arXiv subjects

Toru Seo

Publications and source records attributed to Toru Seo.

11 recordsLinked to original sources

arXiv2026

Flexible and Reliable Network Design for Emerging Transportation Services: Multi-stage Stochastic Programming Approach

This paper proposes a general framework for flexible and reliable network design problems (FR-NDPs). The framework enables planners to change infrastructure investments in response to realized uncertainties, while ensuring desired levels of reliability. Motivated by emerging transportation services such as shared autonomous vehicle (SAV) systems, where historical data are scarce and technological developments uncertain, FR-NDPs integrate strategic investment decisions with operational control. We formulate the FR-NDPs as risk-averse multi-stage stochastic problems to be solvable by stochastic dual dynamic programming (SDDP) and establish sufficient conditions under which strategic and operational subproblems converge to the global optimum. We illustrate applications to SAV capacity expansion and integrated SAV-BRT (Bus Rapid Transit) route design, and numerical experiments on a Midtown Manhattan network highlight three key findings: (i) flexibility and reliability act complementarily to hedge against severe scenarios while mitigating the loss of expected performance; (ii) flexibility in investment planning allows dynamic risk hedging, with risk-averse planners reducing early-stage investments to preserve adaptability; and (iii) differences in operational flexibility between SAV and BRT systems are reflected in strategic decisions, with risk-averse planners tending to refrain investment in transport modes with lower operational flexibility.

math.OC↗

arXiv2026

Distance between Road Networks: A Macroscopic Method for Road Network Datasets Comparison Using Traffic-weighted Geographic Distribution

In transportation network analysis, various types of road network data can be used even when focusing on the same region. Since different road network datasets can make different performance in analyses, it is necessary to compare them and make appropriate selections in a qualitative manner. However, many of the existing methods for comparing road network datasets are limited to specific topological evaluations and do not consider transportation. This study proposes a method for quantitative comparison of different road network datasets with explicit consideration for traffic flows on them. The method first conducts a static traffic assignment with hypothetical demand for each dataset, and then compare the results using Wasserstein distance on two dimensional plane. Case study on different sources of road network datasets and their simplifications suggests the potential use of the proposed method in evaluating and selecting road network datasets.

cs.CE↗

arXiv2026

End-to-end differentiable network traffic simulation with dynamic route choice

Optimization using network traffic models requires computing gradients of objective functions with respect to model parameters. However, derivation of such gradients has often been considered difficult or impractical due to their complexity and size. Conventional approaches rely on numerical differentiation or derivative-free methods that do not scale well with the parameter dimension, or on adjoint methods that require manual derivation for each specific model. This study proposes a novel end-to-end differentiable network traffic flow simulator based on automatic differentiation (AD), employing the Link Transmission Model (LTM) and a Dynamic User Optimum (DUO) route choice model. The LTM operates on continuous aggregate state variables through piecewise-linear min/max operations, which admit subgradients almost everywhere and thus require no smooth relaxation for AD. The DUO is also suitable for AD: although the shortest path search is itself discrete, the resulting diverge ratios at each node are continuous functions of per-destination vehicle counts and are thus differentiable. In order to demonstrate the capability of the proposed model, we solved a dynamic congestion toll optimization problem on the Chicago-Sketch dataset with approximately 2500 links, 1 million vehicles, a 3-hour duration, and 15000 decision variables. The proposed model successfully derived a high-quality solution in 3000 iterations, taking about 40 minutes. The simulator, implemented in Python and JAX, is released as open-source software named UNsim (https://github.com/toruseo/UNsim).

eess.SY↗

arXiv2025

Incorporating graph neural network into route choice model

Route choice models are one of the most important foundations for transportation research. Traditionally, theory-based models have been utilized for their great interpretability, such as logit models and Recursive logit models. More recently, machine learning approaches have gained attentions for their better prediction accuracy. In this study, we propose novel hybrid models that integrate the Recursive logit model with Graph Neural Networks (GNNs) to enhance both predictive performance and model interpretability. To the authors' knowldedge, GNNs have not been utilized for route choice modeling, despite their proven effectiveness in capturing road network features and their widespread use in other transportation research areas. We mathematically show that our use of GNN is not only beneficial for enhancing the prediction performance, but also relaxing the Independence of Irrelevant Alternatives property without relying on strong assumptions. This is due to the fact that a specific type of GNN can efficiently capture multiple cross-effect patterns on networks from data. By applying the proposed models to one-day travel trajectory data in Tokyo, we confirmed their higher prediction accuracy compared to the existing models.

cs.LG↗

arXiv2024

Modeling pedestrian fundamental diagram based on Directional Statistics

Understanding pedestrian dynamics is crucial for appropriately designing pedestrian spaces. The pedestrian fundamental diagram (FD), which describes the relationship between pedestrian flow and density within a given space, characterizes these dynamics. Pedestrian FDs are significantly influenced by the flow type, such as uni-directional, bi-directional, and crossing flows. However, to the authors' knowledge, generalized pedestrian FDs that are applicable to various flow types have not been proposed. This may be due to the difficulty of using statistical methods to characterize the flow types. The flow types significantly depend on the angles of pedestrian movement; however, these angles cannot be processed by standard statistics due to their periodicity. In this study, we propose a comprehensive model for pedestrian FDs that can describe the pedestrian dynamics for various flow types by applying Directional Statistics. First, we develop a novel statistic describing the pedestrian flow type solely from pedestrian trajectory data using Directional Statistics. Then, we formulate a comprehensive pedestrian FD model that can be applied to various flow types by incorporating the proposed statistics into a traditional pedestrian FD model. The proposed model was validated using actual pedestrian trajectory data. The results confirmed that the model effectively represents the essential nature of pedestrian dynamics, such as the capacity reduction due to conflict of crossing flows and the capacity improvement due to the lane formation in bi-directional flows.

nlin.AO↗

arXiv2023

Understanding Impact of Angle in Urban Transportation

Traffic congestion at urban-scale levels occurs when road network supply is insufficient compared with demand. Therefore, the relationship between supply and demand has been extensively investigated in the literature. Especially the impact of a network's topology (i.e., connectivity) on traffic congestion has been widely studied. On the other hand, only a few studies analyze the relationship between the physical shape of the road network (i.e., morphology), demand, and congestion. For example, angular indicators associated with links and trips can be utilized to characterize such morphology. However, statistical analysis of angular indicators requires a specialized methodology called Directional Statistics, and how to apply Directional Statistics to traffic data is not obvious. Here, this study develops a descriptive model of traffic congestion based on Directional Statistics. It describes direction-dependent congestion levels using angular distributions that characterize the shape of road network and travel demand. Specifically, the shape of road network is characterized by the distribution of angles of each road link in a specific region. Likewise, the travel demand is characterized by the distribution of angles of each trip in the region. Then, a statistical model that describes travel time for a trip with arbitrary direction by these two angular distribution is constructed by paying special attention to the fact that roads and demands from all angles would affect congestion. A simple estimation method for the proposed model is also presented. Finally, the model was estimated using actual data in Tokyo, and the relationship between the characteristics of the shape of the road network, the direction of demand, and congestion is analyzed from the new perspective of angles.

stat.AP↗

arXiv2023

UXsim: An open source macroscopic and mesoscopic traffic simulator in Python -- a technical overview

This note describes a technical overview of UXsim, an open source macro/mesoscopic traffic simulator in pure Python programming language. UXsim is based on Kinematic Wave model (more specifically, mesoscopic version of Newell's simplified car-following model) and dynamic user optimum-like route choice principle, which are well established methodology in the transportation research field. It can compute dynamical network traffic flow and have basic visualization and analysis capability. Furthermore, users can implement their own models and control methods into the simulator by using Python, thanks to the flexibility of the language. The simulator and its codes are freely available at https://github.com/toruseo/UXsim under the MIT license.

eess.SY↗

arXiv2023

A Macro-Micro Approach to Reconstructing Vehicle Trajectories on Multi-Lane Freeways with Lane Changing

Vehicle trajectories can offer the most precise and detailed depiction of traffic flow and serve as a critical component in traffic management and control applications. Various technologies have been applied to reconstruct vehicle trajectories from sparse fixed and mobile detection data. However, existing methods predominantly concentrate on single-lane scenarios and neglect lane-changing (LC) behaviors that occur across multiple lanes, which limit their applicability in practical traffic systems. To address this research gap, we propose a macro-micro approach for reconstructing complete vehicle trajectories on multi-lane freeways, wherein the macro traffic state information and micro driving models are integrated to overcome the restrictions imposed by lane boundary. Particularly, the macroscopic velocity contour maps are established for each lane to regulate the movement of vehicle platoons, meanwhile the velocity difference between adjacent lanes provide valuable criteria for guiding LC behaviors. Simultaneously, the car-following models are extended from micro perspective to supply lane-based candidate trajectories and define the plausible range for LC positions. Later, a two-stage trajectory fusion algorithm is proposed to jointly infer both the car-following and LC behaviors, in which the optimal LC positions is identified and candidate trajectories are adjusted according to their weights. The proposed framework was evaluated using NGSIM dataset, and the results indicated a remarkable enhancement in both the accuracy and smoothness of reconstructed trajectories, with performance indicators reduced by over 30% compared to two representative reconstruction methods. Furthermore, the reconstruction process effectively reproduced LC behaviors across contiguous lanes, adding to the framework's comprehensiveness and realism.

math.OC↗

arXiv2022

Dynamic network congestion pricing based on deep reinforcement learning

Traffic congestion is a serious problem in urban areas. Dynamic congestion pricing is one of the useful schemes to eliminate traffic congestion in strategic scale. However, in the reality, an optimal dynamic congestion pricing is very difficult or impossible to determine theoretically, because road networks are usually large and complicated, and behavior of road users is uncertain. To account for this challenge, this work proposes a dynamic congestion pricing method using deep reinforcement learning (DRL). It is designed to eliminate traffic congestion based on observable data in general large-scale road networks, by leveraging the data-driven nature of deep reinforcement learning. One of the novel elements of the proposed method is the distributed and cooperative learning scheme. Specifically, the DRL is implemented by a spatial-temporally distributed manner, and cooperation among DRL agents is established by novel techniques we call spatially shared reward and temporally switching learning. It enables fast and computationally efficient learning in large-scale networks. The numerical experiments using Sioux Falls Network showed that the proposed method works well thanks to the novel learning scheme.

eess.SY↗

arXiv2019

Fundamental diagram estimation by using trajectories of probe vehicles

The fundamental diagram (FD), also known as the flow--density relation, is one of the most fundamental concepts in the traffic flow theory. It describes the relation between equilibrated flow, density, and speed in traffic flow. Conventionally, FDs are estimated by using fixed roadside sensors such as detectors. On the other hand, there is a paucity of studies on FD estimation by using mobile sensors, namely probe vehicles. Probe vehicles enable the collection of traffic data from the entire road network, and thus they are useful sensors for large-scale traffic management. In this study, a framework of FD estimation by using probe vehicle data is developed. It determines FD parameters based on trajectories of randomly sampled vehicles and a given jam density that is easily inferred by other data sources. Specifically, an algorithm for estimating a triangular FD based on actual, potentially noisy traffic data is developed. The algorithm is empirically validated by using real-world probe vehicle data on a highway. The results suggest that the algorithm accurately and robustly estimates the FD parameters.

physics.flu-dyn↗

arXiv2017

Fundamental diagram of urban rail transit considering train-passenger interaction

Urban rail transit often operates with high service frequencies to serve heavy passenger demand during rush hours. Such operations can be delayed by two types of congestion: train congestion and passenger congestion, both of which interact with each other. This delay is problematic for many transit systems, since it can be amplified due to the interaction. However, there are no tractable models describing them; and it makes difficult to analyze management strategies of congested transit systems in general and tractable ways. To fill this gap, this article proposes simple yet physical and dynamic model of urban rail transit. First, a fundamental diagram of transit system (i.e., theoretical relation among train-flow, train-density, and passenger-flow) is analytically derived considering the aforementioned physical interaction. Then, a macroscopic model of transit system for dynamic transit assignment is developed based on the fundamental diagram. Finally, accuracy of the macroscopic model is investigated by comparing to microscopic simulation. The proposed models would be useful for mathematical analysis on management strategies of urban rail transit systems, in a similar way that the macroscopic fundamental diagram of urban traffic did.

eess.SY↗