Daniela Leonardis
Papers
3
Total Citations
8
H-Index
2
About
Daniela Leonardis is a researcher at the intersection of robotic teleoperation, rehabilitation engineering, and AI-driven clinical decision support. Her work focuses on enhancing human-robot interaction, particularly in two critical domains: dexterous teleoperation and post-stroke rehabilitation. In teleoperation, she addresses the fundamental challenge of grasping dexterity, developing virtual dashboard subsystems that compensate for the limitations of stereoscopic vision and force/tactile feedback—a contribution demonstrated in her 2024 paper on the Sully teleoperation system (5 citations). Her most impactful work, however, lies in rehabilitation robotics. Leonardis pioneers the use of machine learning to predict clinical outcomes from high-resolution kinematic and force data collected during robotic therapy. Her 2025 study on feature group importance for outcome prediction (2 citations) provides a framework for personalized treatment tuning, while her systematic data management approach (1 citation) enables effective AI-driven decision support systems. By transforming raw sensor data into actionable clinical insights, Leonardis is helping to bridge the gap between robotic rehabilitation hardware and personalized patient care, ultimately aiming to enhance therapy effectiveness for stroke survivors.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3