Position : Ph.D. Student
Affiliation : INRIA Lille – Nord Europe & Robocath
Advisors : Christian Duriez, Jérémie Dequidt, Philippe Preux
Adress : 40 Avenue Halley Bat A, 59650 Villeneuve d’Ascq, France.
E-Mail : pierre.schegg@inria.fr
Personal Website : LinkedIn
I received my Masters Degree from Ecole Centrale de Lille. I studied Mechanical Engineering and Control Theory. I worked on UAV control (quadcopter, boat, submarine, mobile robot), computer vision, mechanical simulation, compliant grippers (Robocup Logistics League), a surgical robot for otology (partnership with Nantes University Hospital) and 3D printed prosthetics (partnership between Polytechnique Montréal and Centre de Réadaptation Marie Enfant).
My work focuses on autonomous guidewire and catheter navigation in the context of Percutaneous Coronary Interventions. This includes collecting and cleaning patient data of heart and coronary artery geometries, physics-based FEM simulation of guidewire and catheter navigation in the arteries as well as heart beat motion. The main focus of my work is sequential decision making in the context of PCI using Reinforcement Learning and Tree Search based planning. I also demonstrated 2D and 3D transfer from simulation to reality using the R-One robotic platform and silicone phantoms of the arteries.
As of October 2021 this work has led to 1 filed patent and 3 journal articles (1 published and 2 submitted)
I am expecting to defend my thesis in April 2022
Selected publications:
Schegg P , Duriez C (2022) Review on generic methods for mechanical modeling, simulation and control of soft robots. PLOS ONE 17(1): e0251059.
Schegg P, Ménager E, et al. (2022). SofaGym: An open platform for Reinforcement Learning based on Soft Robot simulations. Soft Robotics Journal. submitted, under review
Schegg P, Dequidt J, et al. (2022). Automated planning for robotic guidewire navigation in the coronary arteries. In 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft).
