Jean-Michel Renders

Papers

Total Citations

201

H-Index

About

Jean-Michel Renders is a pioneering researcher whose work bridges classical robotics and modern machine learning. His primary research areas include robot kinematic calibration, parameter identification, and the manipulation of deformable objects. Renders’ most influential contribution is his 1991 paper on kinematic calibration and geometrical parameter identification for robots, which introduced a maximum-likelihood approach for identifying geometrical errors and a novel experimental setup for measuring end-reflector position errors. This foundational work has garnered 193 citations, establishing him as a key figure in precision robotics. He further advanced the field by exploring non-geometrical parameter identification using neural network techniques in 1992, an early integration of learning-based methods into robotic calibration. More recently, Renders has ventured into the challenging domain of deformable object manipulation, as evidenced by his 2024 work on attention-based cloth manipulation from model-free topological representations. This research addresses the stochastic nature of fabric dynamics, applying statistical learning to a problem long considered difficult for robotic systems. With a career spanning over three decades, Renders demonstrates a remarkable ability to evolve with the field, from classical calibration to cutting-edge manipulation of soft materials.