GOOSE: goal oriented orchestration for smart environments

摘要

Smart environment scenarios are characterised by the presence of users, with different needs and preferences, and everyday life objects exploited to meet the expectations of users themselves. Connecting objects to the internet and making them accessible from remote is not sufficient to make an environment 'smart' since such ecosystems should also be able to enable context-sensitive actions along with a management of the interaction between objects and users. In this work, we propose GOOSE, a platform which aimed at interpreting users goals expressed in natural language in order to generate, select, and safely enforce a set of plans to be executed to fulfill target goals. After highlighting the main challenges affecting typical machine-to-machine (M2M) communication scenarios, we show how the use of a semantic reasoner can be used to allow the composition of plans consisting of sequences of services to be called on the smart environment objects. Finally, we address the issue of secure communications between platform and objects, and the management of potentially inconsistent goals.