Stefanos Doltsinis

Information Technologies Institute, Centre for Research and Technology Hellas

Papers

Total Citations

H-Index

About

Stefanos Doltsinis is a leading researcher in intelligent robotic assembly and human-robot interaction, with a focus on manufacturing automation. His primary research areas include machine learning for real-time process monitoring, variable impedance control for robotic manipulation, and safety strategies for human-robot collaboration. Doltsinis is best known for his pioneering work on snap-fit assembly—a critical joining process in manufacturing where success cannot be visually verified. His most influential paper, “A Machine Learning Framework for Real-Time Identification of Successful Snap-Fit Assemblies” (2019, 40 citations), introduces a novel approach using force profile classification to detect assembly completion in real time, bridging the gap between human haptic cues and autonomous robotic execution. This work, supported by the open-access dataset “Ds.04.Certh.Snapfitforceprofiles” (2018), has become a foundational resource for researchers in the field. His earlier research on task-based variable impedance strategies (2016) and minimum-invasive safety protocols for unexpected human-robot contact (2017) further demonstrates his commitment to practical, safe, and efficient automation solutions. Doltsinis’s contributions are shaping the next generation of adaptive, sensor-driven robotic systems for industry.