantoja1,2, Vinicius Souza de Jesus1, Nilson Mori Lazarin1,2, and José Viterbo1
1Institute of Computing - Fluminense Federal University (UFF), Niterói - RJ, Brazil
2Federal Center for Technological Education Celso Suckow da Fonseca (Cefet/RJ), Rio de Janeiro - RJ, Brazil
carlos.pantoja@cefet-rj.br, vsjesus@id.uff.br, nilson.lazarin@cefet-rj.br, and viterbo@ic.uff.br
Embedded artificial intelligence in IoT devices is presented as an option to reduce connectivity dependence, allowing decision-making directly at the edge computing layer. The Multi-agent Systems (MAS) embedded into IoT devices enables, in addition to the ability to perceive and act in the environment, new characteristics like pro-activity, deliberation, and collaboration capabilities to these devices. A few new frameworks and extensions enable the construction of agent-based IoT devices. However, no framework allows constructing them with hardware control, adaptability, and fault tolerance, besides agents' communicability and mobility. This work presents an extension of the Jason framework for developing IoT devices. A case study of an IoT solution with a smart home, a monitoring center, and an autonomous vehicle is presented to demonstrate the framework's applicability.
We consider a scenario that integrates a smart home, a central control, and an unmanned vehicle, all controlled by Multi-agent Systems. The MAS running in the central control has a Communicator to forward service calls and two Jason agents for decision-making in case of calls. The vehicle has an Argo agent for driving and a Communicator agent for receiving agents to use the vehicle. The MAS running in the house has a Communicator agent responsible for interacting with the central and an Argo agent controlling the sensors and actuators.
The dependencies to reproduce the case study are Java>=8 and Debian (or derivate).
wget -c https://bracis2023.chon.group/Reproducibility.tar.gz tar -zxvf Reproducibility.tar.gz cd Reproducibility/StudyCase/ ./executeScenario.sh |
Video Demonstration → https://youtu.be/RzEtJ8eBYaI
Framework → https://bracis2023.chon.group/jasonEmbedded.jar
Source code → https://bracis2023.chon.group/jasonEmbedded-source.tar.gz