Jens Beringhoff

Universität Hamburg, Hamburg University of Technology

Papers

Total Citations

H-Index

About

Jens Beringhoff’s research lies at the intersection of surgical robotics, haptic feedback, and computer vision, with a primary focus on estimating interaction forces between surgical instruments and soft tissue during minimally invasive procedures. His most cited work, “Force estimation from OCT volumes using 3D CNNs” (2019, 19 citations), introduces a novel deep learning approach that leverages optical coherence tomography (OCT) volumetric data to predict instrument-tissue forces without the need for fragile or costly external sensors. This method addresses a critical challenge in robot-assisted surgery: the loss of haptic feedback. Earlier work, “Towards force sensing based on instrument-tissue interaction” (2016, 9 citations), laid the groundwork by proposing a vision-based force estimation technique that avoids instrument modifications, thereby preserving sterility and reducing cost. Beringhoff’s contributions are particularly notable for their potential to restore tactile sensation in teleoperated surgical systems, improving patient safety and surgical precision. His research has been recognized within the medical robotics community for its practical, sensorless approach to force sensing—a key enabler for next-generation minimally invasive interventions.