Some situations (a situation differ from an activity as an activity affects a single user) require the robot to intervene. For instance, the user may have fallen or it may be too cold in the house.  Thus, the robot needs to understand what’s wrong and how to solve it.

To do so, we proposed, along with my colleague Hela Sfar, CAREDAS, an MLN and ontological based anomalous situation detection system.

Publication

• Hela Sfar, Nathan Ramoly, Amel Bouzeghoub, Béatrice Finance, “CAREDAS: Context and Activity Recognition Enabling Detection of Anomalous Situation”, Conference on Artificial Intelligence in Medicine in Europe, 2017