The AD4CHE Dataset and Its Application in Typical Congestion Scenarios of Traffic Jam Pilot Systems

Zhang, Yuxin; Wang, Cheng; Yu, Ruilin; Wang, Luyao; Wei, Qufu; Gao, Yang; Li, Pengfei

doi:10.1109/tiv.2023.3260902

Cited by 17 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The existing publicly available datasets about the merging behavior are NGSIM, INTERACTION [10], AUTOMATUM [11], and AD4CHE [12]. Although these datasets are invaluable for data-driven driving behavior analysis, they have certain shortcomings.…”

Section: Public Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Unraveling Spatial–Temporal Patterns and Heterogeneity of On-Ramp Vehicle Merging Behavior: Evidence from the exiD Dataset

Wang,

Li,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Understanding the spatiotemporal characteristics of merging behavior is crucial for the advancement of autonomous driving technology. This study aims to analyze on-ramp vehicle merging patterns, and investigate how various factors, such as merging scenarios and vehicle types, influence driving behavior. Initially, a framework based on a high-definition (HD) map is developed to extract trajectory information in a meticulous manner. Subsequently, eight distinct merging patterns are identified, with a thorough examination of their behavioral characteristics from both temporal and spatial perspectives. Merging behaviors are examined temporally, encompassing the sequence of events from approaching the on-ramp to completing the merge. This study specifically analyzes the target lane’s spatial characteristics, evaluates the merging distance (ratio), investigates merging speed distributions, compares merging patterns and identifies high-risk situations. Utilizing the latest aerial dataset, exiD, which provides HD map data, the study presents novel findings. Specifically, it uncovers patterns where the following vehicle in the target lane chooses to accelerate and overtake rather than cutting in front of the merging vehicle, resulting in Time-to-Collision (TTC) values of less than 2.5 s, indicating a significantly higher risk. Moreover, the study finds that differences in merging speed, distance, and duration can be disregarded in patterns where vehicles are present both ahead and behind, or solely ahead, suggesting these patterns could be integrated for simulation to streamline analysis and model development. Additionally, the practice of truck platooning has a significant impact on vehicle merging behavior. Overall, this study enhances the understanding of merging behavior, facilitating autonomous vehicles’ ability to comprehend and adapt to merging scenarios. Furthermore, this research is significant in improving driving safety, optimizing traffic management, and enabling the effective integration of autonomous driving systems with human drivers.

show abstract

Section: Public Datasetsmentioning

confidence: 99%

“…The HD map is one of the important technologies for autonomous driving, providing a large amount of more precise vehicle spatial-temporal data. The AD4CHE dataset provides geo-referenced data but lacks the trajectory of vans [12].…”

Section: Public Datasetsmentioning

confidence: 99%

Unraveling Spatial–Temporal Patterns and Heterogeneity of On-Ramp Vehicle Merging Behavior: Evidence from the exiD Dataset

Wang,

Li,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…T HE past decade has witnessed the significant breakthroughs on autonomous driving with artificial intelligence methods [2], [3], leading to numerous applications in transportation, including improving traffic safety [4]- [6], reducing traffic congestion [7], [8], minimizing air pollution [9], [10], and enhancing traffic efficiency [11]- [13]. Object detection is a critical component of autonomous driving, which relies on computer vision and artificial intelligence techniques to understand driving scenarios [2], [14].…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather

et al. 2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, however such assumption may fail in different weather conditions. Due to the domain gap, a detection model trained under clear weather may not perform well in foggy and rainy conditions. Overcoming detection bottlenecks in foggy and rainy weather is a real challenge for autonomous vehicles deployed in the wild. To bridge the domain gap and improve the performance of object detectionin foggy and rainy weather, this paper presents a novel framework for domain-adaptive object detection. The adaptations at both the image-level and objectlevel are intended to minimize the differences in image style and object appearance between domains. Furthermore, in order to improve the model's performance on challenging examples, we introduce a novel adversarial gradient reversal layer that conducts adversarial mining on difficult instances in addition to domain adaptation. Additionally, we suggest generating an auxiliary domain through data augmentation to enforce a new domain-level metric regularization. Experimental findings on public V2V benchmark exhibit a substantial enhancement in object detection specifically for foggy and rainy driving scenarios.

show abstract

Safety assessment for autonomous vehicles: A reference driver model for highway merging scenarios

Wang,

Guo,

Zhao

et al. 2024

Accident Analysis & Prevention

View full text Add to dashboard Cite

The AD4CHE Dataset and Its Application in Typical Congestion Scenarios of Traffic Jam Pilot Systems

Cited by 17 publications

References 53 publications

Unraveling Spatial–Temporal Patterns and Heterogeneity of On-Ramp Vehicle Merging Behavior: Evidence from the exiD Dataset

Unraveling Spatial–Temporal Patterns and Heterogeneity of On-Ramp Vehicle Merging Behavior: Evidence from the exiD Dataset

Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather

Safety assessment for autonomous vehicles: A reference driver model for highway merging scenarios

Contact Info

Product

Resources

About