scholarly journals Speed Distribution Prediction of Freight Vehicles on Mountainous Freeway Using Deep Learning Methods

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Yuren Chen ◽  
Yu Chen ◽  
Bo Yu
Keyword(s):  
Deep Learning ◽  
Regression Models ◽  
Safety Evaluation ◽  
Learning Method ◽  
The Road ◽  
Speed Distribution ◽  
Driving Speed ◽  
Road Geometry ◽  
Speed Prediction ◽  
Freight Vehicles

Driving speed is one of the most critical indicators in safety evaluation and network monitoring in freight transportation. Speed prediction model serves as the most efficient method to obtain the data of driving speed. Current speed prediction models mostly focus on operating speed, which is hard to reveal the overall condition of driving speed on the road section. Meanwhile, the models were mostly developed based on the regression method, which is inconsistent with natural driving process. Recurrent neural network (RNN) is a distinctive type of deep learning method to capture the temporary dependency in behavioral research. The aim of this paper is to apply the deep learning method to predict the general condition of driving speed in consideration of the road geometry and the temporal evolutions. 3D mobile mapping was applied to obtain road geometry information with high precision, and driving simulation experiment was then conducted with the help of the road geometry data. Driving speed was characterized by the bimodal Gauss mixture model. RNN and its variants including long short-term memory (LSTM) and RNN and gated recurrent units (GRUs) were utilized to predict speed distribution in a spatial-temporal dimension with KL divergence being the loss function. The result proved the applicability of the model in speed distribution prediction of freight vehicles, while LSTM holds the best performance with the length of input sequence being 400 m. The result can be related to the threshold of drivers’ information processing on mountainous freeway. Multiple linear regression models were constructed to be a contrast with the LSTM model, and the results showed that LSTM was superior to regression models in terms of the model accuracy and interpretability of the driving process and the formation of vehicle speed. This study may help to understand speed change behavior of freight vehicles on mountainous freeways, while providing the feasible method for safety evaluation or network efficiency analysis.

scholarly journals Speed Models for Motorcycle Riders for Two-lane Rural Roads

2021 ◽  
Vol 17 ◽  
pp. 595-603
Author(s):  
Panagiotis Lemonakis ◽  
George Botzoris ◽  
Athanasios Galanis ◽  
Nikolaos Eliou
Keyword(s):  
Prediction Models ◽  
Flow Speed ◽  
Operating Speed ◽  
Rural Roads ◽  
The Road ◽  
Horizontal Curves ◽  
Road Geometry ◽  
Speed Prediction ◽  
The Subject ◽  
On The Road

The development of operating speed models has been the subject of numerous research studies in the past. Most of them present models that aim to predict free-flow speed in conjunction with the road geometry at the curved road sections considering various geometric parameters e.g., radius, length, preceding tangent, deflection angle. The developed models seldomly take into account the operating speed profiles of motorcycle riders and hence no significant efforts have been put so far to associate the geometric characteristics of a road segment with the speed behavior of motorcycle riders. The dominance of 4-wheel vehicles on the road network led the researchers to focus explicitly on the development of speed prediction models for passenger cars, vans, pickups, and trucks. However, although the motorcycle fleet represents only a small proportion of the total traffic volume motorcycle riders are over-represented in traffic accidents especially those that occur on horizontal curves. Since operating speed has been thoroughly documented as the most significant precipitating factor of vehicular accidents, the study of motorcycle rider's speed behavior approaching horizontal curves is of paramount importance. The subject of the present paper is the development of speed prediction models for motorcycle riders traveling on two-lane rural roads. The model was the result of the execution of field measurements under naturalistic conditions with the use of an instrumented motorcycle conducted by experienced motorcycle riders under different lighting conditions. The implemented methodology to determine the most efficient model evaluates a series of road geometry parameters through a comprehensive literature review excluding those with an insignificant impact to the magnitude of the operating speeds in order to establish simple and handy models.

scholarly journals Road-Aware Trajectory Prediction for Autonomous Driving on Highways

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4703
Author(s):  
Yookhyun Yoon ◽  
Taeyeon Kim ◽  
Ho Lee ◽  
Jahnghyon Park
Keyword(s):  
Deep Learning ◽  
Autonomous Vehicles ◽  
Prediction Method ◽  
Autonomous Driving ◽  
Structural Constraints ◽  
High Definition ◽  
Trajectory Prediction ◽  
The Road ◽  
Road Geometry ◽  
Efficient Learning

For driving safely and comfortably, the long-term trajectory prediction of surrounding vehicles is essential for autonomous vehicles. For handling the uncertain nature of trajectory prediction, deep-learning-based approaches have been proposed previously. An on-road vehicle must obey road geometry, i.e., it should run within the constraint of the road shape. Herein, we present a novel road-aware trajectory prediction method which leverages the use of high-definition maps with a deep learning network. We developed a data-efficient learning framework for the trajectory prediction network in the curvilinear coordinate system of the road and a lane assignment for the surrounding vehicles. Then, we proposed a novel output-constrained sequence-to-sequence trajectory prediction network to incorporate the structural constraints of the road. Our method uses these structural constraints as prior knowledge for the prediction network. It is not only used as an input to the trajectory prediction network, but is also included in the constrained loss function of the maneuver recognition network. Accordingly, the proposed method can predict a feasible and realistic intention of the driver and trajectory. Our method has been evaluated using a real traffic dataset, and the results thus obtained show that it is data-efficient and can predict reasonable trajectories at merging sections.

Rainfall-integrated traffic speed prediction using deep learning method

2017 ◽  
Vol 11 (9) ◽  
pp. 531-536 ◽  
Author(s):  
Yuhan Jia ◽  
Jianping Wu ◽  
Moshe Ben-Akiva ◽  
Ravi Seshadri ◽  
Yiman Du
Keyword(s):  
Deep Learning ◽  
Learning Method ◽  
Speed Prediction ◽  
Traffic Speed

Research on Speed Limit of Two-Lane Highway of Mountain Area

2012 ◽  
Vol 178-181 ◽  
pp. 1904-1907
Author(s):  
Yu Heng Kan ◽  
Xin Qiu ◽  
Xiang Shen ◽  
Qing Yang ◽  
Le Yi Zhang
Keyword(s):  
Ride Comfort ◽  
Evaluation Model ◽  
Driving Safety ◽  
Maximum Speed ◽  
Estimation Model ◽  
Mountain Area ◽  
The Road ◽  
Driving Speed ◽  
Road Geometry ◽  
Limiting Condition

The paper investigates the effects of the road geometry parameters and the driver psychosocial reaction behaviors on driving safety of vehicles on the two-lane highway of mountain area. Firstly, the equivalent accident rate, P, is put forward as driving safety indicator, and the parameter sensitive analysis are performed between P and road geometry parameters including curve radius, slope and length, then the estimation model and evaluation criterion of P is established. Secondly, the psychosocial reaction behavior index, N, is provided as ride comfort indicator, and the evaluation model of N is established by relating N with road geometry parameters and driving speed. Finally, the two kinds of limiting condition including highest safety of the general bending, slope sections and lowest safety of the sharp curve, steep sections are present and the corresponding the driving speed is calculated. The analysis show that when V=35km/h in the most secure particular curved, the optimum driving safety and comfort can be achieved. As well, the maximum speed will be 10km/h in the lowest ones.

scholarly journals A Combined Deep Learning Method with Attention-Based LSTM Model for Short-Term Traffic Speed Forecasting

2020 ◽  
Vol 2020 ◽  
pp. 1-15 ◽  
Author(s):  
Pan Wu ◽  
Zilin Huang ◽  
Yuzhuang Pian ◽  
Lunhui Xu ◽  
Jinlong Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Data Preprocessing ◽  
Prediction Performance ◽  
Attention Mechanism ◽  
Learning Method ◽  
Short Term ◽  
Prediction Module ◽  
Speed Prediction ◽  
Traffic Speed

Short-term traffic speed prediction is a promising research topic in intelligent transportation systems (ITSs), which also plays an important role in the real-time decision-making of traffic control and guidance systems. However, the urban traffic speed has strong temporal, spatial correlation and the characteristic of complex nonlinearity and randomness, which makes it challenging to accurately and efficiently forecast short-term traffic speeds. We investigate the relevant literature and found that although most methods can achieve good prediction performance with the complete sample data, when there is a certain missing rate in the database, it is difficult to maintain accuracy with these methods. Recent studies have shown that deep learning methods, especially long short-term memory (LSTM) models, have good results in short-term traffic flow prediction. Furthermore, the attention mechanism can properly assign weights to distinguish the importance of traffic time sequences, thereby further improving the computational efficiency of the prediction model. Therefore, we propose a framework for short-term traffic speed prediction, including data preprocessing module and short-term traffic prediction module. In the data preprocessing module, the missing traffic data are repaired to provide a complete dataset for subsequent prediction. In the prediction module, a combined deep learning method that is an attention-based LSTM (ATT-LSTM) model for predicting short-term traffic speed on urban roads is proposed. The proposed framework was applied to the urban road network in Nanshan District, Shenzhen, Guangdong Province, China, with a 30-day traffic speed dataset (floating car data) used as the experimental sample. Results show that the proposed method outperforms other deep learning algorithms (such as recurrent neural network (RNN) and convolutional neural network (CNN)) in terms of both calculating efficiency and prediction accuracy. The attention mechanism can significantly reduce the error of the LSTM model (up to 12.4%) and improves the prediction performance.

Investigations of Road Wear Caused by Studded Tires

2014 ◽  
Vol 42 (1) ◽  
pp. 2-15
Author(s):  
Johannes Gültlinger ◽  
Frank Gauterin ◽  
Christian Brandau ◽  
Jan Schlittenhard ◽  
Burkhard Wies
Keyword(s):  
Traffic Safety ◽  
Test Bench ◽  
Operating Conditions ◽  
Test Method ◽  
Analytical Models ◽  
The Road ◽  
Driving Speed ◽  
Major Factors ◽  
Tire Friction ◽  
Variable Operating Conditions

ABSTRACT The use of studded tires has been a subject of controversy from the time they came into market. While studded tires contribute to traffic safety under severe winter conditions by increasing tire friction on icy roads, they also cause damage to the road surface when running on bare roads. Consequently, one of the main challenges in studded tire development is to reduce road wear while still ensuring a good grip on ice. Therefore, a research project was initiated to gain understanding about the mechanisms and influencing parameters involved in road wear by studded tires. A test method using the institute's internal drum test bench was developed. Furthermore, mechanisms causing road wear by studded tires were derived from basic analytical models. These mechanisms were used to identify the main parameters influencing road wear by studded tires. Using experimental results obtained with the test method developed, the expected influences were verified. Vehicle driving speed and stud mass were found to be major factors influencing road wear. This can be explained by the stud impact as a dominant mechanism. By means of the test method presented, quantified and comparable data for road wear caused by studded tires under controllable conditions can be obtained. The mechanisms allow predicting the influence of tire construction and variable operating conditions on road wear.

Sign in / Sign up

Export Citation Format

Share Document