Prediction of Lane Change Intentions of Human Drivers Using an LSTM, a CNN, and a Transformer
IEEE Access · 2026 · 14 · 31685-31698
DOI: 10.1109/access.2026.3668022 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Francesco de Cristofaro und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Republic of Austria, Ministry of Climate Action, Environment, Energy, Mobility, Innovation and Technology, managed by Austrian Research Promotion Agency, Science Technology Plan Project of Zhejiang Province, Zhejiang Asia–Pacific Intelligent Connected Vehicle Innovation Center Company Ltd.
Abstract (Originalsprache)
Lane changes of preceding vehicles have a great impact on the motion planning of automated vehicles, especially in complex traffic situations. Predicting them would benefit the public in terms of safety and efficiency. While many research efforts have been made in this direction, few concentrated on predicting maneuvers within a set time interval compared to predicting at a set prediction time. In addition, there exists a lack of comparisons between different architectures to try to determine the best performing one and to assess how to correctly choose the input for such models. In this paper, the structures of an LSTM, a CNN, and a Transformer network are described and implemented to predict the intention of human drivers to perform a lane change. We show how the data was prepared starting from a publicly available dataset (highD), which features were used, how the networks were designed, and finally, we compare the results of the three networks with different configurations of input data. We found that transformer networks performed better than the other networks and were less affected by overfitting. The accuracy of the method spanned from 82.79% to 96.73% for different input configurations and showed overall good performances considering also precision and recall.
Förderung
- Republic of Austria, Ministry of Climate Action, Environment, Energy, Mobility, Innovation and Technology, managed by Austrian Research Promotion Agency
- Science Technology Plan Project of Zhejiang Province
- Zhejiang Asia–Pacific Intelligent Connected Vehicle Innovation Center Company Ltd
Zitieren
APA
Cristofaro, F. D., Hofbaur, F., Yang, A., & Eichberger, A. (2026). Prediction of Lane Change Intentions of Human Drivers Using an LSTM, a CNN, and a Transformer. IEEE Access, 14, 31685-31698. https://doi.org/10.1109/access.2026.3668022
Vancouver
Cristofaro FD, Hofbaur F, Yang A, Eichberger A. Prediction of Lane Change Intentions of Human Drivers Using an LSTM, a CNN, and a Transformer. IEEE Access. 2026;14:31685-31698. doi:10.1109/access.2026.3668022
BibTeX
@article{Cristofaro2026,
author = {Cristofaro, Francesco de and Hofbaur, Felix and Yang, Aixi and Eichberger, Arno},
title = {Prediction of Lane Change Intentions of Human Drivers Using an LSTM, a CNN, and a Transformer},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {31685--31698},
doi = {10.1109/access.2026.3668022}
}
EUVIMED