Agent-oriented smart objects development

The Internet of Things (IoT) term is recently emerging to envision a global infrastructure of networked physical objects. As different definitions of IoT do currently exist, we specifically refer to IoT as a loosely coupled, decentralized system of smart objects (SOs), which are autonomous physical/digital objects augmented with sensing/actuating, processing, and networking capabilities. SOs are able to sense, log, and interpret information generated within themselves and around the neighboring external world where they are situated, act on their own, cooperate with each other, and exchange information with humans. The development of a IoT based on SOs raises many issues involving hw/sw system architecture and application development methodology. A few approaches (e.g. FedNet, UbiComp, Smart Products) have been to date proposed to support the vision of an SO-based IoT infrastructure. In this paper we first discuss the suitability of the agent paradigm and technology to effectively support the development of such an IoT infrastructure and then propose a multi-layered agent-based architecture for the development of proactive, cooperating and context-aware smart objects. Our architecture takes into account a wide variety of smart objects, from reactive to proactive, from small to very large, from stand-alone to social. The implementation phase can be based on multiple agent languages and platforms (JADE, JADEX, LEAP, MAPS) atop heterogeneous computing systems (computers, smartphones, and sensor nodes).