Jan Wietrzykowski
Papers
5
Total Citations
255
H-Index
4
About
Jan Wietrzykowski is a roboticist whose work sits at the intersection of perception, navigation, and machine learning for autonomous systems. His research focuses on enabling robots to operate robustly in unstructured and challenging environments, particularly through place recognition and motion planning. His most impactful contribution is the development of a low-effort place recognition system that leverages WiFi fingerprints and deep learning, a paper that has garnered 178 citations and demonstrates a practical, cost-effective approach to robot localization. Wietrzykowski has also made significant strides in terrain-aware locomotion, proposing a motion planning framework for six-legged walking robots that integrates both geometric data and semantic labeling of natural terrain. This allows the robot to distinguish between traversable surfaces and obstacles, a critical capability for outdoor deployment. Further contributions include a lightweight RGB-D SLAM system designed for search and rescue robots, and a probabilistic framework for global localization using segmented planes, which incorporates uncertain cues into a robust pose estimation. By combining deep learning, semantic reasoning, and probabilistic methods, Wietrzykowski’s work advances the reliability and autonomy of robots operating in the wild.
Research Focus
Key Achievements
Top Papers
- 1Low-Effort Place Recognition with WiFi Fingerprints Using Deep Learning178 citations · 2017
- 2
- 3Lightweight RGB-D SLAM System for Search and Rescue Robots21 citations · 2015
- 4
- 5A probabilistic framework for global localization with segmented planes3 citations · 2017