Ilka Marhenke

Papers

Total Citations

H-Index

About

Ilka Marhenke’s research focuses on advancing human-robot interaction, particularly through intuitive teleoperation and learning from demonstration (LfD). Her work addresses a critical challenge in industrial robotics: enabling non-expert users to teach complex assembly tasks to robots quickly and efficiently. Her most-cited paper, “Teleoperation for learning by demonstration: Data glove versus object manipulation for intuitive robot control” (43 citations), systematically compares two teleoperation modes, providing foundational insights into how lay users can intuitively demonstrate behaviors to robots. Marhenke also investigates technical hurdles in LfD, such as robot arm singularity—analyzing how speed and delay contribute to alignment issues that break inverse kinematics. Her novel teleoperation device, which allows dynamic switching between control points during teaching, represents a practical contribution to industrial flexibility and efficiency. Though her citation counts are modest, her work is directly relevant to the growing demand for user-friendly robot programming in manufacturing. By bridging the gap between human intuition and robotic precision, Marhenke’s research helps democratize robot teaching, making it accessible to operators without programming expertise—a key step toward more adaptive and responsive industrial automation.