Automatic detection method research of incidents in China-FOT database

Sun, Xiaoyu; Zhu, Xichan; Kaiyuan, Zhang; Lin, Li; Ma, Zhijun; Wang, Dazhi

doi:10.1109/itsc.2016.7795639

Cited by 7 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intersection conflict types are divided into three categories and seven dangerous scenarios based on classification methods such as SHRP2, NHTSA, and InteractIVe. Factors such as road density, surrounding environmental impact, visual-field obstruction, and insufficient information were found to account for a high proportion of the factors inducing intersection accidents, according to the Driving Reliability and Error Analysis Method (DREAM) induction analysis of the logical relationship of factors [33]. Researchers proposed indicators, such as the intrusion area, estimated passing-time difference, and estimated collision time, based on the movement trajectory of vehicles passing through intersections.…”

Section: Related Workmentioning

confidence: 99%

Research on the Vehicle-Behavior Boundary of Intersection Traffic Based on Naturalistic Driving Data Study

Wu,

Ma,

Zhu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

With the development and application of vehicle-infrastructure cooperative technology, the traffic regional safety related to intelligent connected vehicles (ICVs) has become the hotspot of the intelligent transportation system (ITS), and the integration of mixed autonomous and non-autonomous vehicles that are not cooperative in intersection areas has become a significant challenge due to the rapid advancement of autonomous vehicle technology. Autonomous vehicles in intersections with strong-structure and weak-rule characteristics pose a potential hazard in complex traffic situations. Studying the driving behavior of vehicles in intersections is of great significance due to the complex traffic environment, frequent traffic signals, and traffic violations, which can optimize the vehicle driving behavior and improve the safety and efficiency of intersection traffic. By using naturalistic driving data from the DAIR V2X-Seq dataset and general vehicle dynamic parameters, it is possible to obtain the joint-probability-density distribution of the bivariate dynamic parameters of a vehicle. This distribution represents the driving characteristics of vehicles in intersection traffic. The three vehicle dynamic parameters that have an impact on vehicles driving through the intersection area are velocity, angular velocity, and acceleration. The driving behavior characteristics of human-driven vehicles (HVs) and autonomous vehicles (AVs) were analyzed using the multivariate kernel density estimation (MKDE) method to establish the vehicle-behavior boundary. The assessment of the boundary model showed that it accurately characterizes the driving characteristics of HVs and AVs. This boundary can be used to improve the safety detection of intersection areas, enhancing the performance of autonomous vehicles and optimizing intersection traffic.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on the Vehicle-Behavior Boundary of Intersection Traffic Based on Naturalistic Driving Data Study

Wu,

Ma,

Zhu

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Because it is difcult to determine the weights of the four parts in the car-to-TW vehicle scenarios with traditional methods, fuzzy synthetic evaluation was used [23], which involved four steps that are described as follows.…”

Section: Clustering Variable Weightsmentioning

confidence: 99%

Research and Deduction of Car-to-TW Vehicle AEB Test Scenarios Based on Improved Clustering Methods

Dong,

Zhang,

Zhang

et al. 2023

Journal of Advanced Transportation

View full text Add to dashboard Cite

Two-wheeled (TW) vehicle accidents are one of the major types of urban traffic accidents. TW cyclists who lack safety protection usually suffer more serious injuries and deaths in collisions. Developments in automotive active safety technologies are expected to reduce cyclist injuries and deaths, such as automatic emergency braking (AEB). To facilitate the development and testing of AEB technology, typical TW vehicle scenarios need to be constructed. Based on 400 cases of car-to-TW vehicle accident data from the National Automobile Accident In-Depth Investigation System (NAIS) database, we investigated the scenario elements that influence AEB robustness, such as weather, accident time, and road wetness. We obtained seven static scenarios using an improved clustering method, and we obtained specific speed and distance combinations in each scenario using a deduction method. Further, we compared the present findings to those of other scholars and the China New Car Assessment Program (C-NCAP). The kinematic states of the two were similar to that of C-NCAP, but the speed distribution was significantly different. The TW vehicle speed in the C-NCAP is set to 15 km/h or 20 km/h concerning the European test scenarios, but the TW vehicle speed in the present study was 10–60 km/h. Thus, the present findings recommended that subsequent C-NCAP test scenarios increase the category of motorcycles and the speed range of cars covering 20–70 km/h and consider the test conditions of bad weather and wet roads, to test the robustness of AEB.

show abstract

“…This was leveraged to assist in the development and testing of various functions in intelligent connected vehicles. Sun et al [20] identified dangerous scenarios from NDD by setting thresholds for parameters such as speed and acceleration. Wachenfeld et al [21] introduced a dangerous scenario extraction method based on the worst-case collision time.…”

Section: Introductionmentioning

confidence: 99%

Testing Scenario Identification for Automated Vehicles Based on Deep Unsupervised Learning

Liu,

Ren,

et al. 2023

WEVJ

View full text Add to dashboard Cite

Naturalistic driving data (NDD) are valuable for testing autonomous driving systems under various driving conditions. Automatically identifying scenes from high-dimensional and unlabeled NDD remains a challenging task. This paper presents a novel approach for automatically identifying test scenarios for autonomous driving through deep unsupervised learning. Firstly, US DAS2 NDD are leveraged, and the selection of data variables representing the vehicle state and surrounding environment is conducted to formulate the segmentation criterion. The isolation forest (IF) algorithm is then employed to segment the data, yielding two distinct types of datasets: typical scenarios and extreme scenarios. Secondly, a one-dimensional residual convolutional autoencoder (1D-RCAE) is developed to extract scenario features from the two datasets. Compared to four other autoencoders, the 1D-RCAE can effectively extract crucial information from high-dimensional data with optimal feature extraction capability. Next, considering the varying importance of different features, an information entropy (IE)-optimized K-means algorithm is employed to cluster the features extracted using 1D-RCAE. Finally, statistical analysis is performed on the parameters of each cluster of scenarios to explore their distribution characteristics within each class, and four typical scenarios are identified along with five extreme scenarios. The proposed unsupervised framework, combining IF, 1D-RCAE, and IE-improved K-means algorithms, can automatically identify typical and extreme scenarios from NDD. These identified scenarios can then be applied to test the performance of autonomous driving systems, enriching the library of automated driving test scenarios.

show abstract

Automatic detection method research of incidents in China-FOT database

Cited by 7 publications

References 6 publications

Research on the Vehicle-Behavior Boundary of Intersection Traffic Based on Naturalistic Driving Data Study

Research on the Vehicle-Behavior Boundary of Intersection Traffic Based on Naturalistic Driving Data Study

Research and Deduction of Car-to-TW Vehicle AEB Test Scenarios Based on Improved Clustering Methods

Testing Scenario Identification for Automated Vehicles Based on Deep Unsupervised Learning

Contact Info

Product

Resources

About