Slim Essid
Papers
2
Total Citations
125
H-Index
2
About
Slim Essid is a leading researcher in human-robot interaction (HRI), with a particular focus on understanding and predicting user engagement in spontaneous, naturalistic settings. His major contributions center on the development of computational models that can detect and even forecast engagement breakdowns—moments when a user disengages or abandons an interaction before its intended conclusion. Essid’s work is foundational to building more socially aware and responsive robots. He created the UE-HRI dataset (95 citations), a widely used resource comprising 54 spontaneous interactions between humans and the robot Pepper, which has become a benchmark for studying engagement in unscripted scenarios. Building on this, his 2019 paper on early detection of engagement breakdown (30 citations) introduced a supervised classification system that predicts user disengagement, enabling proactive robot responses. This work is critical for advancing robots that can sustain long-term, meaningful interactions. Essid’s research bridges machine learning, social signal processing, and robotics, offering practical tools for designing robots that understand and adapt to human social cues.
Research Focus
Key Achievements
Top Papers
- 1
- 2