Task Models for Inferring Team Intentions

Emerging smart environment infrastructures provide users with a large number of interconnected assisting appliances. Inferring the intention of a team within such an area becomes a central challenge, especially if multiple user are observed by noisy heterogenous sensors. We propose a team task model based on hierarchical Dynamic Bayesian Network (DBN) for inferring the current task and activity of a team of users online. Given (noisy and intermittent) sensor readings of the team members’ positions in a meeting room, we are interested in inferring the team’s current objective.