Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Tu, Wu, Kan, Zhu, Yongdong, Ji, Wei
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:https://arxiv.org/abs/2212.10737
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913214111940608
author Xu, Tu
Wu, Kan
Zhu, Yongdong
Ji, Wei
author_facet Xu, Tu
Wu, Kan
Zhu, Yongdong
Ji, Wei
contents This paper proposes a new driving style recognition approach that allows autonomous vehicles (AVs) to perform trajectory predictions for surrounding vehicles with minimal data. Toward that end, we use a hybrid of offline and online methods in the proposed approach. We first learn typical driving styles with PCA and K-means algorithms in the offline part. After that, local Maximum-Likelihood techniques are used to perform online driving style recognition. We benchmarked our method on a real driving dataset against other methods in terms of the RMSE value of the predicted trajectory and the observed trajectory over a 5s duration. The proposed approach can reduce trajectory prediction error by up to 37.7\% compared to using the parameters from other literature and up to 24.4\% compared to not performing driving style recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2212_10737
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Driving Style Recognition at First Impression for Online Trajectory Prediction
Xu, Tu
Wu, Kan
Zhu, Yongdong
Ji, Wei
Systems and Control
This paper proposes a new driving style recognition approach that allows autonomous vehicles (AVs) to perform trajectory predictions for surrounding vehicles with minimal data. Toward that end, we use a hybrid of offline and online methods in the proposed approach. We first learn typical driving styles with PCA and K-means algorithms in the offline part. After that, local Maximum-Likelihood techniques are used to perform online driving style recognition. We benchmarked our method on a real driving dataset against other methods in terms of the RMSE value of the predicted trajectory and the observed trajectory over a 5s duration. The proposed approach can reduce trajectory prediction error by up to 37.7\% compared to using the parameters from other literature and up to 24.4\% compared to not performing driving style recognition.
title Driving Style Recognition at First Impression for Online Trajectory Prediction
topic Systems and Control
url https://arxiv.org/abs/2212.10737