Driver lane change intention recognition in the connected environment

Guo, Yingshi; Zhang, Hongjia; Chang, Wang; Sun, Qinyu; Li, Wanmin

doi:10.1016/j.physa.2021.126057

Cited by 43 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ghiasi et al [100] believed that intelligent networked vehicles may operate with smaller longitudinal and lateral spacing than traditional human driving vehicles (HVS), thanks to the developing technologies in rapid and accurate control and cooperative mobility. Additionally, narrower expressway lanes can be allocated to intelligent networked vehicles to increase traffic capacity.…”

Section: Optimization Methods Of Dedicated Lane-management Strategymentioning

confidence: 99%

A Survey on Mixed Traffic Flow Characteristics in Connected Vehicle Environments

Chang

Zhang²,

Li³

et al. 2022

Sustainability

Self Cite

View full text Add to dashboard Cite

Intelligent transportation has become a hot research field in recent years The development direction of road traffic construction in the future, the relevant technologies and methods in the process of gradual promotion and application of intelligent connected vehicles continue to attract the attention of scholars and engineers. There are more and more relevant theories, methods and systems. This paper summarizes the current state of microscopic and macroscopic traffic models, characteristic analysis methods of mixed traffic flow, and lane management methods in connected vehicle environments. At the end of this paper, the conclusions of this work are presented, and possible future directions for safety warning research under connected vehicle environments are discussed. This paper represents the current research status of traffic flow characteristics under connected vehicle environments to some extent, which can provide references for future traffic flow characteristic research in terms of framework, methods and technologies, etc.

show abstract

Section: Optimization Methods Of Dedicated Lane-management Strategymentioning

confidence: 99%

A Survey on Mixed Traffic Flow Characteristics in Connected Vehicle Environments

Chang

Zhang²,

Li³

et al. 2022

Sustainability

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, the construction of smart cities and the development of intelligent transportation systems require particular attention to traffic safety and traffic efficiency issues at intersections. The connected environment has received increasing attention [5]- [7] since the U.S. Department of Transportation and the Ministry of Science and Technology of the People's Republic of China launched their respective intelligent connected transportation environment projects, which emphasize traffic safety and traffic efficiency [8], [9]. Technological advances in sensors and communication have promoted the development of a connected traffic environment.…”

Section: A Motivations and Challengesmentioning

confidence: 99%

“…Before training the model, we need to smooth the data. Therefore, most of the computational cost of the proposed model is attributed to solving the convex optimization problem (9). According to W ∈ Z n×n , the computational complexity of solving (9) is O(n 3 ).…”

Section: Algorithm 1 Inverse Covariance Matrix Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Turning Maneuver Prediction of Connected Vehicles at Signalized Intersections: A Dictionary Learning-Based Approach

Zhang

Wang

et al. 2022

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

Vehicle-to-Infrastructure (V2I) communication has provided a solution for the improvement of the traffic efficiency of smart city intersections. For example, turning maneuvers prediction at signalized intersections in a connected environment helps traffic command centers time traffic lights and dynamically predict traffic flow. However, the modeling methods used in existing research on this topic have some limitations, such as poor scalability and interpretability of machine learning. Thus, this study proposes a dictionary learning-based approach to predict turning maneuvers before the intersection. The proposed dictionary model estimates the LogDet divergence-based sparse inverse covariance matrix (LDbSICM) of driving behavior samples. The graphical lasso method is used to estimate the sparse inverse covariance matrix of the driving samples to construct a dictionary library of the maneuver behavior. The LogDet divergence is used to calculate the difference between each inverse covariance matrix. A driving simulator is utilized to collect experimental data consisting of turning left (TL), turning right (TR), and going straight (GS) behaviors to establish and evaluate the proposed model. The experimental results demonstrate that the proposed dictionary learning-based turning maneuver prediction model achieves 100% prediction accuracy for TL and GS and 97.2% for TR. The proposed model has substantial advantages over existing methods. The model can predict TL, TR, and GS in a connected environment 270, 280, and 290 m, respectively, before the intersection.

show abstract

“…Therefore, some researchers have incorporated driver states, such as eye-movement features [ 23 ] and physiological features [ 24 ], to analyze driving behaviors. Guo et al [ 25 ] identified the driving intention to lane change using a bidirectional LSTM network based on an attention mechanism with vehicle kinematic data, driver maneuver data, driver eye-movement data, and head rotation data as input, and achieved an accuracy of 93.33% at 3 s prior to the lane change. However, the eye-movement data and physiological data are mostly collected in an intrusive manner, which can cause some interference with driving.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Xie

Chen

et al. 2021

IJERPH

View full text Add to dashboard Cite

Real-time driving behavior identification has a wide range of applications in monitoring driver states and predicting driving risks. In contrast to the traditional approaches that were mostly based on a single data source with poor identification capabilities, this paper innovatively integrates driver expression into driving behavior identification. First, 12-day online car-hailing driving data were collected in a non-intrusive manner. Then, with vehicle kinematic data and driver expression data as inputs, a stacked Long Short-Term Memory (S-LSTM) network was constructed to identify five kinds of driving behaviors, namely, lane keeping, acceleration, deceleration, turning, and lane changing. The Artificial Neural Network (ANN) and XGBoost algorithms were also employed as a comparison. Additionally, ten sliding time windows of different lengths were introduced to generate driving behavior identification samples. The results show that, using all sources of data yields better results than using the kinematic data only, with the average F1 value improved by 0.041, while the S-LSTM algorithm is better than the ANN and XGBoost algorithms. Furthermore, the optimal time window length is 3.5 s, with an average F1 of 0.877. This study provides an effective method for real-time driving behavior identification, and thereby supports the driving pattern analysis and Advanced Driving Assistance System.

show abstract

Driver lane change intention recognition in the connected environment

Cited by 43 publications

References 33 publications

A Survey on Mixed Traffic Flow Characteristics in Connected Vehicle Environments

A Survey on Mixed Traffic Flow Characteristics in Connected Vehicle Environments

Turning Maneuver Prediction of Connected Vehicles at Signalized Intersections: A Dictionary Learning-Based Approach

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Contact Info

Product

Resources

About