Marco Piccinelli
Papers
6
Total Citations
104
H-Index
4
About
Marco Piccinelli is a leading researcher at the intersection of autonomous robotics, surgical systems, and artificial intelligence. His work primarily focuses on enabling robots to perform complex surgical subtasks—such as soft-tissue manipulation, dissection, and retraction—with increasing autonomy. Piccinelli’s major contributions include developing a soft tissue simulation environment for training reinforcement learning agents in autonomous robotic surgery (71 citations), which allows safe, trial-and-error policy learning before clinical deployment. He also pioneered data-driven methods for intra-operative estimation of anatomical attachments, enabling robots to adapt to dynamic surgical environments in real time. His research extends to advanced sensing, including 3D vision-based electrical impedance scanning for soft tissue conductivity, and trajectory planning enhanced by mixed reality for intuitive human-robot interaction. With a strong focus on Learning from Demonstrations (LfD) and Partially Observable Markov Decision Processes (POMDPs), Piccinelli is shaping the future of Robot-Assisted Minimally Invasive Surgery (RAMIS), moving surgeons from direct control to supervisory roles. His work has garnered over 100 citations, reflecting its growing influence in surgical robotics and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Trajectory planning using Mixed Reality: an experimental validation4 citations · 2021
- 5
- 6Learning from Demonstrations for Autonomous Soft-tissue Retraction2 citations · 2021