International Journal of Intelligent Transportation Systems Research

Based on the analysis of the field traffic flow time series, we found that there is self-similarity and periodic similarity in the traffic flow of different observation scales, which makes the short-term traffic flow prediction a meaningful work. For the purpose of finding the smallest prediction cycle, fractal analysis was conducted in the relation between the observation scale and the prediction cycle by using both the field data and the simulated data. We calculate the fractal dimension and the scaling region of traffic flow time series by using the G-P algorithm. If the scaling region can be found in the traffic flow time series at some observation scale, it means that there is self-similarity in the time series at that observation scale. The minimum observation scale at which there is self-similarity in the traffic flow is the smallest prediction cycle. This observation scale is a prerequisite for judging whether the traffic flow can be predicted or not. This research provides a reference for the short-term traffic flow prediction on expressway and urban road.

Driving error is one of the crucial contributing factors to the increasing number of traffic deaths all over the world. Both external and internal stimuli significantly affect the driving performance of individuals, irrespective of their mild, moderate, or aggressive driving styles. Continued research is being performed to increase the efficiency of vehicle safety systems and improvise existing autonomous and semi-autonomous vehicles. This paper reviews the existing state-of-the-art technologies for different types of abnormal driving detection. The review is categorized into three sections i.e., abnormal driving detection using i) vehicular features, ii) physiological features, and iii) hybrid features. Various approaches have been compared for abnormal driving detection and areas for improvement are distilled. The research gaps identified lie in the lack of i) consideration of environmental data, ii) non-invasive physiological data, and iii) comparative studies among different types of driving abnormalities.

Station-type one-way carsharing systems (OWCS) using electric vehicles (EV) are expected to equip all dedicated stations with chargers to prevent opportunity loss caused by a drivable-distance shortage. However, it is not cost-efficient for an OWCS operator to install chargers at all stations. Therefore, they need a method for finding the optimal stations to be equipped with chargers while also staying within their budget limit. We propose a search method that evaluates the result of a two-step simulation that accounts for state transition. As a case study using practical operational data for Tokyo, we searched for candidate stations to be augmented by chargers.

In this paper, a Real-Time Monte Carlo Localization (RT_MCL) method for autonomous cars is proposed. Unlike the other localization approaches, the balanced treatment of both pose estimation accuracy and its real-time performance is the main contribution. The RT_MCL method is based on the fusion of lidar and radar measurement data for object detection, a pole-like landmarks probabilistic map, and a tailored particle filter for pose estimation. The lidar and radar are fused using the Unscented Kalman Filter (UKF) to provide pole-like static-objects pose estimations that are well suited to serve as landmarks for vehicle localization in urban environments. These pose estimations are then clustered using the Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) algorithm to represent each pole landmarks in the form of a source-point model to reduce computational cost and memory requirements. A reference map that includes pole landmarks is generated off-line and extracted from a 3-D lidar to be used by a carefully designed Particle Filter (PF) for accurate ego-car localization. The particle filter is initialized by the fused GPS + IMU measurements and used an ego-car motion model to predict the states of the particles. The data association between the estimated landmarks by the UKF and that in the reference map is performed using Iterative Closest Point (ICP) algorithm. The RT_MCL is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Extensive simulation studies have been carried out to evaluate the performance of the RT_MCL in both longitudinal and lateral localization. The RT_MCL was able to estimate the ego-car pose with an 11-cm mean error in real-time.

This study proposes a statistical approach to incident detection in a section of the intercity freeway by applying GPS probe data to a GIS geofenced platform. We evaluated the proposed method using data sources from real traffic sensors of the intercity Tehran-Qom freeway in Iran. Through the SEPEHTAN project in Iran, intercity bus fleet equipped with an onboard unit that provides GPS data transferring to the central database. The main novelties in this paper are gathering density and speed time series from GPS probe data in a GIS platform and using autocorrelation factor to detect the location of the incident. The method compared with three different AID algorithms and real terms as well. Although the penetration rate was 3%, the results were considerably meet with the actual traffic condition. We reached 92.8% detection rate and 7.1% for the false alarm.

Real-Time Kinematic (RTK) positioning is a precise positioning method, which is expected to support self-driving. However, it is known that the availability of RTK highly depends on the Global Navigation Satellite System (GNSS) signal environment, which is influenced by buildings and viaduct of tunnel. Before driving, it is convenience if we can simulate the GNSS signal environment using a three-dimensional (3D) map and predict the availability of RTK. It is also important to know the limitation of RTK for other sensors. Therefore, we predicted it using machine learning based on the past test-driving and simulated signal environment datasets. The prediction accuracy was almost 65–80% from two evaluation tests in Tokyo and we found several new issues to consider for RTK availability prediction.

The demand for prior planning of travel chains and more available information during the journey is induced by the passengers’ growing requirements. Many journey planners are already available on the internet, but these often provide only partially comprehensive solutions and are difficult to be compared. For analysis and evaluation of the multimodal journey planners a framework of aspects has been developed, so that they can be compared in a quantitative way and ranked by functional, operational and visualization features. In the course of comparison some top features of the planners have been highlighted, too. Furthermore, development directions were determined, which are the following: multimodality, real-time data, location-based services and personalized recommendations for all transport modes. Hence the journey planners can be ordered into service levels.

Evaluating the safety of different traffic facilities is a complex and crucial task. Microscopic simulation models have been widely used for traffic management but have been largely neglected in traffic safety studies. Micro-simulation to study safety is more ethical and accessible than the traditional safety studies, which only assess historical crash data. However, current microscopic models are unable to mimic unsafe driver behavior, as they are based on presumptions of safe driver behavior. This highlights the need for a critical examination of the current microscopic models to determine which components and parameters have an effect on safety indicator reproduction. The question then arises whether these safety indicators are valid indicators of traffic safety. The safety indicators were therefore selected and tested for straight motorway segments in Brisbane, Australia. This test examined the capability of a micro-simulation model and presents a better understanding of micro-simulation models and how such models, in particular car following models can be enriched to present more accurate safety indicators.