Abed Soleymani
Papers
8
Total Citations
106
H-Index
7
About
Abed Soleymani is a researcher at the forefront of robot-assisted surgery, rehabilitation robotics, and artificial intelligence, whose work bridges machine learning, haptic teleoperation, and surgical skill assessment to advance human-robot interaction in medical settings. His most widely recognized contribution — a framework for modeling and emulating a physiotherapist's role in robot-assisted rehabilitation (27 citations) — demonstrated how haptic teleoperation could effectively replicate in-hospital therapies for home-based patients. Soleymani has made substantial strides in automating surgical skill evaluation, developing deep learning and domain-adapted machine learning approaches that objectively assess trainee surgeons' performance, reducing reliance on time-consuming and bias-prone qualitative methods, with several papers accumulating over a dozen citations within just a few years of publication. His more recent work extends into reinforcement learning for surgical autonomy, including a sim-to-real approach for autonomous blood suction (13 citations), and information-theoretic methods for analyzing bimanual coordination during complex surgical tasks. Beyond the operating room, Soleymani has also explored smart robotic walkers for gait symmetry assessment, reflecting a broad commitment to intelligent rehabilitation technologies. Collectively, his research is shaping safer, more effective training pipelines and autonomous capabilities for next-generation surgical and rehabilitation robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2Surgical Skill Evaluation From Robot-Assisted Surgery Recordings17 citations · 2021
- 3
- 4
- 5
- 6
- 7
- 8