Future Everyday Interaction with the Autonomous Internet of Things (A-IoT)

A-IoT is an EPSRC funded 3-year project investigating interaction mechanisms for an autonomous Internet of Things (IoT).

An Autonomous IoT actively manages data and decisions on behalf of users, drawing upon machine learning techniques and optimization algorithms. However, it is critical to still allow users to make informed choices about their general needs and comfort. Nascent instantiations of the A-IoT range from smart thermostats that learn to autonomously control central heating systems based on the presence of users and their routine, to washing machines that order detergent for delivery when it runs out. But how should interactions with autonomous systems be engineered to support users' daily activities? To what extent may users be willing to delegate agency to A-IoT systems in everyday contexts? These are some of the key questions our project aims to address. 

The overall objective is to establish the scientific underpinnings of user interactions with Autonomous IoT (A-IoT) systems, in a domestic everyday context, with the aim of explicating the following research questions: to what extent may users be willing to delegate agency to A-IoT systems; how should interactions with A-IoT systems be engineered to support rather than hinder users' daily activities; how should intelligent agents be designed to manage such A-IoT systems? 

In particular, the project objectives are to: 

1. Understand, through design ethnography and envisionment workshops, how people manage the contingencies of everyday life, particularly those that already involve agency delegation to other people, and how they orient themselves to future technologies that may support agency delegation; resulting in design requirements for accountable A-IoT systems. 
2. Design and prototype new user interaction mechanisms for the A-IoT, so that they can be integrated in everyday routines, leading to a principled understanding of UX design for A-IoT systems. 
3. Evaluate prototypes of A-IoT systems in the wild, through field trials developed around prototypes of future scenarios, resulting in interaction design principles shaping the delegation of autonomy to IoT systems, and in understanding of users' perception and expectations of the A-IoT. 
4. Develop algorithms that take into account human preferences in interactions with (multiple) autonomous agents in the context of domestic practices and supply networks, leading to advanced machine learning models of human behaviour.