No abstract

No abstract

No abstract

In-vehicle traffic lights (IVTLs) have been identified as a potential means of eco-driving. However, the extent to which they influence driving characteristics in the event of obstructed on-road traffic lights (ORTLs) has yet to be fully examined. Firstly, the situation of partially deployed IVTLs in both vehicles was analyzed to identify the factors that affect driving characteristics. Through the following distance model, relative vehicle speed, acceleration and deceleration, and following distance were recognized as the contributing factors. The evaluation indicators for driving characteristics were thereby further established. Then, a hardware-in-the-loop simulation platform was built using PreScan-MATLAB/Simulink joint simulation software and a Logitech G29 device. IVTLs were implemented using modules in the joint simulation software. Finally, under the scenarios of obstructed ORTLs and various deployment conditions of IVTLs, the original data were collected from 50 experimental subjects with simulated driving. The subjects included 25 males and 25 females, all of whom were non-professional drivers, with ages ranging from 20 to 40 years old. The conclusion was reached that IVTLs could improve driving comfort by approximately 10% in sunny weather (p = 0.008 < 0.05, p = 0.023 < 0.05; p = 0.046 < 0.05, p = 0.001 < 0.05), driving maneuverability by approximately 30% in foggy weather (p = 0.033 < 0.05), and driving safety by approximately 50% in the ORTLs obstructed by a truck scenario (p = 0.019 < 0.05). In general, even if only one vehicle was equipped with IVTLs, certain gain effects on the driving characteristics of both vehicles could still be provided.

The economy and safety of passages through the urban road intersection environment is an important research topic in the field of intelligent transportation systems, but vehicle speed prediction as its subtopic is still under-researched, and its prediction accuracy is unsatisfactory. Therefore, a model for vehicle speed prediction based on the nonlinear autoregressive model with multisource exogenous inputs (NARXs) neural network is proposed. The model combines the human-vehicle-road model with the NARXs neural network to perform speed prediction between urban road intersections. First, multisource features, including the variables of driving behavior characteristics, vehicle responses, and road conditions, are extracted to construct the human-vehicle-road model. Then, the model is introduced into the NARXs neural network. Finally, the advantages of the proposed model are verified from two perspectives by evaluation indices such as mean absolute error ( MAE), mean absolute percentage error ( MAPE), root mean square error ( RMSE), Theil index ( Theil ic), and goodness-of-fit ( R2) compared with several other models. On the one hand, the analysis results show that the proposed model has higher prediction accuracy than the other comparative models for different prediction durations and has the best performance in 30 s duration backward prediction. On the other hand, the curves of each evaluation index of the proposed model are horizontal, which indicates that the prediction performance of the model hardly varies with the length of the training dataset. These positive results demonstrate the higher accuracy and outstanding characteristics of the proposed model in the subject of vehicle speed prediction.