Kevin Jebbink

Papers

Total Citations

H-Index

About

Kevin Jebbink is a roboticist advancing the frontier of robust autonomy through the principled use of invariants—mathematical constraints that remain unchanged under system transformations. His research focuses on integrating invariant-based world models into robotic perception and control, enabling machines to maintain reliable performance despite environmental disturbances. Jebbink’s most-cited work, "Invariant-Based World Models for Robust Robotic Systems Demonstrated on an Autonomous Football Table" (2022), showcases this approach by equipping a robotic football table with skills that resist perturbations, such as lighting changes or physical jostling. While his citation count is still growing—a testament to the novelty of his ideas—the work has already garnered attention for its elegant fusion of theoretical rigor and practical demonstration. Jebbink’s contributions lie in bridging the gap between abstract mathematical invariants and real-world robotic tasks, offering a pathway to more resilient systems in dynamic settings. His research holds promise for applications ranging from industrial automation to autonomous vehicles, where robustness is critical. As a rising voice in robotics, Jebbink is shaping how machines perceive and act under uncertainty, making his work a compelling read for students and researchers alike.