Max Robotics — Global Service Robot Directory + US Certification

About

Marek Kopicki is a robotics researcher whose work spans robotic manipulation, grasp planning, and machine learning for physical interaction. His research addresses some of the most challenging problems in autonomous robotics, including how robots can predict, plan, and adapt their manipulation strategies in complex, real-world environments. Kopicki's most influential contribution, "Dynamic Grasp and Trajectory Planning for Moving Objects" (2018, 102 citations), demonstrates how robots can dynamically track and grasp objects handed over by human collaborators — a critical capability for human-robot teamwork. His early work on learning to predict rigid body behavior under manipulation (2011, 63 citations) pioneered data-driven alternatives to physics simulators, enabling robots to plan more robustly from experience. His push manipulation research established foundational algorithms for non-prehensile manipulation using probabilistic and model-predictive approaches. Kopicki has also made notable contributions to nuclear decommissioning robotics (2016, 83 citations), applying advanced manipulation in high-stakes industrial settings where reliable autonomy is essential. His work on active vision, tactile feedback, and task-relevant grasp selection further reflects a holistic approach — ensuring robots not only grasp objects, but do so intelligently in service of downstream tasks. With over 460 combined citations, his research has meaningfully advanced the field of dexterous robotic manipulation.