Physics-Guided Gaussian Process Mapping of Strong-Gradient Radiation Fields from Mobile Robot Surveys: The Role of Sampling Geometry
Hui Li, Qing Fan, Liye Liu, Hua Li, Faguo Chen, Mingming Wang, Deyuan Li, Yuan Zhao, Zhi Chen · 2026
Read Physics-Guided Gaussian Process Mapping of Strong-Gradient Radiation Fields from Mobile Robot Surveys: The Role of Sampling Geometry by Hui Li, Qing Fan, Liye Liu, Hua Li, Faguo Chen, Mingming Wang, Deyuan Li, Yuan Zhao, Zhi Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611590.txt.
Description
Hui Li and co-authors map steep radiation fields with a roaming robot, and ask which rebuild method to trust. Their 2026 study uses one collimated source in a two-dimensional indoor hall. Fields near shielded sources slope hard, and workers need the slopes drawn right. A tracked robot paired laser mapping with a dose sensor, and ran the hall seven times. Methods were scored on points near the driven path and, more strictly, on blocks never visited.
Where sampling spread evenly, a neural net beat process models soundly. Along driven paths, its edge vanished near the path and flipped to big errors off it. A physics-guided process model won off-path, cutting error against all rivals.
Catalog record
| CREATOR | Hui Li, Qing Fan, Liye Liu, Hua Li, Faguo Chen, Mingming Wang, Deyuan Li, Yuan Zhao, Zhi Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |