A conversational agent for creating flexible daily automation

The spread of sensors and intelligent devices of the Internet of things and their integration in daily environments are changing the way we interact with some of the most common objects in everyday life. Therefore, there is an evident need to provide non-expert users with the ability to customize in a simple but effective way the behaviour of these devices based on their preferences and habits. This paper presents RuleBot, a conversational agent that uses machine learning and natural language processing techniques to allow end users to create automation according to a flexible implementation of the trigger-action paradigm, and thereby customize the behaviour of devices and sensors using natural language. In particular, the paper describes the design and implementation ofRuleBot, and reports on a user test and lessons learnt