Position Estimation Considering Uncertain Classification of Cyclists Based on Partially Observed Movement Characteristics
Kento Suzuki, Takuma Ito · 2026
Read Position Estimation Considering Uncertain Classification of Cyclists Based on Partially Observed Movement Characteristics by Kento Suzuki, Takuma Ito (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-13211305.txt.
Description
Kento Suzuki and Takuma Ito refine a method for predicting where a cyclist will be at a blind intersection, in this study from twenty twenty-six. On Japan's narrow community roads, walls and hedges hide crossing cyclists until late. Their earlier system filled the blind spots with statistics: typical cyclist movements for each spot, used as virtual observations and virtual control inputs in position estimation.
The gap was classification. Real-time sensors see too little to sort a rider confidently into one behavior cluster. The new method keeps the classification soft, blending the statistics of every cluster by their probabilities, so uncertainty is priced in rather than ignored. Simulations and a real-world experiment beat the older, hard-classification approach. The authors aim the method at cooperative safety systems that warn drivers before the cyclist appears.
Catalog record
| CREATOR | Kento Suzuki, Takuma Ito |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |