Maximilian Ulmer

Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

Papers

Total Citations

H-Index

About

Maximilian Ulmer is a robotics researcher whose work sits at the intersection of computer vision, reinforcement learning, and autonomous manipulation. His research focuses on enabling robots to perceive and interact with their environments under uncertainty—whether from imprecise 3D models or unstructured real-world settings. In his most cited work, Ulmer tackles the challenging problem of 6D object pose estimation for orbital robotics, introducing a dense 2D-to-3D correspondence predictor that estimates object pose from single images even when only approximate 3D geometry is available. This contribution, published in 2023, has already garnered 20 citations, reflecting its relevance to space robotics and computer vision. Ulmer also addresses vision-based obstacle avoidance for robotic manipulators, proposing a unified framework that integrates perception and motion generation—a departure from the siloed approaches common in the field. Additionally, his work on adaptive force-impedance action spaces for reinforcement learning explores how robots can learn complex manipulation skills efficiently, bridging the gap between simulation and real-world deployment. With a growing citation footprint and a focus on practical, robust robotic systems, Ulmer’s research is shaping how robots perceive and act in uncertain, dynamic environments.