Juergen Hess

Papers

Total Citations

H-Index

About

Juergen Hess is a researcher whose work sits at the intersection of robotics, computer vision, and human-robot interaction. His key research areas include human motion classification and visual failure detection in robotic manipulation. Hess made a significant contribution to the field of human action recognition with his novel graph-based approach for learning and classifying motion models from motion capture data. By representing observed trajectories as graphs, his method enables robots to better understand and anticipate human movements—a critical capability for service and domestic robots. This foundational work has garnered 10 citations, establishing a framework that other researchers have built upon. In his later work on visual failure detection, Hess tackled the challenging problem of distinguishing subtle task outcomes—such as whether a screw tip is near a hole or fully inserted. His research on viewpoint selection (8 citations) demonstrates that these minute differences are often only observable from specific camera angles, and sometimes require information from multiple viewpoints for complete verification. This work has practical implications for improving the reliability of automated assembly and quality control in manufacturing.