Lateral classification of vehicle behavior for automated logic scenario generation

Advanced testing and validation in the automotive industry are predominantly conducted through real-world driving, while simulation is primarily used for scenarios that are difficult, dangerous, or impractical to reproduce on the road. The production of a well-designed simulation scenario includes n...

Full description

Saved in:
Bibliographic Details
Main Authors: Vjekoslav Diklić, Ivan Marković
Format: Article
Language:English
Published: Taylor & Francis Group 2025-10-01
Series:Automatika
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/00051144.2025.2535068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850100782826782720
author Vjekoslav Diklić
Ivan Marković
author_facet Vjekoslav Diklić
Ivan Marković
author_sort Vjekoslav Diklić
collection DOAJ
description Advanced testing and validation in the automotive industry are predominantly conducted through real-world driving, while simulation is primarily used for scenarios that are difficult, dangerous, or impractical to reproduce on the road. The production of a well-designed simulation scenario includes numerous edge cases and relies on expert labor, but it can still miss real-world complexities. Given that, scenarios based on real-world driving data are more desirable, but are dominantly based on replaying the positions of all vehicles over time. For greater flexibility, real-world driving scenarios should be automatically converted into logic scenarios with adjustable segments such as lane keeping, lane changing, accelerating, etc. This paper introduces a new method for detecting and classifying lateral vehicle movements. The method is based on polynomial fitting and identifies the start and end points of vehicle lane changes with inflection points of a third-degree polynomial. For evaluation, two publicly available, manually labeled lane-change datasets are used, and a novel highway lane-change simulation dataset is introduced. The polynomial approach is compared against a bidirectional long short-term memory (Bi-LSTM) model introduced in this work, as well as three additional neural network architectures drawn from recent literature, followed by a discussion of the experimental validation for each.
format Article
id doaj-art-c4fab905d7a44fe49f94c3f9586bb3f5
institution DOAJ
issn 0005-1144
1848-3380
language English
publishDate 2025-10-01
publisher Taylor & Francis Group
record_format Article
series Automatika
spelling doaj-art-c4fab905d7a44fe49f94c3f9586bb3f52025-08-20T02:40:13ZengTaylor & Francis GroupAutomatika0005-11441848-33802025-10-0166462563710.1080/00051144.2025.2535068Lateral classification of vehicle behavior for automated logic scenario generationVjekoslav Diklić0Ivan Marković1dSPACE d.o.o., Zagreb, CroatiaDepartment of Control and Computer Engineering, Laboratory for Autonomous Systems and Mobile Robotics, University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, CroatiaAdvanced testing and validation in the automotive industry are predominantly conducted through real-world driving, while simulation is primarily used for scenarios that are difficult, dangerous, or impractical to reproduce on the road. The production of a well-designed simulation scenario includes numerous edge cases and relies on expert labor, but it can still miss real-world complexities. Given that, scenarios based on real-world driving data are more desirable, but are dominantly based on replaying the positions of all vehicles over time. For greater flexibility, real-world driving scenarios should be automatically converted into logic scenarios with adjustable segments such as lane keeping, lane changing, accelerating, etc. This paper introduces a new method for detecting and classifying lateral vehicle movements. The method is based on polynomial fitting and identifies the start and end points of vehicle lane changes with inflection points of a third-degree polynomial. For evaluation, two publicly available, manually labeled lane-change datasets are used, and a novel highway lane-change simulation dataset is introduced. The polynomial approach is compared against a bidirectional long short-term memory (Bi-LSTM) model introduced in this work, as well as three additional neural network architectures drawn from recent literature, followed by a discussion of the experimental validation for each.https://www.tandfonline.com/doi/10.1080/00051144.2025.2535068Logic scenariosdriving scenariosegment identificationautomated scenario generationbidirectional long-short term memory networklane change classification
spellingShingle Vjekoslav Diklić
Ivan Marković
Lateral classification of vehicle behavior for automated logic scenario generation
Automatika
Logic scenarios
driving scenario
segment identification
automated scenario generation
bidirectional long-short term memory network
lane change classification
title Lateral classification of vehicle behavior for automated logic scenario generation
title_full Lateral classification of vehicle behavior for automated logic scenario generation
title_fullStr Lateral classification of vehicle behavior for automated logic scenario generation
title_full_unstemmed Lateral classification of vehicle behavior for automated logic scenario generation
title_short Lateral classification of vehicle behavior for automated logic scenario generation
title_sort lateral classification of vehicle behavior for automated logic scenario generation
topic Logic scenarios
driving scenario
segment identification
automated scenario generation
bidirectional long-short term memory network
lane change classification
url https://www.tandfonline.com/doi/10.1080/00051144.2025.2535068
work_keys_str_mv AT vjekoslavdiklic lateralclassificationofvehiclebehaviorforautomatedlogicscenariogeneration
AT ivanmarkovic lateralclassificationofvehiclebehaviorforautomatedlogicscenariogeneration