Alexander Krawciw

Papers

Total Citations

H-Index

About

Alexander Krawciw is a robotics researcher whose work centers on perception and autonomy for mobile robots in unstructured environments. His primary research areas include 3D LiDAR-based scene understanding, unsupervised learning, and change detection—critical for robots operating in dynamic, real-world settings. Krawciw’s major contribution is a novel, fully unsupervised deep learning approach to LiDAR change detection, which reframes semantic segmentation as a binary problem, enabling robots to identify environmental changes without requiring predefined semantic classes or labeled training data. This breakthrough is especially impactful for field robotics, where closed-set semantic models often fail. His 2024 paper, “Change of Scenery: Unsupervised LiDAR Change Detection for Mobile Robots,” has garnered early citations, reflecting its timely relevance. By eliminating the need for costly annotations, Krawciw’s work paves the way for more adaptable, long-term autonomous navigation in forests, mines, and disaster zones. His research promises to make robots more resilient and perceptive in the wild, marking him as an emerging innovator in robotic perception.