traffic microsimulation

To address insufficient traffic simulation fidelity and ambiguous requirement specifications in driving simulators, this paper proposes a systematic traffic simulation requirement analysis method based on sub-goal decomposition. The experimental objective is hierarchically decomposed into verifiable sub-goals—including microscopic traffic modeling, agent behavioral modeling, and visual rendering—thereby establishing a structured, traceable mapping from research objectives to simulation configuration. This method establishes, for the first time, an explicit linkage between traffic simulation design and underlying experimental goals, significantly enhancing simulation fidelity, experimental validity, and participant immersion. Empirical evaluation demonstrates that the proposed framework supports high-fidelity development and human–autonomy interaction testing of autonomous driving systems.

Evaluating coverage adequacy of scenario libraries for Automated Driving System (ADS) type-approval remains challenging, particularly in ensuring both comprehensive Operational Design Domain (ODD) coverage and faithful representation of intrinsic diversity in real-world driving data. Method: This paper proposes a computable, two-layer coverage metric: (i) quantifying ODD coverage sufficiency, and (ii) assessing representational completeness of underlying driving data diversity. Our approach integrates statistical analysis of the HighD dataset, scenario clustering with ODD-dimensional mapping, coverage modeling, and gap identification algorithms. Contribution/Results: Evaluated on over 200,000 real-world traffic scenarios across 10 categories, the method achieves up to 100% ODD coverage under specific conditions and precisely identifies missing scenario types and data patterns. To our knowledge, this is the first work to jointly and quantitatively assess ODD coverage and data diversity coverage, establishing a reproducible, verifiable evaluation paradigm for scenario library construction.

This paper addresses the lack of systematic evaluation of car-following (CF) models in traffic simulation and advanced driver-assistance systems (ADAS). Methodologically, it conducts the first interdisciplinary review integrating perspectives from transportation engineering, control theory, cognitive science, and machine learning—unifying the evolutionary trajectory from classical models (e.g., IDM, OVM) and psychophysical models to adaptive cruise control (ACC) algorithms and data-driven approaches (e.g., reinforcement learning, imitation learning). A multidimensional evaluation framework is proposed, assessing interpretability, generalizability, real-time performance, and deployability. The key contributions include identifying complementary strengths and critical knowledge gaps across modeling paradigms, delineating precise applicability boundaries for each model class, and proposing a future research framework for co-optimization of ADAS and traffic simulation. This work provides both theoretical foundations and practical guidelines for intelligent driving modeling.

This study addresses the critical need for safety verification of autonomous driving systems (ADS) by extracting traffic participant behaviors from real-world driving data to inform safety assumption modeling. Method: Grounded in the IEEE 2846–2022 standard, we systematically instantiate the safety assumption framework into computable kinematic boundary parameters for the first time. Leveraging the UniD dataset, we construct a behavior representation system integrating high-level scenarios, kinematic characteristics, and safety relevance, and quantitatively characterize the reasonably predictable behavioral boundaries. Our approach integrates Python-driven data processing, scenario modeling, and kinematic boundary extraction. Contribution/Results: We deliver a curated set of initial states and constraint parameters for traffic participants across representative driving scenarios—directly deployable in simulation or on-vehicle testing. This advances standardized, data-driven ADS safety verification with improved fidelity and operational relevance.

Existing traffic simulators struggle to generate large-scale, high-fidelity urban scenarios with diverse driving styles, hindering robust evaluation of autonomous driving systems. To address this, we propose the first controllable traffic simulation framework based on diffusion models. Our method unifies multi-source traffic data into a coherent scene representation and introduces a conditional guidance mechanism to explicitly control driving styles—including aggressive, conservative, and stochastic behaviors. This approach overcomes the dual limitations of conventional rule-based and data-driven simulators in behavioral diversity and scene generalizability, enabling real-time, high-fidelity simulation over city-scale road networks with thousands of vehicles. Experiments demonstrate that our platform supports systematic manipulation of key variables—such as traffic density and style composition—thereby significantly enhancing the effectiveness and interpretability of autonomous driving algorithm evaluation, particularly in edge-case scenarios.

This study addresses the limitation of conventional microsimulation in faithfully reproducing transient traffic wave dynamics. We propose a data-driven co-simulation framework integrating CARLA with high-fidelity trajectory data from the I-24 MOTION dataset. Our method introduces a boundary-condition-driven mechanism—leveraging ghost cells, autonomous vehicle generation, and configurable vehicle dynamics models—to reconstruct spatiotemporal traffic states end-to-end. To our knowledge, this is the first implementation of measurement-based, boundary-driven simulation within CARLA, overcoming the constraints of localized car-following models and enabling microscale emergence of macroscopic traffic phenomena. Experiments successfully replicate the formation, propagation, and dissipation of traffic waves under both high- and low-density conditions, achieving significantly improved spatiotemporal fidelity. The framework provides a high-fidelity simulation environment for evaluating traffic control strategies and validating autonomous vehicle perception systems.

This work addresses a critical limitation in existing autonomous driving algorithms: their reliance on microscopic driving data that lacks macroscopic traffic context, while macroscopic data alone cannot be readily linked to individual vehicle behaviors. To bridge this gap, the paper proposes the first unified framework that jointly models microscopic vehicle trajectories and macroscopic traffic statistics. By integrating partially observed microscopic state reconstruction with population-level statistical alignment, the approach leverages imitation learning and reinforcement learning to impose dual constraints during policy optimization—ensuring fidelity to both individual ground-truth trajectories and emergent macroscopic traffic patterns. The resulting driving policies generate behaviors consistent with real-world traffic flow when deployed, thereby enabling safe and scalable human–autonomy collaboration in complex traffic environments.

Existing traffic simulation tools struggle to accurately capture the complex interactions between human-driven and autonomous vehicles in mixed traffic environments and lack a systematic synthesis of relevant AI methodologies. This work proposes the first unified taxonomy that encompasses three categories of AI approaches: agent-level behavioral modeling, environment-level simulation, and integration of cognitive and physical information, thereby bridging the research gap between transportation engineering and computer science. By consolidating mainstream simulation platforms, datasets, and evaluation metrics, the study systematically analyzes the limitations of current tools, clarifies the evolutionary trajectory of AI methods in this domain, and puts forward a standardized evaluation protocol along with promising future research directions to advance high-fidelity mixed traffic simulation.

This study addresses the limited interoperability of existing traffic agent models across autonomous driving simulation platforms due to the absence of a unified integration standard, which compromises the consistency and reliability of evaluation results. To overcome this, the authors propose a modular simulation integration architecture based on open standards, uniquely combining the Open Simulation Interface (OSI) and the Functional Mock-up Interface (FMI). This framework establishes a generic, reusable specification for agent model encapsulation, clearly defining interfaces, data mappings, and execution semantics. The approach enables seamless deployment of the same agent model across three major platforms—OpenPASS, CARLA, and CarMaker—with consistent behavioral performance, thereby demonstrating strong cross-platform interoperability and modularity. A reference implementation has been open-sourced to advance standardization in simulation ecosystems.

To address the challenge of extracting high-fidelity microscopic vehicle trajectories from roadside video in dense, heterogeneous traffic—where occlusion, limited field-of-view, and irregular vehicle motion severely degrade tracking accuracy—this work introduces MVT, the first open-source, UAV-based aerial trajectory dataset with centimeter-level precision. Captured over six representative urban corridors in India’s National Capital Region at 30 Hz, MVT provides spatiotemporal coordinates, velocity, acceleration, and fine-grained vehicle class labels. We propose Data from Sky (DFS), an automated trajectory extraction framework integrating manual verification, spatial average speed consistency checks, and probe-vehicle trajectory validation to ensure high confidence and reliability. As the inaugural UAV-derived microscopic dataset tailored to heterogeneous urban environments, MVT spans diverse traffic densities and compositional mixes, enabling empirical discovery of key behavioral patterns—including lane-keeping preferences, speed distributions, and lateral maneuvering characteristics—and supporting downstream research in heterogeneous traffic modeling, simulation, and safety analysis.