Luis Denninger
Papers
2
Total Citations
6
H-Index
2
About
Luis Denninger is a leading researcher in robotic perception and autonomous manipulation, with a focus on object pose estimation under challenging conditions such as symmetry. His work addresses a critical gap in robotics: the inability of traditional pose estimators to handle symmetric objects, which often leads to ambiguous or incorrect poses for manipulation tasks. Denninger’s key contribution, detailed in his highly cited 2022 paper "Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels," introduces a novel framework that learns implicit probability distributions over orientations. This allows robots to reason about multiple valid poses for symmetric objects, significantly improving robustness in real-world scenarios. The work has garnered 3 citations, reflecting its early impact in the field. Additionally, Denninger contributed to the RoboCup 2023 Humanoid AdultSize champion team NimbRo, where his work on NimbRoNet3 visual perception and responsive gait with waveform in-walk kicks enabled dynamic, real-time soccer play. This achievement highlights his ability to translate theoretical advances into practical, award-winning robotic systems, making him a notable figure in both perception and embodied AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2