Metraipolis › archive › dc_7e5deab52f86
Cross-Scenario Controller Parameter Transformation from Real-World Driving Data through Flow Matching — arXiv:2610.32719
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32719
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T20:14:48.480Z
- SHA-256 of the archived text
529b919d4f2b59b2ad0a247abb6c260897ea416370296f225a1c81946da3cb4c- Stable URL of this page
https://metraipolis.com/documento/dc_7e5deab52f86
How to cite
Cross-Scenario Controller Parameter Transformation from Real-World Driving Data through Flow Matching — arXiv:2610.32719 — arXiv (en), https://arxiv.org/abs/2610.32719 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e5deab52f86 (Metraipolis archive dc_7e5deab52f86, sha256 529b919d4f2b59b2ad0a247abb6c260897ea416370296f225a1c81946da3cb4c)
BibTeX
@misc{dc7e5deab52f86,
title = {Cross-Scenario Controller Parameter Transformation from Real-World Driving Data through Flow Matching — arXiv:2610.32719},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32719},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e5deab52f86; sha256 529b919d4f2b59b2ad0a247abb6c260897ea416370296f225a1c81946da3cb4c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32719. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Advanced Driver Assistance Systems have become increasingly widespread, aiming to support drivers, reduce workload, and improve traffic safety. However, many systems are rarely used because their behavior feels unnatural and does not match individual driving behavior. The growing availability of large-scale, real-world human driving data enables more human-like and driver-individual assistance functions. This paper formulates the adaptation of Adaptive Cruise Control parameters as a driver-individual scenario-to-scenario transport problem, transforming controller parameters from one driving context to another. Using flow matching, we train a generative model to predict the target-scenario behavior of previously unseen drivers from only a few demonstrations in a source scenario. We compare the approach with a linear parameter-shift baseline and evaluate flow-matching variants incorporating driver-consistent coupling, driver embeddings, and classifier-free guidance based on driving profiles extracted from trajectory data using a variational autoencoder. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.32719 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-26T19:49:03.502Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).