Pascal Colling
Papers
1
Total Citations
2
H-Index
1
About
Pascal Colling is a researcher focused on advancing the reliability and efficiency of 3D perception systems, particularly for autonomous driving and robotics. His primary research areas include object detection in LiDAR point clouds and quality estimation for deep learning models. Colling’s major contribution is the development of LMD (Light-weight Model-agnostic Detector), a novel framework that enables real-time, prediction-level quality estimation for object detection without requiring ground truth data. This work addresses a critical gap in safety-critical applications by allowing systems to assess their own detection confidence on the fly. While his most-cited paper, "LMD: Light-Weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds" (2024), has garnered 2 citations in its early stage, it represents a promising step toward trustworthy autonomous perception. Colling’s approach stands out for its model-agnostic design and computational efficiency, making it suitable for resource-constrained platforms. His research holds potential for improving the robustness of LiDAR-based perception in real-world environments, contributing to safer autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1