Driver Lane-Changing Behavior Prediction Based on Deep Learning

Wei, Cheng; Hui, Fei; Khattak, Asad J.

doi:10.1155/2021/6676092

Cited by 13 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [35] proposed a joint IRL-DL framework to predict drivers' future behavior in ride-hailing platforms, achieving consistent and remarkable improvements over models without drivers' preference vectors. Wei et al [36] proposed a hybrid neural network prediction model based on RNN and a fully connected neural network (FC) to accurately predict lane-changing behavior in real traffic scenarios. The proposed model achieved a prediction accuracy of 93.5% and improved the prospective time of prediction by about 2.1s on average.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Model for Driver Behavior Detection in Cyber-Physical System-Based Intelligent Transport Systems

Gupta,

Gaurav,

Tai Chui

et al. 2024

IEEE Access

View full text Add to dashboard Cite

As Intelligent Transport Systems (ITS) continue to evolve, the quest for improving road safety and transportation efficiency has gained renewed emphasis.One of the pivotal aspects in this endeavor is the detection and analysis of driver behavior. Recognizing signs of fatigue, distraction, or inattentiveness is critical in enhancing road safety and optimizing traffic flow. In this paper, we present a pioneering approach to driver behavior detection within the realm of ITS using deep learning models in the Cyber-Physical Systems (CPS) framework. Our research focuses on the discernment of critical behaviors such as eye closure, open-eye state, yawning, and non-yawning instances. With an unwavering commitment to road safety and transportation efficiency, we've harnessed the power of deep learning to design, develop, and train an exceptionally accurate model. Through rigorous evaluation, we achieved an impressive 94% accuracy. Our findings unveil the potential of CPS-based solutions for real-time driver behavior monitoring, providing a foundation for safer roadways and more streamlined traffic management. The proposed deep learning model offers robust and accurate predictions, enabling timely responses to various driving conditions. This research significantly advances the field of driver behavior analysis within the context of intelligent transportation systems, with broad implications for road safety and traffic management.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning Model for Driver Behavior Detection in Cyber-Physical System-Based Intelligent Transport Systems

Gupta,

Gaurav,

Tai Chui

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Relevant scholars have carried out a large number of explorations using to construct driving behavior models and achieved good results. For example, Li et al [31] and Wei et al [93] used RNN to predict lane change behavior, and the accuracy reached 96% and 93.5%, respectively. EdDoughmi et al [32] identified fatigued driving behaviors by inputting the collected video stream data of drivers' faces into the 3D-RNN model established, with an accuracy of 92%.…”

Section: Recurrent Neuralmentioning

confidence: 99%

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

Zhao

Zhong

Zhi-jun

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

The frequent traffic accidents lead to a large number of casualties and large related financial losses every year; this serious state is owed to several factors; among those, driving behavior is one of the most imperative subjects to discuss. Driving behaviors mainly include behavior characteristics such as car-following, lane change, and risky driving behavior such as distraction, fatigue, or aggressive driving, which are of great help to various tasks in traffic engineering. An accurate and reliable method of driving behavior recognition is of great significance and guidance for vehicle driving safety. In this paper, the vehicle multisensor information, vehicle CAN bus data acquisition system, and typical feature extraction methods are summarized at first. And then, several driving behavior recognition models based on machine learning and deep learning are reviewed. Through a detailed analysis of the features of random forests, support vector machines, convolutional neural networks, and recurrent neural networks used to build driving behavior recognition models, the following findings are obtained: the driving behavior model constructed by traditional machine learning model is relatively mature but it is greatly affected by feature extraction, data scale, and model structure, which affects the accuracy of the final driving behavior recognition. Deep learning model based on a neural network has achieved high accuracy in identifying driving behavior, and it may gradually become the mainstream of constructing the driving behavior model with the development of big data, artificial intelligence technology, and computer hardware. Finally, this paper points out some content that needs to be further explored, to provide reference and inspiration for scholars in this field to continue to study the driving behavior recognition model in depth.

show abstract

“…The prediction of the surrounding environment by the intelligent driving system has always been a difficulty in the industry, especially in the intelligence of the bicycle. Because the field of vision of the sensor is blocked by the surrounding vehicles and other things, its detection range is limited, so the vehicle can get less environmental information, and the difficulty of prediction is further increased [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

Support Vector Machine Based Lane-Changing Behavior Recognition and Lateral Trajectory Prediction

Feng

Yan

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of technology, vehicle trajectory prediction and safety decision technology has become an important part of active safety technology. Among them, the vehicle trajectory prediction technology can predict the vehicle position, speed, and other motion states in the predicted period according to the current and historical vehicle running state, and the prediction results can provide support for judging the vehicle safety in the predicted period. In order to analyze the above problems, this study fully extracted the main feature information from the vehicle lane change track data with the help of the powerful nonlinear learning and high pattern recognition ability of support vector machine, and conducted identification modeling for the actual lane change process of the vehicle and predictive analysis of the vehicle lateral movement track. First, the lane-changing behavior of vehicles was analyzed, and the vehicle lane-changing execution stage and 10 influencing factors that could characterize lane-changing behavior were determined based on NGSIM to extract the data of lane-change-related variables. Then, a lane-changing recognition model based on gridsearch-PSO is proposed. In the Matlab environment, the model has a test accuracy of 97.68%, while the SVM model without optimization parameters has a recognition accuracy of only 80.87%. The results show that the model has strong classification ability and robustness. Finally, by using the polynomial model for lateral movement trajectory fitting, K-fold cross-validation method is used for fitting polynomial model fitting test.

show abstract

Driver Lane-Changing Behavior Prediction Based on Deep Learning

Cited by 13 publications

References 35 publications

Deep Learning Model for Driver Behavior Detection in Cyber-Physical System-Based Intelligent Transport Systems

Deep Learning Model for Driver Behavior Detection in Cyber-Physical System-Based Intelligent Transport Systems

A Review for the Driving Behavior Recognition Methods Based on Vehicle Multisensor Information

Support Vector Machine Based Lane-Changing Behavior Recognition and Lateral Trajectory Prediction

Contact Info

Product

Resources

About