Modelling heavy vehicle car‐following behaviour in congested traffic conditions

Aghabayk, Kayvan; Sarvi, Majid; Forouzideh, Nafiseh; Young, William

doi:10.1002/atr.1242

Cited by 33 publications

(10 citation statements)

References 22 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher ACG percent would waste vehicle energy directly. As shown in (17) to (19), ACG percent is defined as two aspects: (1) drivers pressed the acceleration pedal but the gear is zero or (2) acceleration pedal is pressed and the pedal travel of clutch is equal to or more than 2/3 at the same time.…”

Section: ) Standard Deviation Of Acceleration Pedal Applying Value (mentioning

confidence: 99%

“…Hence, aiming at reliability prediction and evaluation, the method based on artificial neural network would be better. Among these artificial neural networks, backpropagation (BP) neural network is the most commonly used, especially in practical application [17,18]. Moreover, BP network has apparent advantages in self-learning, selforganizing, good fault tolerance, and excellent nonlinear approximation ability [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Ecolevel Estimation Method of Individual Driver Performance Based on Driving Simulator Experiment

Zhao

Rong

2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Accurately acquiring the ecolevel of individual driver performance is the precondition for more targeted ecodriving behavior optimization. Because of obvious advantage in mining hidden relationship, machine learning was adopted to explore the complicated relationship between driver performance and vehicle fuel consumption and thus to predict the ecolevel of individual driver performance in this study. Based on driving simulator tests, data of driver performance and vehicle fuel consumption were collected. The ecolevel was indicated as the ecoscore corresponding to vehicle fuel consumption. The model input was designed as 10 feature indexes of driver performance (e.g., percentage number, mean value, standard deviation, and power of applying acceleration pedal). The output was treated as ecoscore. Taking a number of one hundred of data segments in vehicle starting process as training sample, the optimal structure, functions, and learning rate of a backpropagation neural network model with three layers were obtained, after repeated model simulation experiments. The validation test of 16 sample data items showed that the mean prediction accuracy of our developed model was 92.89%. In addition, comparative analysis displayed that the performance of backpropagation neural network based model was better than linear regression based model and random forest based model, from the aspects of elapsed time and prediction accuracy in estimating the ecolevel of driver performance. The study results provide an effective method to grasp the ecolevel of driver performance and further contribute to driving behavior optimization towards vehicle fuel consumption and emissions reduction.

show abstract

Section: ) Standard Deviation Of Acceleration Pedal Applying Value (mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Ecolevel Estimation Method of Individual Driver Performance Based on Driving Simulator Experiment

Zhao

Rong

2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Many specialized studies have investigated the road running characteristics attributable to large vehicles. Related research mainly analyzed the bottleneck effect of large vehicles from the microscopic theory and obtained some generally accepted conclusions [4][5][6][7][8][9][10][11]. In 1992, Gazis and Herman [4] proposed a mobile bottleneck concept for vehicle queuing caused by slow vehicles on low-speed roads and proposed a mobile bottleneck model for symmetric lane changing in two-lane highways.…”

Section: Introductionmentioning

confidence: 99%

“…At a sufficiently high truck mixing rate, the traffic speed approaches a certain fixed speed, which is related to the expected speed of the truck. Some scholars have studied the dynamics of heavy vehicle interactions in car following [8][9][10][11][12]. By simulating the behavior of following in the congested traffic conditions and the lane changing operation of heavy vehicles, it was found that the existence of heavy vehicles will lead to larger space and time headways, longer reaction time, and more robust car-following behavior.…”

Section: Introductionmentioning

confidence: 99%

Influence of Large Vehicles on the Speed of Expressway Traffic Flow

Gao

Jia

et al. 2020

Advances in Civil Engineering

View full text Add to dashboard Cite

Large vehicles impact the quality of traffic flow. To predict the impact of large-scale vehicles on the average speed of traffic flow, vehicle speeds under different vehicle mixing rates were collected through field observations. A laser roadside traffic survey instrument with automatic vehicle type identification functionality was used to collect cross section traffic flow data. The v/C ratio, large vehicle mixing rate, and average speed of traffic were calculated for each data set. A total of 158 traffic flow data sets were captured and divided into three groups according to the v/C ratio of the expressway. The v/C ratio ranges of the three groups are v/C≤0.35, 0.35<v/C≤0.55, and 0.55<v/C≤0.90. SPSS software was used to analyze the correlation between the vehicle mixing rate and the average speed under different traffic flow conditions, and a model was determined between the average speed of the vehicle flow and the large vehicle mixing rate. Analysis of the results with SPSS revealed a negative logarithmic linear relationship between the average traffic speed and the mixing rate of large vehicles. The results could also be applied to passenger cars. The models are considered as corrections of the average speed of the traffic flow after the mixing of large vehicles. When the mixing rate of large vehicles is close to zero, the forecast value of the model is the average speed of passenger cars. Furthermore, as the traffic volume of the road section increased, the influence of the mixing rate on traffic flow speed became more obvious. The adaptability of the proposed prediction model of the expressway mixing rate was verified by evaluating model predictions against actual measurements.

show abstract

“…The findings of his research show the complication of acceleration/deceleration of heavy freight vehicles causes larger space and time headways when traffic flow approaches capacity. Besides, heavy freight vehicles intend to keep a stable speed when following and the reaction time of different drivers' changes less obviously [21]. Yang et al [22] used cellular automation to simulate the car-following behaviors of heavy freight vehicles when following passenger cars, which indicates that car-following behaviors between heavy freight vehicles and passenger cars will exert different impact on traffic capacity if traffic flow state changes.…”

Section: Introductionmentioning

confidence: 99%

An extended car-following model considering the influence of bus

Shen

Qiu

et al. 2017

Teh. vjesn.

View full text Add to dashboard Cite

Original scientific paper In order to describe car-following behaviour of traffic flow which is composed of buses and passenger cars on freeway, an extended car-following model is proposed for single lane traffic in this paper. The proposed model discriminates four types of car-bus following combination, car-following-bus, busfollowing-bus, bus-following-car and car-following-car. The four combinations are considered in terms of following distance, following speed and following acceleration/deceleration. The proposed methodology is demonstrated using data collected from the combination of microwave radar detector and roadside laser detector on Xuanwu Avenue in the main urban area of Nanjing. Besides, the field data is divided into two data sets, one used for the training of the model, and the other for evaluation purpose. Gazis model and Edie model, the two most extensively used car-following models, are calibrated against the same training data sets and used as a reference benchmark. Finally, the performance of the model, proposed by this paper, was compared with the two classic models based on the evaluation data sets. The results show that buses have different characteristics and manoeuvrability compared with passenger cars. With the influence of buses in the car-following process, it could lead to uneven distribution of traffic flow on the lanes and become the main reason for traffic highway capacity decline. The model, proposed in this paper, is more accurate and stable when predicting acceleration/deceleration of different vehicles during car-following. It has better superiority to describe the car-following behaviours under the influence of bus on freeway. Keywords: bus; car-following model; model calibration; stimulus-response process; traffic flow Prošireni model kolone vozila koji uzima u obzir utjecaj autobusaIzvorni znanstveni članak Kako bi se opisalo ponašanje prometa kolone vozila, koja se sastoji od autobusa i osobnih automobila na autocesti, u ovom članku je predložen prošireni model kolone vozila za promet u jednoj traci. Predloženi model razlikuje četiri vrste kombinacija kolona automobil-autobus, automobil-nakon-autobusa, autobus-nakon-autobusa, autobus-nakon-automobila i automobil-nakon-automobila. Četiri kombinacije uzimaju u obzir udaljenost, brzinu i ubrzavanje/usporavanje kolone. Predložena metodologija je prikazana uporabom podataka prikupljenih kombinacijom mikrovalnog radarskog detektora i cestovnog laserskog detektora na aveniji Xuanwu u glavnom urbanom području Nanjinga. Osim toga, podaci o terenu podijeljeni su u dva seta podataka, jedan se koristi za uvježbavanje modela, a drugi je za ocjenu. Gazis model i Edie model, dva najčešće korištena modela kolone vozila, kalibrirani su prema istim skupovima podataka za vježbu, a koriste se kao referentna vrijednost. Konačno, izvedba modela, predložena ovim radom, uspoređena je s dva klasična modela na temelju evaluacijskih skupova podataka. Rezultati pokazuju da autobusi imaju različite karakteristike i manevriranost u usporedbi s osobnim ...

show abstract

Modelling heavy vehicle car‐following behaviour in congested traffic conditions

Cited by 33 publications

References 22 publications

An Ecolevel Estimation Method of Individual Driver Performance Based on Driving Simulator Experiment

An Ecolevel Estimation Method of Individual Driver Performance Based on Driving Simulator Experiment

Influence of Large Vehicles on the Speed of Expressway Traffic Flow

An extended car-following model considering the influence of bus

Contact Info

Product

Resources

About