Jian Sun

• Tongji University

This paper revisits the Reactive Dynamic User-Equilibrium (RDUE) model for dynamic traffic assignment (DTA) of macroscopic traffic flow in two-dimensional continuum space, focusing on the Eikonal equation—a crucial partial differential equation (PDE) with specific boundary conditions. Traditionally, solving Eikonal equations has relied on iterative...

Autonomous Vehicles (AVs) have entered the commercialization stage, but their limited ability to interact and express intentions still poses challenges in interactions with Human-driven Vehicles (HVs). Recent advances in large language models (LLMs) enable bidirectional human-machine communication, but the conflict between slow inference speed and...

Simulated scenario-based test on Highly Automated Vehicles (HAVs) has been widely-received to ensure HAVs' safety as a solution to the problem brought on by mileage-based road testing. An appropriate scenario library is an important guarantee for the reliability of test results and test efficiency. Most scenario datasets opened to public contain re...

The successful deployment of Autonomous Vehicles (AVs) within the transportation system is contingent upon comprehensive safety validation. To assess the accident rate of AVs in real traffic is essential in safety validation. However, it is hindered by the complexity of traffic scenarios and the rarity of accidents, necessitating impractical billio...

Although Deep Reinforcement Learning (DRL) and Large Language Models (LLMs) each show promise in addressing decision-making challenges in autonomous driving, DRL often suffers from high sample complexity, while LLMs have difficulty ensuring real-time decision making. To address these limitations, we propose TeLL-Drive, a hybrid framework that integ...

Objective: Motorized vehicles (MV) and non-motorized vehicles (NMV) are mixed in the intersection center area (ICA). This mixing leads to complicated interactions between vehicles, which seriously affects traffic safety, especially at mixed intersections of high density. To deep understanding of the interaction course between motorized and non-mot...

A lack of understanding of interactions and the inability to effectively resolve conflicts continue to impede the progress of Connected Autonomous Vehicles (CAVs) in their interactions with Human-Driven Vehicles (HDVs). To address this challenge, we propose the Recognize then Resolve (RtR) framework. First, a Bilateral Intention Progression Graph (...

Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for the deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are developed, in which behaviors of traffic participants are manipulated to induce safety-critical events. Howev...

Simulation environments are essential for validating algorithms, evaluating system performance, and ensuring safety in autonomous driving systems before real-world deployment. Existing autonomous driving simulators are designed for urban scenarios but lack coverage of unstructured road environments in open-pit mining. This paper introduces MineSim,...

Urban time series, such as mobility flows, energy consumption, and pollution records, encapsulate complex urban dynamics and structures. However, data collection in each city is impeded by technical challenges such as budget limitations and sensor failures, necessitating effective data imputation techniques that can enhance data quality and reliabi...

The mixing of motorized and non-motorized vehicles in the central area of the intersection with a high density of interaction behavior leads to a high risk of collision that seriously endangers users. To devise effective control strategies for risky driving behavior, it is crucial to model how risk evolves during these interactions. This study pres...

The cooperative driving technology of Connected and Autonomous Vehicles (CAVs) is crucial for improving the efficiency and safety of transportation systems. Learning-based methods, such as Multi-Agent Reinforcement Learning (MARL), have demonstrated strong capabilities in cooperative decision-making tasks. However, existing MARL approaches still fa...

Connected Autonomous Vehicles (CAVs) are being tested globally, but their performance in complex scenarios remains suboptimal. While cooperative driving improves CAV performance by leveraging vehicle collaboration, its lack of interaction and continuous learning limits current applications to single scenarios and specific Cooperative Driving Automa...

Motorized vehicles (MV) and non-motorized vehicles (NMV) are mixed in the intersection center area (ICA). This mixing leads to complicated interactions between vehicles, which seriously affects traffic safety, especially at mixed intersections of high density. To deep understanding of the interaction course between motorized and non-motorized vehic...

The driving interaction-a critical yet complex aspect of daily driving-lies at the core of autonomous driving research. However, real-world driving scenarios sparsely capture rich interaction events, limiting the availability of comprehensive trajectory datasets for this purpose. To address this challenge, we present InterHub, a dense interaction d...

The real-time road surface friction coefficient (RSFC) is a critical parameter for evaluating skid resistance and making safe driving decisions in driver assistance systems and autonomous vehicles, especially under adverse weather conditions. RSFC estimation depends on the interaction between the road surface and tires. However, accurate estimation...

Spatiotemporal traffic data (STTD) displays complex correlational structures. Extensive advanced techniques have been designed to capture these structures for effective forecasting. However, because STTD is often massive in scale, practitioners need to strike a balance between effectiveness and efficiency using computationally efficient models. An...

Scenario-based testing has become a crucial method for certifying the safety of autonomous vehicles amidst the rapid advancement of autonomous driving technology. The exploration of worst-case scenarios, which plays a vital role in safety assessments and accelerated improvements of autonomous driving systems, has posed challenges due to the high di...

The cooperative driving technology of Connected and Autonomous Vehicles (CAVs) is crucial for improving the efficiency and safety of transportation systems. Learning-based methods, such as Multi-Agent Reinforcement Learning (MARL), have demonstrated strong capabilities in cooperative decision-making tasks. However, existing MARL approaches still fa...

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific dimensions or source-dependent patterns, restricting them from unifying representations. Here, we present a novel parad...

The balance between model capacity and generalization has been a key focus of recent discussions in long-term time series forecasting. Two representative channel strategies are closely associated with model expressivity and robustness, including channel independence (CI) and channel dependence (CD). The former adopts individual channel treatment an...

Autonomous vehicles (AV) are consistently criticized for their inadequacies in harmoniously interacting with human-driven vehicles (HV), primarily attributed to the lack of sociality, a key human trait that balances individual and group rewards. Understanding sociality is essential for smooth AV navigation but remains challenging. To address this,...

At present, Connected Autonomous Vehicles (CAVs) have begun to open road testing around the world, but their safety and efficiency performance in complex scenarios is still not satisfactory. Cooperative driving leverages the connectivity ability of CAVs to achieve synergies greater than the sum of their parts, making it a promising approach to impr...

The integration of Autonomous Vehicles (AVs) into existing human-driven traffic systems poses considerable challenges, especially within environments where human and machine interactions are frequent and complex, such as at unsignalized intersections. To deal with these challenges, we introduce a novel framework predicated on dynamic and socially-a...

The proliferation of e-commerce and urbanization has significantly intensified delivery operations in urban areas, boosting the volume and complexity of delivery demand. Data-driven predictive methods, especially those utilizing machine learning techniques, have emerged to handle these complexities in urban delivery demand management problems. One...

Automated Vehicle (AV) validation based on simulated testing requires unbiased evaluation and high efficiency. One effective solution is to increase the exposure to risky rare events while reweighting the probability measure. However, characterizing the distribution of risky events is particularly challenging due to the paucity of samples and the t...

A throughout safety verification of an Autonomous Driving System (ADS) is essential to ensure its capability to drive safely in naturalistic traffic environment. Commonly used test automation methods such as Important Sampling (IS) do not perform well in distribution fitting efficiency in high-dimensional scenarios. In this paper, we proposed the A...

Interacting with human road users is one of the most challenging tasks for autonomous vehicles. For congruent driving behaviors, it is essential to recognize and comprehend sociality, encompassing both implicit social norms and individualized social preferences of human drivers. To understand and quantify the complex sociality in driving interactio...

Assessing drivers' interaction capabilities is crucial for understanding human driving behaviour and enhancing the interactive abilities of autonomous vehicles. In scenarios involving strong interaction, existing metrics focussed on interaction outcomes struggle to capture the evolutionary process of drivers' interactive behaviours, making it chall...

Ensuring fault tolerance of Highly Automated Vehicles (HAVs) is crucial for their safety due to the presence of potentially severe faults. Hence, Fault Injection (FI) testing is conducted by practitioners to evaluate the safety level of HAVs. To fully cover test cases, various driving scenarios and fault settings should be considered. However, due...

The balance between model capacity and generalization has been a key focus of recent discussions in long-term time series forecasting. Two representative channel strategies are closely associated with model expressivity and robustness, including channel independence (CI) and channel dependence (CD). The former adopts individual channel treatment an...

Millimeter-wave (mm-wave) radar technology has become a popular choice for collecting vehicle trajectory data. However, the high cost of deploying these radars densely has necessitated sparser placements to be more cost-effective. Unfortunately, this leads to perceptual sparsity in roadside detection, with significant gaps and vehicles losing their...

In the domain of autonomous vehicles (AVs), decision-making is a critical factor that significantly influences the efficacy of autonomous navigation. As the field progresses, the enhancement of decision-making capabilities in complex environments has become a central area of research within data-driven methodologies. Despite notable advances, exist...

This is the conference version of our paper: Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner. Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to dat...

The simulation-based testing is essential for safely implementing autonomous vehicles (AVs) on roads, necessitating simulated traffic environments that dynamically interact with the Vehicle Under Test (VUT). This study introduces a VUT-Centered environmental Dynamics Inference (VCDI) model for realistic, interactive, and diverse background traffic...

Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific dimensions or source-dependent patterns, restricting them from unifying representations. Here, we present a novel parad...

Highly Automated Vehicles (HAVs) are exposed to numerous unexpected faults that threaten the functionality of the Autonomous Driving System (ADS) in HAVs, and even minor faults can lead to serious consequences such as collisions. Accordingly, fault tolerance of HAVs should be thoroughly evaluated before large-scale deployment. Fault Injection (FI)...

Traffic monitoring is essential for the efficiency and safety of urban transportation systems. It helps in observing traffic congestion, incidents, accidents, roadworks, and other disruptions. Traditional methods depend largely on fixed detectors, which have significant limitations in responding to diverse and dynamic traffic events. Connected vehi...

Carpooling is one of the travel demand management strategies to mitigate road congestion. Incentive-Based Travel Demand Management (IBTDM) strategies are pivotal for carpool promotion by providing incentives to address inconveniences and privacy apprehensions, yet their efficacy lacks validation. Considering the constraints of incentive budget as w...

Cooperative Adaptive Cruise Control (CACC) represents a quintessential control strategy for orchestrating vehicular platoon movement within Connected and Automated Vehicle (CAV) systems, significantly enhancing traffic efficiency and reducing energy consumption. In recent years, the data-driven methods, such as reinforcement learning (RL), have bee...

In recent years, mopeds have emerged as attractive two-wheeled vehicles because of their high mobility. However, the flexibility and randomness associated with mopeds make the development of two-wheeled microscopic simulation models more difficult. Human factors (HFs), for example, the riding style, are the major source of behavior heterogeneity, a...

Sensor and machine learning technologies have improved the perception of traffic systems by providing detailed data about individual vehicle trajectories. Combining data from different types of sensors shows promise for comprehensive perception of global traffic, but it remains challenging. Stationary roadside units only gather sparse trajectories...

Autonomous driving has drawn considerable attention across various sectors, including government, industry, and academia. Scientific testing and evaluation play a pivotal role in driving advancements in autonomous driving technology. However, in the realm of research and development, several common challenges have emerged, including disagreements a...

Merging areas serve as the potential bottlenecks for continuous traffic flow on freeways. Traffic incidents in freeway merging areas are closely related to decision-making errors of human drivers, for which the autonomous vehicles (AVs) technologies are expected to help enhance the safety performance. However, evaluating the safety impact of AVs is...

Incentive-based travel demand management (IBTDM) programs endow monetary incentives to encourage travel demand redistribution across space and time. They are more appealing than alternatives such as congestion charging because commuters do not need to pay out of pocket. However, such congestion-alleviation solutions are usually managed by small pri...

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...

As the rapid advancement of artificial intelligence (AI), information and communication technologies, autonomous driving system (ADS) has increased permeation into the traditional automotive industry in recent years. To reduce the Safety of the Intended Functionality (SOTIF) risk of autonomous driving system hence improving its dependability, SIL s...

This paper introduces a Privacy-Preserving Traffic Assignment (PPTA) model designed to evaluate the impact of Differential Privacy (DP) mechanisms on traffic patterns across Multimodal Transportation Systems (MTSs). With the rise in traveler data exchange, there is an increasing need for secure and efficient data handling methods that prioritize us...

Incentive-Based Travel Demand Management (IBTDM) strategies utilize monetary incentives to alleviate congestion by encouraging travelers to 1) alter travel routes, 2) shift departure times, 3) shift travel modes, and 4) eliminate trips. In recent years, plenty of IBTDM pilots have been successfully implemented. Since the implementation of IBTDM str...

为促进中国自动驾驶技术发展，在充分调研论证的基础上，按照工具化设计的理念，国家自然科学基金委员会交通与运载工程学科提出了场景库社会共建、开发环境敏捷、被测技术解耦、测试部署轻量化、评测结果公开透明的自动驾驶测试公共服务平台OnSite的建设构想，设置了战略委员会、技术委员会、用户委员会、创新基金会，自主决策，达成公共服务平台独立发展，良好运行的目标。2021年，交通与运载工程学科通过面上项目群快速启动本领域研究，2022年起，持续通过重点项目、面上项目群资助自动驾驶测评相关技术研究，推动OnSite平台建设，积极开展有组织科研。制定了单项决策规划能力测评-从单项测评到全栈技术测评-从虚拟测评到虚实融合测评-从单车测评到车队测评-从测评导向到开发测评一体五阶段公共服务平台建设计划；目前，已完成...

◦ Investigates sparser radar placements for cost-effectiveness ◦ Shows potential of vehicle re-identification using trajectories only ◦ Tailors a "Generator-as-a-Matcher" model, simple and easy-to-train

Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing decision-making performance in complex scenarios has emerged as a prominent research focus. Despite considerable ad...

High-density, unsignalized intersections have always been a bottleneck of efficiency and safety. The emergence of Connected Autonomous Vehicles (CAVs) results in a mixed traffic condition, further increasing the complexity of the transportation system. Against this background, this paper aims to study the intricate and heterogeneous interaction of...

Deep learning models have been widely used in trajectory prediction. However, they typically focus on developing a pre-training model by learning average features from trajectory data and are difficult to learn and predict heterogeneous behavior patterns. Especially in the case of cyclists, the prediction of low-probability risky behavior is a majo...

For autonomous vehicles (AVs), accurately predicting the future motions of Vulnerable Road Users (VRUs) is essential for safe and reliable interactions. Especially in cities with many vehicle-bicycle-mixed traffic roads, predicting the trajectories of multi-cyclists remains a significant challenge for AVs. However, current trajectory prediction met...

One of the key factors determining whether autonomous vehicles (AVs) can be seamlessly integrated into existing traffic systems is their ability to interact smoothly and efficiently with human drivers and communicate their intentions. While many studies have focused on enhancing AVs' human- like interaction and communication capabilities at the beh...

Given the complex nature of interaction under ambiguous right-of-way scenarios, the interactions between Autonomous Vehicles (AVs) and Human-driven Vehicles (HVs) present considerable challenges to the safety and efficiency of the traffic system. Existing AVs struggle to comprehend and apply common HV social norms, especially the proactive behavior...

The integration of Autonomous Vehicles (AVs) into existing human-driven traffic systems poses considerable challenges , especially within environments where human and machine interactions are frequent and complex, such as at unsignalized intersections. To deal with these challenges, we introduce a novel framework predicated on dynamic and socially-...

Numerous efforts have been made to address the section‐level travel speed prediction problem. However, section‐level predictions can hardly be used for fine‐grained applications, such as lane management and lane‐level navigation. The main reason for this is that significant speed heterogeneity exists among the lanes within one section. Thus, this s...

Missing data is a pervasive issue in both scientific and engineering tasks, especially for the modeling of spatiotemporal data. This problem attracts many studies to contribute to machine learning solutions. Existing imputation solutions mainly include low-rank models and deep learning models. On the one hand, low-rank models assume general structu...

To validate whether Highly Automated Vehicles (HAVs) can live up to human expectations, it is essential to estimate their risk rate within the context of the naturalistic driving environment. Due to the low probability of exposure to risky events, the testing process is exceedingly time-consuming. To tackle this issue, we proposed a Surrogate-based...

Microscopic traffic simulation is vital to assess the performances of various traffic operation and management schemes. Microscopic traffic simulation is usually not parameter-free, and it relies on independent parameters to predict traffic evolution. Thus, parameter calibration is indispensable to conveying trustworthy simulation results. Heuristi...

Traffic volume is an indispensable ingredient to provide fine-grained information for traffic management and control. However, due to the limited deployment of traffic sensors, obtaining full-scale volume information is far from easy. Existing work on this topic focuses primarily on improving the overall estimation accuracy of a particular method a...

Traffic bottlenecks significantly influence the operation efficiency of large-scale road networks. Developing advanced control strategies for bottleneck optimization is a cost-efficient and critical way to deal with network congestion. However, the state-of-the-art studies upon network congestion control focus on the topology level, which may fail...

Intra-driver heterogeneity is defined as transition of driver's behavior between usual and unusual, which is an intrinsic feature of drivers while yet to be extensively explored. This study used a large-scale naturalistic driving data set to investigate intra-driver heterogeneity in car-following. We constructed an IDM-based baseline model to repre...

Two-wheelers have prevailed in cities, exhibiting flexible and unpredictable behaviors that pose challenges to road safety. Therefore, it’s necessary to implement behaviour modelling to gain insight into risk-taking behaviours of two-wheelers. Nevertheless, human factors (HF), as important research content, are not well considered in many existing...

Autonomous driving technology is poised to transform transportation systems. However, achieving safe and accurate multi-task decision-making in complex scenarios, such as unsignalized intersections, remains a challenge for autonomous vehicles. This paper presents a novel approach to this issue with the development of a Multi-Task Decision-Making Ge...

With the gradual perfection of Highly Automated Vehicles (HAVs), it is obligatory to assess their safety performance in simulation that mirrors the real-world driving environment. However, the minimal likelihood of exposure to risky events can result in an extremely time-consuming testing process. To address this issue, we applied a surrogate-based...

The advent of autonomous vehicles (AVs) alongside human-driven vehicles (HVs) has ushered in an era of mixed traffic flow, presenting a significant challenge: the intricate interaction between these entities within complex driving environments. AVs are expected to have human-like driving behavior to seamlessly integrate into human-dominated traffic...

Path dispersion (the spatial distribution of vehicular paths) is an important feature of traffic flow inside intersections and differs from traffic flow running along traffic lanes at road segment, especially under conflicting movements. The path dispersion reflects the operational features of traffic flow and is related to driving behaviour, arriv...

The authors regret an error in the acknowledgments section regarding the project number provided for the support received from the Science and Technology Commission of Shanghai Municipality. The incorrect project number (No. 22dz103200) was included in the acknowledgments section of the published paper. The accurate project number that should have...

Sensor and machine learning technologies have improved the perception of traffic systems by providing detailed data about individual vehicle trajectories. Combining data from different types of sensors shows promise for holographic perception of global traffic but remains challenging: stationary roadside units only gather sparse trajectories of pas...

Spatiotemporal graph neural networks (STGNNs) have emerged as a leading approach for learning representations and forecasting on traffic datasets with underlying topological and correlational structures. However, current STGNNs use intricate techniques with high complexities to capture these structures, making them difficult to understand and scale...

Ridesharing is recognized as an environmentally friendly alternative to daily transportation that can potentially reduce vehicular carbon emissions. Transportation Network Companies (TNC) have been providing ridesharing services. However, generalized costs need to be balanced between rideshare drivers and passengers via financial instruments to rea...

Highly Automated Vehicles (HAVs) are exposed to various kinds of internal or external data faults, which may lead to disengagements and collisions. Detecting critical faults and evaluating the fault tolerance of HAVs, especially in terms of motion planning, is of great importance before HAVs are deployed on a large scale. However, due to the curse...

Millimeter-wave (mm-wave) radar technology has become popular for vehicle trajectory data collection. However, the high cost of deploying these radars densely has made it necessary to use sparser placements for more cost-effective. Unfortunately, this approach creates significant blind spots in detection, causing vehicles to lose their IDs and maki...

Urban traffic is a large-scale, complex dynamical system that transitions between free-flow and congestion states. Understanding the emergence of traffic states is crucial for both dynamical modeling and traffic control, and has attracted much attention. By modeling congestion of a large-scale traffic network as a percolation process, researchers f...

Autonomous driving technology is poised to transform transportation systems. However, achieving safe and accurate multi-task decision-making in complex scenarios, such as unsignalized intersections, remains a challenge for autonomous vehicles. This paper presents a novel approach to this issue with the development of a Multi-Task Decision-Making Ge...

One of the key factors determining whether autonomous vehicles (AVs) can be seamlessly integrated into existing traffic systems is their ability to interact smoothly and efficiently with human drivers and communicate their intentions. While many studies have focused on enhancing AVs' human-like interaction and communication capabilities at the beha...

Driving distraction is a common abnormal behavior which seriously disturbs the safety and stability of traffic flow. Because the vehicle has a large degree of freedom in the longitudinal car-following(CF) driving context， most of the distracted driving behaviors exist in the CF driving context. Therefore， it is of great significance to deeply under...

Interacting with other human road users is one of the most challenging tasks for autonomous vehicles. To generate congruent driving behaviors, the awareness and understanding of sociality, which includes implicit social customs and individualized social preferences of human drivers, are required. To understand and quantify the complex sociality in...