Probabilistic Logic Reasoning in Multi-agent Based Smart Home Environment

The dynamic nature of the ambient assisted living (AAL) environments coupled with vague inhabitant voice commands may result in ambiguous, incomplete, and inconsistent contextual information about the state of the home and its inhabitants. Ultimately, these lead the AAL system into uncertainty, which is common in smart home environments due to inaccurate sensor readings or due to the existence of unobserved variables for privacy reasons. Aiming at tackling some of these challenges, this paper applies a probabilistic logic based reasoning technique into a multi-agent based smart home architecture. Accordingly, the study shows how the probabilistic reasoning technique enables the agents to reason under uncertainty. Further, it discusses how intelligent agents enhance their decision-making process by exchanging information about missing data or unobservable variables using agent interaction protocols. In addition, the paper presents the proof-of-concept implementation and preliminary experimental evaluation of the proposed smart home system architecture. In general, the study demonstrates that the combination of multi-agent system (MAS) technologies and probabilistic logic programming can help in building a smart home reasoning system, which is capable of performing well under vague inhabitant commands and missing information in partially observable environments.