Lane Change Inconsistencies in the highD Dataset

2025/03/20 by Zhaohan Wang, Yang Gao · 2 voices
Engineering · Computer Science · #Autonomous Vehicle Technology and Safety #Traffic control and management #Time Series Analysis and Forecasting

paper · pdf · doi:10.32866/001c.132341

openalex publication_date 2025/03/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The highD dataset is renowned for its large-scale, high-frequency data points and smooth, precise vehicle trajectories, making it a valuable resource for various traffic research applications. However, its suitability for studying lane-changing behavior is questionable due to the lack of upstream and downstream context at the recording sites. Further analysis shows inconsistency in speed gains during lane changes in opposite directions, suggesting potential limitations on its application in lane change studies.

Discussions

• Wang, Zhaohan, and Yang Gao. 2025. “Lane Change Inconsistencies in the highD Dataset.” Findings, March. doi.org/10.32866/001.... [bsky, 2 points, 0 comments]
• Wang, Zhaohan, and Yang Gao. 2025. “Lane Change Inconsistencies in the highD Dataset.” Findings, March. https://doi.org/10.32866/001c.132341. [bsky, 0 points, 0 comments]

Related

• Why Studying Cut-ins? Comparing Cut-ins and Other Lane Changes Based on Naturalistic Driving Data
• On the precise quantification of the impact of a single discretionary lane change on surrounding traffic
• Uncovering variability in human driving behavior through automatic extraction of similar traffic scenes from large naturalistic datasets
• Controlled Experiments on Lane Changing by Transitional Autonomous Vehicle: Dataset and Behavioral Insights
• Exploration of lane-changing duration for heavy vehicles and passenger cars: a survival analysis approach