Samuel Paradis

About

Samuel Paradis is a leading researcher in surgical robotics, specializing in the automation of high-precision subtasks using cable-driven systems like the da Vinci robot. His work bridges depth-sensing, deep learning, and control theory to achieve superhuman performance in surgical manipulation. Paradis’s most cited paper (39 citations) demonstrates how advanced RGBD cameras enable reliable automation of surgical subtasks, while his 2022 study (37 citations) on automating peg transfer shows that deep learning-calibrated systems can exceed human speed, accuracy, and consistency. He also developed an intermittent visual servoing framework (33 citations) that maintains precision despite instrument changes—a critical challenge in real surgeries. His work on unmodified surgical needle localization and grasping (30 citations) advances suturing automation, and his Fog Robotics algorithms (21 citations) introduce cloud-based lambda computing for adaptive motion planning. Paradis’s contributions have been recognized for their potential to reduce surgeon fatigue and improve procedural efficiency, with several papers achieving notable citation counts in the competitive field of medical robotics. His research continues to push the boundaries of what autonomous surgical systems can achieve.

Research Focus

Key Achievements

Top Papers

1. 1
   Applying Depth-Sensing to Automated Surgical Manipulation with a da Vinci Robot

   39 citations · 2020
2. 2
   Automating Surgical Peg Transfer: Calibration With Deep Learning Can Exceed Speed, Accuracy, and Consistency of Humans

   37 citations · 2022
3. 3
   Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation

   33 citations · 2021
4. 4
   Learning to Localize, Grasp, and Hand Over Unmodified Surgical Needles

   30 citations · 2022
5. 5
   Fog Robotics Algorithms for Distributed Motion Planning Using Lambda Serverless Computing

   21 citations · 2020
6. 6
   Superhuman Surgical Peg Transfer Using Depth-Sensing and Deep Recurrent Neural Networks.

   9 citations · 2020
7. 7
   6-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNN

   7 citations · 2020
8. 8
   Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Sensing, Temporal Windowing, and Linear and Recurrent Neural Network Compensation

   5 citations · 2020
9. 9
   Intermittent Visual Servoing: Efficiently Learning Policies Robust to Instrument Changes for High-precision Surgical Manipulation

   3 citations · 2020

Key Collaborators

Contact & Links