The adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation of ASM, featuring end-to-end calibration using real-world ground truth data. The calibration is formulated as a parameterized kernel optimization problem. The model is calibrated using data from a full-state observation testbed, with input from a sparse radar sensor network. The implementation is developed in PyTorch, enabling integration with various deep learning methods. We evaluate the results in terms of speed distribution, spatio-temporal error distribution, and spatial error to provide benchmark metrics for the traffic reconstruction problem. We further demonstrate the usability of the calibrated method across multiple freeways. This article is reproducible and can serve as a benchmark for various freeway operation tasks.

Analyzing stop-and-go waves at the scale of miles and hours of data is an emerging challenge in traffic research. The past 5 years have seen an explosion in the availability of large-scale traffic data containing traffic waves and complex congestion patterns, making existing approaches unsuitable for repeatable and scalable analysis of traffic waves in these data. This paper makes a first step towards addressing this challenge by introducing an automatic and scalable stop-and-go wave identification method capable of capturing wave generation, propagation, dissipation, as well as bifurcation and merging, which have previously been observed only very rarely. Using a concise and simple critical-speed based definition of a stop-and-go wave, the proposed method identifies all wave boundaries that encompass spatio-temporal points where vehicle speed is below a chosen critical speed. The method is built upon a graph representation of the spatio-temporal points associated with stop-and-go waves, specifically wave front (start) points and wave tail (end) points, and approaches the solution as a graph component identification problem. It enables the measurement of wave properties at scale. The method is implemented in Python and demonstrated on a large-scale dataset, I-24 MOTION INCEPTION. Our results show insights on the complexity of traffic waves. Traffic waves can bifurcate and merge at a scale that has never been observed or described before. The clustering analysis of all the identified wave components reveals the different topological structures of traffic waves. We explored that the wave merge or bifurcation points can be explained by spatial features. The gallery of all the identified wave topologies is demonstrated at https://trafficwaves.github.io/.

The real-world potential of stop-and-go wave smoothing at scale remains largely unquantified. Smoothing freeway waves requires opening a gap large enough for them to dissipate, but that gap is often impractically large. We propose a counterfactual wave-smoothing benchmark that reconstructs a smooth, feasible trajectory from each empirical trajectory by solving a quadratic program with fixed boundary conditions and a maximum-gap constraint, and we use the MOVES model to estimate the resulting emission reduction potential. Applying the framework to nine weeks of weekday peak-period data from the I-24 MOTION testbed, which exhibits rich day-to-day variation in wave dynamics, we find meaningful potential for passenger cars under a 0.1-mile maximum-gap constraint: average CO2 reductions of 9.80% to 14.08% across lanes, with 12.94% to 25.70% in CO, 24.29% to 29.76% in HC, and 29.40% to 36.03% in NOx. Trucks emerge as particularly attractive targets, showing roughly twice the reduction potential of passenger cars.

Most deployed Variable Speed Limit (VSL) systems rely on aggregated low-fidelity traffic detector data, which limits their ability to provide timely responses to emerging downstream slowdowns. To address this limitation, this study introduces a cross-fidelity slowdown prediction framework that learns from high-fidelity trajectory-derived slowdown events while operating solely on low-fidelity detector inputs available in the field. Using real-world data from a freeway corridor, we construct a benchmark dataset and evaluate rule-based, classical machine learning, and deep learning methods. Results show that deep learning methods achieve the best performance under both in-distribution and out-of-distribution testing. Integrating the proposed predictor into an existing VSL system by overriding its outputs improves the accuracy of previously misclassified slow-down cases by over 80%. Finally, a spatio-temporal sensitivity analysis is conducted to examine how the number of detectors and temporal records influence model performance, offering insights for sustainable and scalable freeway management.

This paper describes the persistent monitoring with mounted lidar sensors of a transportation corridor over the course of 120 uninterrupted days in Nashville, TN. The data for these 120 days are publicly released as part of publication of this work. The goal of this monitoring is to provide opportunities to design interventions for unsafe intersections, better understand traffic dynamics, and explore the potential for closed-loop control of vehicle signals and walk signs. Lidar units are installed with some overlapping, and some non-overlapping fields of view, offering coverage of eight locations (five intersections and three mid-block areas) across a span of two miles. Continuous object trajectories for all modes of travel are generated from edge processing of raw lidar point cloud data. Unlike camera-based sensing, lidar is natively privacy preserving. This provides an opportunity for improved reception in communities. The paper provides a full description of the corridor, the types of classifications performed by each lidar installation, and the refresh rates and data types recorded. In addition, sample analyses are given to demonstrate the richness of the data. Sample results include hot spots for near-miss events between classified objects, daily turning count statistical analysis, and out of crosswalk pedestrian activity.

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. These "phantom jams" or "stop-and-go waves,"are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment leveraged a heterogeneous fleet of 100 longitudinally-controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this paper. The MegaController is a hierarchical control architecture, which consists of two main layers. The upper layer is called Speed Planner, and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock on-board sensors. The Speed Planner ingests live data feeds provided by third parties, as well as data from our own control vehicles, and uses both to perform the speed assignment. The architecture of the speed planner allows for modular use of standard control techniques, such as optimal control, model predictive control, kernel methods and others, including Deep RL, model predictive control and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers, or only some. Control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars, and electronic selection of ACC set points in others. The proposed architecture allows for the combination of all possible settings proposed above. Most configurations were tested throughout the ramp up to the MegaVandertest.

This study investigates the assisted lane change functionality of five different vehicles equipped with advanced driver assistance systems (ADAS). The goal is to examine novel, under-researched features of commercially available ADAS technologies. The experimental campaign, conducted in the I-24 highway near Nashville, TN, US, collected data on the kinematics and safety margins of assisted lane changes in real-world conditions. The results show that the kinematics of assisted lane changes are consistent for each system, with four out of five vehicles using slower speeds and decelerations than human drivers. However, one system consistently performed more assertive lane changes, completing the maneuver in around 5 seconds. Regarding safety margins, only three vehicles are investigated. Those operated in the US are not restricted by relevant UN regulations, and their designs were found not to adhere to these regulatory requirements. A simulation method used to classify the challenge level for the vehicle receiving the lane change, showing that these systems can force trailing vehicles to decelerate to keep a safe gap. One assisted system was found to have performed a maneuver that posed a hard challenge level for the other vehicle, raising concerns about the safety of these systems in real-world operation. All three vehicles were found to carry out lane changes that induced decelerations to the vehicle in the target lane. Those decelerations could affect traffic flow, inducing traffic shockwaves.

Purpose: Many trajectories data sets have been openly provided by different teams worldwide during the last decade. The experimental design, data acquisition setup, sensor placement, data analysis and presentation is biased to the ultimate scope of research, financial support, and experimental constraints. While this is understandable, there is a clear need for the adoption of a common and generic template that will act as an umbrella for the presentation of any new dataset. This is important to ensure transparency regarding data acquisition and limitations, applicability in terms of research investigations, complementarity with existing available resources and the realization of benchmarks for different research topics. This paper aims to contribute towards this cause. Method: A common template is used to describe each of recent nine datasets, representative of different data collection methods and research purposes. For each dataset, a dedicated section identifies the primary sources of data errors or incompleteness. In addition, a methodological framework that systematically retraces the full process of trajectory dataset collection, from preparation to sharing, has been identified. This comprehensive approach made it possible to draw lessons and formulate proposals at each stage of the dataset life cycle. Finally, a collective discussion process among all the authors was conducted to define future data collection methods and how to improve data sharing. Results: This paper produces a structured synthesis of lessons and key observations drawn from open-source trajectory datasets. It develops a taxonomy that retraces the full lifecycle of trajectory dataset collection, from preparation to sharing, supported by a critical discussion of current practices. Building on this framework, the paper delivers recommendations and discussion at two levels: (i) general recommendations on data collection and sharing, and (ii) recommendations for new types of trajectory datasets. Discussion: Although the datasets presented and discussed here are only a subpart of the numerous undergoing efforts for trajectory data collection and sharing across the globe, their representativeness is sufficient for a clear definition of guidelines for future initiatives, helping the community to build richer, more interoperable datasets without repeating past limitations.

This review offers a comprehensive overview of current traffic modeling, estimation, and control methods, along with resulting field experiments. It highlights key developments and future directions in leveraging technological advancements to improve traffic management and safety. The focus is on macroscopic, microscopic, and micro-macro models, as well as state-of-the-art control techniques and estimation methods for deploying vehicles in traffic field experiments.

Stop-and-go waves are a fundamental phenomenon in freeway traffic flow, contributing to inefficiencies, crashes, and emissions. Recent advancements in high-fidelity sensor technologies have improved the ability to capture detailed traffic dynamics, yet such systems remain scarce and costly. In contrast, conventional traffic sensors are widely deployed but suffer from relatively coarse-grain data resolution, potentially impeding accurate analysis of stop-and-go waves. This article explores whether generative AI models can enhance the resolution of conventional traffic sensor to approximate the quality of high-fidelity observations. We present a novel approach using a conditional diffusion denoising model, designed to reconstruct finegrained traffic speed field from radar-based conventional sensors via iterative refinement. We introduce a new dataset, WaveX (Ji et al., 2025a), comprising 132 hours of data from both low and high-fidelity sensor systems, totaling over 2 million vehicle miles traveled. Our approach leverages this dataset to formulate the traffic state refinement problem as a spatio-temporal super-resolution task. We demonstrate that our model can effectively reproduce the patterns of stop-and-go waves, achieving high accuracy in capturing these critical traffic dynamics. Our results show promising advancements in traffic state refinement, offering a cost-effective way to leverage existing low spatio-temporal resolution sensor networks for improved traffic analysis and management. We also open-source our dataset, trained model and code to enable further research and applications.

This article presents the first field deployment of a multiagent reinforcement learning (MARL)-based variable- speed-limit (VSL) control system on Interstate 24 (I-24) near Nashville, TN, USA. We design and demonstrate a full pipeline from training MARL agents in a traffic simulator to a field deployment on a 17-mi segment of I-24 encompassing 67 VSL controllers. The system was launched on 8 March 2024 and has made approximately 35 million decisions on 28 million trips in six months of operation. We apply an invalid action masking mechanism and several safety guards to ensure real-world constraints. The MARL-based implementation operates up to 98% of the time, with the safety guards overriding the MARL decisions for the remaining time. We evaluate the performance of the MARL-based algorithm in comparison to a previously deployed non-RL VSL benchmark algorithm on I-24. The results show that the MARL-based VSL control system achieves a superior performance.

This article presents experimental evidence of the ability of a single automated vehicle acting as a controller to effectively dissipate stop-and-go waves in real traffic. The automated vehicle succeeded in stabilizing the speed profile by reducing oscillations in time and speed variations between vehicles during rush hour on I-24 in the Nashville area. We detail the control design, deployment and results obtained in this experiment, conducted as part of the CIRCLES consortium’s “MegaVanderTest” 2022, which involved a total of 100 automated vehicles.

This work introduces a multi-camera tracking dataset consisting of 234 hours of video data recorded concurrently from 234 overlapping HD cameras covering a 4.2 mile stretch of 8-10 lane interstate highway near Nashville, TN. Video is recorded in cooperation with Tennessee State Department of Transportation and its policies. The video is recorded during a period of high traffic density with 500+ objects typically visible within the scene and typical object longevities of 3-15 minutes. GPS trajectories from 270 vehicle passes through the scene are manually corrected in the video data to provide a set of ground-truth trajectories for recall-oriented tracking metrics, and object detections are provided for each camera in the scene (159 million total before cross-camera fusion). Initial benchmarking of tracking-by-detection algorithms is performed against the GPS trajectories, and a best HOTA of only 9.5% is obtained (best recall 75.9% at IOU 0.1, 47.9 average IDs per ground truth object), indicating the benchmarked trackers do not perform sufficiently well at the long temporal and spatial durations required for traffic scene understanding. Video data, scene information, and vehicle trajectories are made publicly available at i24motion.org.

In this paper we propose an automatic trajectory data reconciliation to correct common errors in vision-based vehicle trajectory data. Given "raw" vehicle detection and tracking information from automatic video processing algorithms, we propose a pipeline including (a) an online data association algorithm to match fragments that describe the same object (vehicle), which is formulated as a min-cost network circulation problem of a graph, and (b) a one-step trajectory rectification procedure formulated as a quadratic program to enhance raw detection data. The pipeline leverages vehicle dynamics and physical constraints to associate tracked objects when they become fragmented, remove measurement noises and outliers and impute missing data due to fragmentations. We assess the capability of the proposed two-step pipeline to reconstruct three benchmarking datasets: (1) a microsimulation dataset that is artificially downgraded to replicate upstream errors, (2) a 15-min NGSIM data that is manually perturbed, and (3) tracking data consists of 3 scenes from collections of video data recorded from 16-17 cameras on a section of the I-24 MOTION system, and compare with the corresponding manually-labeled ground truth vehicle bounding boxes. All of the experiments show that the reconciled trajectories improve the accuracy on all the tested input data for a wide range of measures. Lastly, we show the design of a software architecture that is currently deployed on the full-scale I-24 MOTION system consisting of 276 cameras that covers 4.2 miles of I-24. We demonstrate the scalability of the proposed reconciliation pipeline to process high-volume data on a daily basis.

This article introduces a new virtual trajectory dataset derived from the I-24 MOTION INCEPTION v1.0.0 dataset to address challenges in analyzing large but noisy trajectory datasets. Building on the concept of virtual trajectories, we provide a Python implementation to generate virtual trajectories from large raw datasets that are typically challenging to process due to their size. We demonstrate the practical utility of these trajectories in assessing speed variability and travel times across different lanes within the INCEPTION dataset. The virtual trajectory dataset opens future research on traffic waves and their impact on energy.

The Interstate-24 MObility Technology Interstate Observation Network (I-24 MOTION) is a new instrument for traffic science located near Nashville, Tennessee. I-24 MOTION consists of 276 pole-mounted high-resolution traffic cameras that provide seamless coverage of approximately 4.2 miles I-24, a 4-5 lane (each direction) freeway with frequently observed congestion. The cameras are connected via fiber optic network to a compute facility where vehicle trajectories are extracted from the video imagery using computer vision techniques. Approximately 230 million vehicle miles of travel occur within I-24 MOTION annually. The main output of the instrument are vehicle trajectory datasets that contain the position of each vehicle on the freeway, as well as other supplementary information vehicle dimensions and class. This article describes the design and creation of the instrument, and provides the first publicly available datasets generated from the instrument. The datasets published with this article contains at least 4 hours of vehicle trajectory data for each of 10 days. As the system continues to mature, all trajectory data will be made publicly available at i24motion.org/data.

This work presents a novel video dataset recorded from overlapping highway traffic cameras along an urban interstate, enabling multi-camera 3D object tracking in a traffic monitoring context. Data is released from 3 scenes containing video from at least 16 cameras each, totaling 57 minutes in length. 877,000 3D bounding boxes and corresponding object tracklets are fully and accurately annotated for each camera field of view and are combined into a spatially and temporally continuous set of vehicle trajectories for each scene. Lastly, existing algorithms are combined to benchmark a number of 3D multi-camera tracking pipelines on the dataset, with results indicating that the dataset is challenging due to the difficulty of matching objects traveling at high speeds across cameras and heavy object occlusion, potentially for hundreds of frames, during congested traffic. This work aims to enable the development of accurate and automatic vehicle trajectory extraction algorithms, which will play a vital role in understanding impacts of autonomous vehicle technologies on the safety and efficiency of traffic.

Monocular 3D object detection is a challenging task because depth information is difficult to obtain from 2D images. A subset of viewpoint-agnostic monocular 3D detection methods also do not explicitly leverage scene homography or geometry during training, meaning that a model trained thusly can detect objects in images from arbitrary viewpoints. Such works predict the projections of the 3D bounding boxes on the image plane to estimate the location of the 3D boxes, but these projections are not rectangular so the calculation of IoU between these projected polygons is not straightforward. This work proposes an efficient, fully differentiable algorithm for the calculation of IoU between two convex polygons, which can be utilized to compute the IoU between two 3D bounding box footprints viewed from an arbitrary angle. We test the performance of the proposed polygon IoU loss (PIoU loss) on three state-of-the-art viewpoint-agnostic 3D detection models. Experiments demonstrate that the proposed PIoU loss converges faster than L1 loss and that in 3D detection models, a combination of PIoU loss and L1 loss gives better results than L1 loss alone (+1.64% AP70 for MonoCon on cars, +0.18% AP70 for RTM3D on cars, and +0.83%/+2.46% AP50/AP25 for MonoRCNN on cyclists).

The dissipation of stop-and-go waves attracted recent attention as a traffic management problem, which can be efficiently addressed by automated driving. As part of the 100 automated vehicles experiment named MegaVanderTest, feedback controls were used to induce strong dissipation via velocity smoothing. More precisely, a single vehicle driving differently in one of the four lanes of I-24 in the Nashville area was able to regularize the velocity profile by reducing oscillations in time and velocity differences among vehicles. Quantitative measures of this effect were possible due to the innovative I-24 MOTION system capable of monitoring the traffic conditions for all vehicles on the roadway. This paper presents the control design, the technological aspects involved in its deployment, and, finally, the results achieved by the experiment.