Pascal Meisner

Karlsruhe Institute of Technology, FZI Research Center for Information Technology

Papers

Total Citations

H-Index

About

Pascal Meisner is a robotics researcher whose work focuses on enabling robots to perform complex manipulation tasks without relying on pre-programmed object models or explicit environmental knowledge. His primary research areas include self-supervised learning for robotic manipulation, online trajectory adaptation, and sensor-based localization for autonomous systems. Meisner's most impactful contribution is his 2020 paper on self-supervised learning for precise pick-and-place operations, which has garnered 75 citations. This work addresses a fundamental challenge in robotics—performing flexible pick-and-place tasks without requiring an object model. Instead, the robot learns from a single demonstrated goal state, using planar manipulation to adapt to novel objects. This approach significantly reduces the need for extensive pre-programming and enhances robotic adaptability in unstructured environments. In his other notable work, Meisner developed TrueÆdapt, a model-free method for learning smooth online trajectory adaptations that respect physical constraints like jerk, acceleration, and velocity. Additionally, his earlier research on robust localization of furniture parts using depth and intensity data from range sensors contributed to autonomous manipulation in cluttered spaces. Through these contributions, Meisner has advanced the field of robot learning and manipulation, making robots more capable of operating in real-world, dynamic settings.