Mikel De Iturrate Reyzabal

Mikel De Iturrate Reyzabal

PhD Student in the Department of Biomedical Engineering and Imaging Sciences at King's College London

Posts by Collection

portfolio

publications

OMsense: An Omni Tactile Sensing Principle Inspired by Compound Eyes

Published in IEEE/ASME Transactions on Mechatronics, 2023

In this paper, we design a new sensing technique using arrays of lenses, in order to reduce the pixel density of the image.

Recommended citation: OMsense: An Omni Tactile Sensing Principle Inspired by Compound Eyes C Yu, M Chen, MDI Reyzabal, J Back, D Cao, H Liu - IEEE/ASME Transactions on Mechatronics, 2023

Comparative verification of control methodology for robotic interventional neuroradiology procedures

Published in International Journal of Computer Assisted Radiology and Surgery, 2023

This paper presents a comparative study of different control methodologies for robotic interventional neuroradiology simulated in SOFA.

Recommended citation: Jackson, Benjamin, et al. "Comparative verification of control methodology for robotic interventional neuroradiology procedures." International Journal of Computer Assisted Radiology and Surgery 18.11 (2023): 1977-1986.

DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery

Published in IEEE Robotics and Automation Letters, 2024

In this paper, we analyse the effectiveness of Vision Transformers and temporal sampling on the estimation of forces in Minimally Invasive Robotic Surgery.

Recommended citation: Reyzabal, Mikel De Iturrate, et al. "DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery." IEEE Robotics and Automation Letters (2024). http://mikelitu.github.io/files/dafoes.pdf

talks

Implementing Dynamic Active Constraints for Safe Remote Robotic Surgery in SOFA

Published:

Safe navigation of body lumens and interaction with organs is an open challenge in Minimally Invasive Surgery (MIS). Simulating active constraints on soft-tissue for surgical robots has been a promising solution to this challenge; with active constraints, the robot is guided to move in a safe imaginary passage during a MIS navigation or interaction task. This research presents a way to utilize SOFA (Simulation Open Framework Architecture) to implement dynamic active constraints for safe remote robotic palpation and navigation around an organ through a Geomatic Touch haptic interface with force feedback. An active constraint is formulated as a Bilateral Constraint, using the SOFA Sliding Constraint module, between two safely interacting objects, here the robot tip and liver tissue. By simulating a path-following navigation scenario with and without the active constraints in SOFA, we observed a significant improvement (13.034 mm vs 0.009 mm) in the path following error in the presence of active constraints. These results can be used to simulate more complex surgical scenarios in SOFA as well as for semi-autonomous navigation of surgical robots in real life.

teaching