Max Robotics — Global Service Robot Directory + US Certification

About

Simon Manschitz is a robotics researcher whose work centers on robot learning, movement primitives, and the transfer of human manipulation skills to robotic systems through kinesthetic demonstrations. His research has made significant contributions to the challenge of enabling robots to learn and execute complex, sequential tasks by observing human guidance rather than relying solely on explicit programming. Manschitz is perhaps best known for his pioneering work on sequencing movement primitives, developing frameworks that allow robots to automatically learn the transitions between discrete motion segments. His 2015 paper on learning movement primitive attractor goals has garnered 55 citations, while his 2014 work on sequential skill learning from demonstrations has attracted 47 citations — together representing foundational contributions to the field. His research introduced graph-based representations and probabilistic decomposition methods to handle both positional and force-interaction tasks, broadening the applicability of learned skills to real-world manipulation scenarios such as unscrewing objects or performing contact-rich assembly. A recurring theme across his body of work is bridging the gap between human dexterity and robotic capability, addressing challenges of concurrency, force interaction, and skill sequencing. His research provides a compelling roadmap for making robots more intuitive to teach and more adaptable in unstructured environments.