Tokyo Metropolitan Expressway Research Articles

A deep reinforcement learning-based intelligent intervention framework for real-time proactive road safety management

We propose a variable speed limit (VSL) system for improving the safety of urban expressways in real time. The system has two main functions: monitoring traffic data and then using the data to assess crash risk through a real-time crash prediction model (RTCPM). When the risk is high, the system triggers VSL control to restore traffic conditions to normal. The study addresses several weaknesses in existing VSL-based real-time safety interventions. Existing models are not widely applicable due to varying detector spacing among different freeways, and even within a study area. Therefore, with the existing detector spacing as an input, a cell transmission model (CTM) is used to simulate traffic states for the desired cell size. A dynamic Bayesian network (DBN) is used for modeling in the RTCPM. The proposed CTM model is then modified to allow VSL control. Whereas existing studies selected various VSL strategies from a predefined list, we employ a deep Q-network, which is a reinforcement learning-based machine learning algorithm, for the VSL control. Two busy segments of the Tokyo Metropolitan Expressway were used as the study area. After several iterations, our proposed real-time system reduced the crash risk by 19%.

Viaduct maintenance for future traffic demands and earthquakes

The Tokyo Metropolitan Expressway in Japan has been in operation for more than half a century. Recently, serious damages in the network have been reported in many of the old routes. However, the Metropolitan Expressway has little-to-no of experience in managing such a situation so far. Thus, developing an appropriate management strategy focusing on maintenance is critical to the expressway. The emphasis of this study is placed on the maintenance improvement of steel viaducts, and the project aims to evaluate their marginal maintenance cost and identify the influences on the cost from uncertainties such as earthquakes and future traffic demand from an econometric perspective. The study reveals that the traffic volume of passenger cars can be identified as a significant factor, while the effect of earthquake events on the cost is not clearly pronounced. Based on the analyses, it is found that the current maintenance approach is capable of dealing with fluctuations in traffic volume, which is the most influential factor. Furthermore, an increase in the amount of maintenance works could possibly lower the maintenance costs due to economies of scale. The results also indicate that the efficiency of the current maintenance method could be improved.

An Analysis of the Actual Fluctuation of Drivers’ Route Choice on the Tokyo Metropolitan Expressway Network

An Analysis of the Actual Fluctuation of Drivers’ Route Choice on the Tokyo Metropolitan Expressway Network

Spatial patterns of throughputs of road network: A preliminary result of Tokyo Metropolitan Expressway data

Spatial patterns of throughputs of road network: A preliminary result of Tokyo Metropolitan Expressway data

STABILITY OF TRAFFIC CONGESTION PATTERNS AND MACROSCOPIC FUNDAMENTAL DIAGRAMS IN TOKYO METROPOLITAN EXPRESSWAY NETWORK

STABILITY OF TRAFFIC CONGESTION PATTERNS AND MACROSCOPIC FUNDAMENTAL DIAGRAMS IN TOKYO METROPOLITAN EXPRESSWAY NETWORK

Effects of the change of toll system on social surplus: A case study of distance-based toll in Tokyo Metropolitan Expressway

Abstract We examines the effects of the change of toll system on the economic efficiency, focusing on a case of Tokyo Metropolitan Expressway, i.e., Shutoko, whose toll system had shifted from flat toll to distance-based toll. Drivers using the parallel general road are considered, and they are to pay the fuel tax to the government. We calculated the social surplus comprised of the consumers’ surplus and the producers’ surplus among both the highway company and the government. Furthermore, it is shown that the Ramsey pricing rule could increase the social surplus while toll receipts of the highway company being unchanged.

Effects of Change in Toll Systems on Social Surplus: A Case Study of Distance-based Tolls on Tokyo Metropolitan Expressway

Effects of Change in Toll Systems on Social Surplus: A Case Study of Distance-based Tolls on Tokyo Metropolitan Expressway

Identification of Factors that May Affect the Discharge Flow at a Bottleneck

This study investigates various factors that cause the reduction of discharge flow at a bottleneck on an urban expressway. The current worst bottleneck on Tokyo Metropolitan Expressway Network seems to be combined complicate factors that affect the discharge flow at the bottleneck. 5 causing factors, merging ratio, longitudinal gradient, duration time involved in congestion, environment of backlight and brightness are considered, and the impact of these 5 causing factors are investigated. Then the results supported the hypothesis that all of the 5 causing factors affect the discharge flow rate.

Construction of an entrance/exit for an underground expresswayon Tokyo Metropolitan Expressway by the open-cut tunnel construction method

Construction of an entrance/exit for an underground expresswayon Tokyo Metropolitan Expressway by the open-cut tunnel construction method

Analyses of Route Choice and Route Switching Behavior Using ETC data from Tokyo Metropolitan Expressway

The analyses of route choice behavior based on revealed preference (RP) data are rare because of the difficulty of observing route choice decisions in practice. On Tokyo metropolitan expressway, traffic surveillance and electronic toll collection (ETC) systems provide rich sources of traffic condition and behavior data. This paper analyzes route choice and route switching behavior using the observed route choice decisions collected from ETC data in the selected study area. Moreover, the paper identifies and evaluates the importance of attributes relating to traffic condition information and drivers’ traveling characteristics derived from both ETC and detector data.

Analysis of the Lane-Change Behavior at Lane Closure by Driving Simulation Experiment

To mitigate the traffic congestion at merging sections in urban expressway networks, a dynamic lane operation is being studied in Japan, which dynamically switches one lane to either approach of a merging section with more traffic demand. To evaluate the safety concern, the lane-change behavior when one lane is closed by variable barrier which is informed by variable message sign (VMS) is analyzed in this study. A driving simulation experiment is conducted for the analysis considering the implementation of the dynamic lane operation for merging sections at Route C1 of Tokyo Metropolitan Expressway. Traffic condition and the distance between a lane-closure point and the VMS are considered as critical factors affecting the risky behavior, and their influence on the lane change behavior is studied.

Analysis of Route Choice and Route Switching Behavior Using Panel ETC Data from the Tokyo Metropolitan Expressway

Conventional logit-based models with cross-sectional data are not capable of capturing the individual's behavior that is correlated over time. Although panel data provide the source of information to overcome this issue, collecting panel data, especially from revealed preference data, is generally expensive and difficult in practice. The present paper shows the use of repeated observations from Electronic Toll Collection (STC) data with information about attributes derived from detector data to analyze and model route choice and route switching behavior on a selected study area of the Tokyo Metropolitan Expressway. In general, the estimated results show that drivers respond differently to different levels of congestion information. Moreover, when accounting for the panel data, the factors that capture panel effect are highly significant statistically and improvement of the models' goodness of fit can be observed for both behavioral models.

Analysis of Daily Variability Characteristics of Travel Behavior on Tokyo Metropolitan Expressway using ETC Data

Analysis of Daily Variability Characteristics of Travel Behavior on Tokyo Metropolitan Expressway using ETC Data

A real-time crash prediction model for the ramp vicinities of urban expressways

Ramp vicinities are arguably the known black-spots on urban expressways. There, while maintaining high speed, drivers need to respond to several complex events such as maneuvering, reading road signs, route planning and maintaining safe distance from other maneuvering vehicles simultaneously which demand higher level of cognitive response to ensure safety. Therefore, any additional discomfort caused by traffic dynamics may induce driving error resulting in a crash. This manuscript presents a methodology for identifying these dynamically forming hazardous traffic conditions near the ramp vicinities with high resolution real-time traffic flow data. It separates the ramp vicinities into four zones – upstream and downstream of entrance and exit ramps, and builds four separate real-time crash prediction models. Around two year (December 2007 to October 2009) crash data as well as their matching traffic sensor data from Shibuya 3 and Shinjuku 4 expressways under the jurisdiction of Tokyo Metropolitan Expressway Company Limited have been utilized for this research. Random multinomial logit, a forest of multinomial logit models, has been used to identify the most important variables. Finally, a real-time modeling method, Bayesian belief net (BBN), has been employed to build the four models using ramp flow, flow and congestion index in the upstream and flow and speed in the downstream of the ramp location as variables. The newly proposed models could predict 50%, 42%, 43% and 55% of the future crashes with around 10% false alarm for the downstream of entrance, downstream of exit, upstream of entrance and upstream of exit ramps respectively. The models can be utilized in combination with various traffic smoothing measures such as ramp metering, variable speed limit, warning messages through variable message signs, etc. to enhance safety near the ramp vicinities.

Analysis of Traffic Conditions Prediction at the Incident Congestion on Tokyo Metropolitan Expressway

Analysis of Traffic Conditions Prediction at the Incident Congestion on Tokyo Metropolitan Expressway

Measurement and analysis of traffic-induced response of viaducts in Tokyo Metropolitan Expressway

Measurement and analysis of traffic-induced response of viaducts in Tokyo Metropolitan Expressway

A Bayesian network based framework for real-time crash prediction on the basic freeway segments of urban expressways

The concept of measuring the crash risk for a very short time window in near future is gaining more practicality due to the recent advancements in the fields of information systems and traffic sensor technology. Although some real-time crash prediction models have already been proposed, they are still primitive in nature and require substantial improvements to be implemented in real-life. This manuscript investigates the major shortcomings of the existing models and offers solutions to overcome them with an improved framework and modeling method. It employs random multinomial logit model to identify the most important predictors as well as the most suitable detector locations to acquire data to build such a model. Afterwards, it applies Bayesian belief net (BBN) to build the real-time crash prediction model. The model has been constructed using high resolution detector data collected from Shibuya 3 and Shinjuku 4 expressways under the jurisdiction of Tokyo Metropolitan Expressway Company Limited, Japan. It has been specifically built for the basic freeway segments and it predicts the chance of formation of a hazardous traffic condition within the next 4–9min for a particular 250 meter long road section. The performance evaluation results reflect that at an average threshold value the model is able to successful classify 66% of the future crashes with a false alarm rate less than 20%.

Microscopic Risk Analysis of Rear-End Collision on Tokyo Metropolitan Expressway

Microscopic Risk Analysis of Rear-End Collision on Tokyo Metropolitan Expressway

Microscopic Risk Analysis of Rear-End Collision on Tokyo Metropolitan Expressway

Microscopic Risk Analysis of Rear-End Collision on Tokyo Metropolitan Expressway

Traffic Flow Forecasting and Spatial Data Aggregation

Research investigated ways to forecast traffic flow over an area covering multiple links of a roadway network. The question arose of whether to construct one large-scale model or to combine results from separate smaller-scale models. Intuition favors link-specific analyses, but econometric results show how using aggregate models can increase accuracy. It is shown how theory holds that correlations between traffic conditions on different roadway links and errors in link-specific observations of traffic conditions increase the relative accuracy of larger-scale models, whereas site-specific sensitivities suggest smaller-scale data. Empirical evidence is presented regarding the relative accuracy of various models of traffic flow rate. One form of a seasonal autoregressive integrated moving average time series model for general flow forecasting is chosen, along with methodologies for automatically selecting models based on input data. Studies based on data from the Tokyo Metropolitan Expressway show that increasing data aggregation consistently increases model accuracy. Sums of forecasts of link flows yield predictions of areawide flow roughly as accurate as predictions based on univariate analysis of areawide data. Areawide flows are easier to predict accurately than link flows. Modeling large-area traffic flow with a univariate model is considerably simpler but produces less subsequently useful results than use of separate, link-specific models.