原文传递
Adaptive Lane-Departure Prediction Method with Support Vector Machine and Gated Recurrent Unit Models
| 题名： | Adaptive Lane-Departure Prediction Method with Support Vector Machine and Gated Recurrent Unit Models |
| 正文语种： | eng |
| 作者： | Lie Guo;Zengke Qin;Pingshu Ge;Tianyi Gao |
| 作者单位： | School of Automotive Engineering Dalian Univ. of Technology Dalian 116024 China;School of Automotive Engineering Dalian Univ. of Technology Dalian 116024 China;College of Mechanical and Electronic Engineering Dalian Minzu Univ. Dalian 116600. China;College of Mechanical and Electronic Engineering Dalian Minzu Univ. Dalian 116600 China |
| 关键词： | Lane-departure prediction (LDP); Driver state; Gated recurrent unit (GRU); Trajectory prediction |
| 摘要： | Ignoring the driver's corrective actions is the main reason for false warnings in the lane-departure prediction method. We proposed a lane-departure prediction (LDP) method based on a support vector machine (SVM) and improved gated recurrent unit (GRU) models. The driver's visual distraction state was analyzed by using a radial basis function (RBF) based SVM model. The vehicle's lateral deviation was predicted by using a GRU model. The characteristic parameters of the GRU model were extracted from vehicle time series data using the time to lane crossing (TLC) model and the vehicle-road model. Considering that the farther the vehicle deviates from the lane centerline, the higher its deviation risk, a lateral deviation risk (LDR) loss function was proposed to improve the accuracy of the GRU model. By combining the SVM model and LDR-GRU model, the proposed LDP method can predict the future trajectory of the vehicle and adaptively adjust the safety boundary according to the driver's state. Naturalistic driving data from 52 drivers were collected to train and validate the adaptive LDP method. Finally, we compared the proposed LDR-GRU-SVM model with the TLC model, GRU model, LDR-GRU model, and GRU-SVM model. Experimental results show that the TLC model presents the highest false warning rate of 23.1% within a prediction time of 1s, while the proposed method is able to reduce the false warning rate to 1.2%. |
| 出版年： | 2022 |
| 期刊名称： | Journal of Transportation Engineering |
| 卷： | 148 |
| 期： | 11 |
| 页码： | 04022103.1-04022103.9 |
相关文献
- Floating Car Data-Based Short-Term Travel Time Forecasting with Deep Recurrent Neural Networks Incorporating Weather Data
- two-stage-training support vector machine approach to predicting unintentional vehicle lane departure
- Arterial corridor travel time prediction under non-recurring conditions
- Real-time multistep prediction of public parking spaces based on Fourier trans form-least squares support vector regression
- Meritor Wabco updates Toolbox diagnostics software
- Traffic speed prediction for intelligent transportation system based on a deep feature fusion model
检索历史
应用推荐
