Offline reinforcement learning (RL) enables learning decision-making policies directly from historical data, which is advantageous for safety-critical domains like traffic control. However, existing offline RL benchmarks in transportation systems typically rely on simulated data, which may not fully capture the complexities of real-world environments. In this paper, we introduce the first offline RL benchmark for variable speed limit (VSL) control, built from approximately 100 million transitions of real-world interaction data collected from a field-deployed, multi-agent RL-based VSL system on a major freeway. We evaluate five state-of-the-art offline RL algorithms under multiple dataset conditions defined by varying sizes and action noise levels. Through traffic microsimulation experiments, we analyze algorithm performance and generalization, providing insights into the challenges and opportunities of offline RL for intelligent transportation systems. The dataset and benchmark are released at https://github.com/Lab-Work/i24-vsl-orl.

This paper proposes the utilization of a multi-mode ACC based on interpretable Finite State Machine (FSM) to address challenges in infrastructure and surrounding condition changes while meeting macroscopic safety and comfort requirements in traffic flow. Specifically, the paper designs and simulates a merge yield control mode, a dynamic speed change mode, and a safety and monitoring mode switching under defined state transitions with the traditional car-following mode. Advanced ACC algorithms have been applied to improve traffic efficiency and have demonstrated energy savings. Yet they have typically been deployed in a single-use case: car-following mode. In this mode, where the Autonomous Vehicle (AV) maintains an appropriate distance or time gap with the preceding vehicle, decelerating when the gap is small and accelerating when it is large, the system may struggle to guarantee safety and comfort in complex and variable driving scenarios. Although there exist mode-switching ACC and merge mode controllers, in which even involving latitude direction control have been proposed, their dynamics when driving alongside other controlled or human-driving vehicles under a Connected and Autonomous Vehicles (CAVs) traffic environment remains unclear. The paper includes results from an implementation that was successfully tested on the open road, and simulation results that show dampened disturbances from the mode-switching approach, compared to single-mode use of an ACC controller in the same scenarios.

Early and accurate detection of anomalous events on the freeway, such as accidents, can improve emergency response and clearance. However, existing delays and mistakes from manual crash reporting records make it a difficult problem to solve. Current large-scale freeway traffic datasets are not designed for anomaly detection and ignore these challenges. In this paper, we introduce the first large-scale lane-level freeway traffic dataset for anomaly detection. Our dataset consists of a month of weekday radar detection sensor data collected in 4 lanes along an 18-mile stretch of Interstate 24 heading toward Nashville, TN, comprising over 3.7 million sensor measurements. We also collect official crash reports from the Tennessee Department of Transportation Traffic Management Center and manually label all other potential anomalies in the dataset. To show the potential for our dataset to be used in future machine learning and traffic research, we benchmark numerous deep learning anomaly detection models on our dataset. We find that unsupervised graph neural network autoencoders are a promising solution for this problem and that ignoring spatial relationships leads to decreased performance. We demonstrate that our methods can reduce reporting delays by over 10 minutes on average while detecting 75% of crashes. Our dataset and all preprocessing code needed to get started are publicly released at https://vu.edu/ft-aed/ to facilitate future research.

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.

Designing and validating controllers for connected and automated vehicles to enhance traffic flow presents significant challenges, from the complexity of replicating real-world stop-and-go traffic dynamics in simulation, to the intricacies involved in transitioning from simulation to actual deployment. In this work, we present a full pipeline from data collection to controller deployment. Specifically, we collect 772 km of driving data from the I-24 in Tennessee, and use it to build a one-lane simulator, placing simulated vehicles behind real-world trajectories. Using policy-gradient methods with an asymmetric critic, we improve fuel efficiency by over 10% when simulating congested scenarios. Our comprehensive approach includes reinforcement learning for controller training, software verification, hardware validation and setup, and navigating various sim-to-real challenges. Furthermore, we analyze the controller's behavior and wave-smoothing properties, and deploy it on four Toyota Rav4’s in a real-world validation experiment on the I-24. Finally, we release the driving dataset (Nice et al., 2021), the simulator and the trained controller (Lichtlé et al., 2022), to enable future benchmarking and controller design.

Variable speed limit (VSL) control has emerged as a promising traffic management strategy for enhancing safety and mobility. In this study, we introduce a multi-agent reinforcement learning framework for implementing a large-scale VSL system to address recurring congestion in transportation corridors. The VSL control problem is modeled as a Markov game, using only data widely available on freeways. By employing parameter sharing among all VSL agents, the proposed algorithm can efficiently scale to cover extensive corridors. The agents are trained using a reward structure that incorporates adaptability, safety, mobility, and penalty terms; enabling agents to learn a coordinated policy that effectively reduces spatial speed variations while minimizing the impact on mobility. Our findings reveal that the proposed algorithm leads to a significant reduction in speed variation, which holds the potential to reduce incidents. Furthermore, the proposed approach performs satisfactorily under varying traffic demand and compliance rates.

With the rapid development of Internet of Things technologies, the next generation traffic monitoring infrastructures are connected via the web, to aid traffic data collection and intelligent traffic management. One of the most important tasks in traffic is anomaly detection, since abnormal drivers can reduce traffic efficiency and cause safety issues. This work focuses on detecting abnormal driving behaviors from trajectories produced by highway video surveillance systems. Most of the current abnormal driving behavior detection methods focus on a limited category of abnormal behaviors that deal with a single vehicle without considering vehicular interactions. In this work, we consider the problem of detecting a variety of socially abnormal driving behaviors, i.e., behaviors that do not conform to the behavior of other nearby drivers. This task is complicated by the variety of vehicular interactions and the spatial-temporal varying nature of highway traffic. To solve this problem, we propose an autoencoder with a Recurrent Graph Attention Network that can capture the highway driving behaviors contextualized on the surrounding cars, and detect anomalies that deviate from learned patterns. Our model is scalable to large freeways with thousands of cars. Experiments on data generated from traffic simulation software show that our model is the only one that can spot the exact vehicle conducting socially abnormal behaviors, among the state-of-the-art anomaly detection models. We further show the performance on real world HighD traffic dataset, where our model detects vehicles that violate the local driving norms.

Autonomous vehicle-based traffic smoothing con-trollers are often not transferred to real-world use due to challenges in calibrating many-agent traffic simulators. We show a pipeline to sidestep such calibration issues by collecting trajectory data and learning controllers directly from trajectory data that are then deployed zero-shot onto the highway. We construct a dataset of 772.3 kilometers of recorded drives on the I–24. We then construct a simple simulator using the recorded drives as the lead vehicle in front of a simulated platoon consisting of one autonomous vehicle and five human followers. Using policy-gradient methods with an asymmetric critic to learn the controller, we show that we are able to improve average MPG by 11% in simulation on congested trajectories. We deploy this controller to a mixed platoon of 4 autonomous Toyota RAV-4's and 7 human drivers in a validation experiment and demonstrate that the expected time-gap of the controller is maintained in the real world test. Finally, we release the driving dataset [1], the simulator, and the trained controller at https://github.com/nathanlct/trajectory-training-icra.

Accurate and timely detection of large events on urban transportation networks enables informed mobility management. This work tackles the problem of extreme event detection on large-scale transportation networks using origin-destination mobility data, which is now widely available. Such data is highly structured in time and space, but high dimensional and sparse. Current multivariate time series anomaly detection methods cannot fully address these challenges. To exploit the structure of mobility data, we formulate the event detection problem in a novel way, as detecting anomalies in a set of time-dependent directed weighted graphs. We further propose a Context augmented Graph Autoencoder (Con-GAE) model to solve the problem, which leverages graph embedding and context embedding techniques to capture the spatial and temporal patterns. Con-GAE adopts an autoencoder framework and detects anomalies via semi-supervised learning. The performance of the method is assessed on several city-scale travel-time datasets from Uber Movement, New York taxis, and Chicago taxis and compared to state-of-the-art approaches. The proposed Con-GAE can achieve an improvement in the area under the curve score as large as 0.15 over the second best method. We also discuss real-world traffic anomalies detected by Con-GAE.

Advanced driver-assistance systems (ADAS) have matured over the past few decades with the dedication to enhance user experience and gain a wider market penetration. However, personalization features, as an approach to make the current technologies more acceptable and trustworthy for users, have been gaining momentum only very recently. In this work, we aim to learn personalized longitudinal driving behaviors via a Gaussian Process (GP) model. The proposed method learns from individual driver’s naturalistic car-following behavior, and outputs a desired acceleration profile that suits the driver’s preference. The learned model, together with a predictive safety filter that prevents rear-end collision, is used as a personalized adaptive cruise control (PACC) system. Numerical experiments show that GP-based PACC (GP-PACC) can almost exactly reproduce the driving styles of an intelligent driver model. Additionally, GP-PACC is further validated by human-in-the-loop experiments on the Unity game engine-based driving simulator. Trips driven by GP-PACC and two other baseline ACC algorithms with driver override rates are recorded and compared. Results show that on average, GP-PACC reduces the human override duration by 60% and 85% as compared to two widely-used ACC models, respectively, which shows the great potential of GP-PACC in improving driving comfort and overall user experience.

Measuring the built and natural environment at a fine-grained scale is now possible with low-cost urban environmental sensor networks. However, fine-grained city-scale data analysis is complicated by tedious data cleaning including removing outliers and imputing missing data. While many methods exist to automatically correct anomalies and impute missing entries, challenges still exist on data with large spatial-temporal scales and shifting patterns. To address these challenges, we propose an online robust tensor recovery (OLRTR) method to preprocess streaming high-dimensional urban environmental datasets. A small-sized dictionary that captures the underlying patterns of the data is computed and constantly updated with new data. OLRTR enables online recovery for large-scale sensor networks that provide continuous data streams, with a lower computational memory usage compared to offline batch counterparts. In addition, we formulate the objective function so that OLRTR can detect structured outliers, such as faulty readings over a long period of time. We validate OLRTR on a synthetically degraded National Oceanic and Atmospheric Administration temperature dataset, and apply it to the Array of Things city-scale sensor network in Chicago, IL, showing superior results compared with several established online and batch-based low-rank decomposition methods.

End-to-end production of vehicle tracking data from video in real-time and with high accuracy remains a challenging problem due to the computational cost of object detection on each frame. In this work we present Tracking with Crop-based Detection, a method for speeding object tracking in constrained contexts (with stable cameras and relatively-predictable object motion) such as vehicle traffic monitoring. We leverage this context to provide a strong prior for object locations, which we use to 1.) boost detection speed by detecting objects only in regions corresponding to object priors on most frames and 2.) inform the selection of the detector output for each object. We evaluate Crop-based Detection as an extension to the KIOU object tracker (Crop-KIOU) on the UA-DETRAC dataset. The proposed tracker outperforms all other reported algorithms in terms of PR-MOTA, PR-MOTP, and mostly tracked objects on the UA-DETRAC benchmark, establishing a new state-of-the-art. Relative to tracking by detection with KIOU, Crop-KIOU achieves a 26% higher frame-rate and increases accuracy. Furthermore, Tracking with Crop-based Detection can be combined with frame skipping; we show a 149% increase in framerate relative to KIOU with no decrease in accuracy using this combination of methods.

In this article, we assess the string stability of seven 2018 model yearadaptive cruise control(ACC) equipped vehicles that are widely available in the US market. Seven distinct vehicle models from two different vehicle makes are analyzed using data collected from more than 1,200 miles of driving in car-following experiments with ACC engaged by the follower vehicle. The resulting dataset is used to identify the parameters of a linear second order delay differential equation model that approximates the behavior of the black box ACC systems. The string stability of the data-fitted model associated with each vehicle is assessed, and the main finding is that all seven vehicle models have string unstable ACC systems. For one commonly available vehicle model that offers ACC as a standard feature on all trim levels, we validate the string stability finding with a multi-vehicle homogeneousplatoon experiment in which all vehicles are the same year, make, and model. In this test, an initial disturbance of 6 mph is amplified to a 25 mph disturbance, at which point the last vehicle in the platoon is observed to disengage the ACC. The data collected in the driving experiments is made available, representing the largest publicly available comparative driving dataset on ACC equipped vehicles.

Event detection is gaining increasing attention in smart cities research. Large-scale mobility data serves as an important tool to uncover the dynamics of urban transportation systems, and more often than not the dataset is incomplete. In this article, we develop a method to detect extreme events in large traffic datasets, and to impute missing data during regular conditions. Specifically, we propose a robust tensor recovery problem to recover low-rank tensors under fiber-sparse corruptions with partial observations, and use it to identify events, and impute missing data under typical conditions. Our approach is scalable to large urban areas, taking full advantage of the spatio-temporal correlations in traffic patterns. We develop an efficient algorithm to solve the tensor recovery problem based on the alternating direction method of multipliers (ADMM) framework. Compared with existing l 1 norm regularized tensor decomposition methods, our algorithm can exactly recover the values of uncorrupted fibers of a low-rank tensor and find the positions of corrupted fibers under mild conditions. Numerical experiments illustrate that our algorithm can achieve exact recovery and outlier detection even with missing data rates as high as 40% under 5% gross corruption, depending on the tensor size and the Tucker rank of the low rank tensor. Finally, we apply our method on a real traffic dataset corresponding to downtown Nashville, TN and successfully detect the events like severe car crashes, construction lane closures, and other large events that cause significant traffic disruptions.

In certain flow regimes, the ideal uniform vehicle flow on the road is unstable, and stop-and-go traffic develops. The instability that leads to this less fuel-efficient unsteady flow results from the collective behavior of all human drivers. This work studies under which circumstances the presence of a single autonomous vehicle (AV) can locally stabilize the flow, without changing the way the humans drive. If possible, this can enable traffic flow control via very few AVs serving as mobile actuators. First, the analysis of car-following models reveals that in idealized conditions (no system noise), the flow can in fact be made linearly stable by means of a low fraction of control vehicles. Second, we highlight the fundamental limitations of this sparse control when considering models with noise.

This paper poses the joint traffic state estimation and incident detection problem as a hybrid state estimation problem, in which a continuous variable denotes the traffic state and a discrete model variable identifies the location and severity of an incident. A multiple model particle smoother is proposed to solve the hybrid estimation problem, in which the multiple model particle filter is used to accommodate the nonlinearity and switching dynamics of the traffic incident model, and the smoothing algorithm is applied to improve the accuracy of the estimate when data are limited. The proposed algorithms are evaluated through numerical experiments using CORSIM as the true model. The proposed algorithm is also compared with a standard macroscopic traffic estimator via particle filtering and the California incident detection algorithm. The results show that jointly estimating the state and incidents in one algorithm is better than two dedicated algorithms working independently.

Reliable and accurate traffic sensing is the basis of Intelligent Transportation Systems (ITS), which mitigate traffic mobility and safety issues. To promote vast adoption of ITS technologies, rapid deployment and auto-calibration of traffic sensing systems are critical. Aiming at the development of an advanced traffic sensing system for construction zones, this poster presents our preliminary results for detecting vehicles and estimating traffic speeds by applying signal processing and machine learning techniques using Passive Infrared (PIR) sensor data.

This work poses the problem of estimating traffic signal phases from a sequence of maneuvers. We model the problem as an inference problem on a discrete-time hidden Markov model (HMM) in which maneuvers are observations and signal phases are hidden states. The model is calibrated from maneuver observations using either the classical Baum-Welch algorithm or a Bayesian learning algorithm. The trained model is then used to infer the traffic signal phases on the data set via the Viterbi algorithm. When training with the Bayesian learning algorithm, we set the prior distribution as a Dirichlet distribution. We identify the best parameters of the prior distribution for both fixed-time and sensor-actuated signals using numerical simulations and employ them in the field experiments. It is shown that when the model is trained by the Bayesian learning method with appropriate prior parameters from the Dirichlet distribution, the inferred phases are more accurate in both numerical and field experiments. Because the best set of prior parameters for a fixed-time intersection is different from those for sensor-actuated signals, a classification strategy to distinguish between these two types of signals is proposed. The supporting source code and data are available for download at https://github.com/reisiga2/TrafficSignalPhaseEstimation.

Secure reliable position information is indispensable for many transportation systems and services, such as traffic monitoring, fleet management, electronic toll collection, route guidance, vehicle telematics, and emergency response. Unfortunately, civil Global Positioning System (GPS) signals are vulnerable to spoofing attacks. This paper introduces a signal authentication architecture based on a network of cooperative GPS receivers. A receiver in the network correlates its received military P(Y) signal with those received by other receivers (hereinafter referred to as cross-check receivers) to detect spoofing attacks. This paper describes three candidate structures to implement this architecture and evaluates spoofing detection performance through theoretical analyses and field experiments. We show that the spoofing detection performance improves exponentially with increasing number of cross-check receivers. Even if the cross-check receivers are low cost, unreliable, and in challenging environment, cooperative authentication can match, if not outperform, a single high-quality reliable reference receiver in terms of spoofing detection performance.

Traffic monitoring using probe vehicles with GPS receivers promises significant improvements in cost, coverage, and accuracy over dedicated infrastructure systems. Current approaches, however, raise privacy concerns because they require participants to reveal their positions to an external traffic monitoring server. To address this challenge, we describe a system based on virtual trip lines and an associated cloaking technique, followed by another system design in which we relax the privacy requirements to maximize the accuracy of real-time traffic estimation. We introduce virtual trip lines which are geographic markers that indicate where vehicles should provide speed updates. These markers are placed to avoid specific privacy sensitive locations. They also allow aggregating and cloaking several location updates based on trip line identifiers, without knowing the actual geographic locations of these trip lines. Thus, they facilitate the design of a distributed architecture, in which no single entity has a complete knowledge of probe identities and fine-grained location information. We have implemented the system with GPS smartphone clients and conducted a controlled experiment with 100 phone-equipped drivers circling a highway segment, which was later extended into a year-long public deployment.

Automotive traffic monitoring using probe vehicles with Global Positioning System receivers promises significant improvements in cost, coverage, and accuracy. Current approaches, however, raise privacy concerns because they require participants to reveal their positions to an external traffic monitoring server. To address this challenge, we propose a system based on virtual trip lines and an associated cloaking technique. Virtual trip lines are geographic markers that indicate where vehicles should provide location updates. These markers can be placed to avoid particularly privacy sensitive locations. They also allow aggregating and cloaking several location updates based on trip line identifiers, without knowing the actual geographic locations of these trip lines. Thus they facilitate the design of a distributed architecture, where no single entity has a complete knowledge of probe identities and fine-grained location information. We have implemented the system with GPS smartphone clients and conducted a controlled experiment with 20 phone-equipped drivers circling a highway segment. Results show that even with this low number of probe vehicles, travel time estimates can be provided with less than 15% error, and applying the cloaking techniques reduces travel time estimation accuracy by less than 5% compared to a standard periodic sampling approach.

The problem of regulating air traffic in the en route airspace of the National Airspace System is studied using a Eulerian network model to describe air traffic flow. The evolution of traffic on each edge of the network is modeled by a modified Lighthill-Whitham-Richards partial differential equation. The equation is transformed with a variable change, which makes it linear and enables us to use linear finite difference schemes to discretize the problem. We pose the problem of optimal traffic flow regulation as a continuous optimization program in which the partial differential equation appears in the constraints. We propose a discrete formulation of this problem, which makes all constraints (the discretized partial differential equations, boundary, and initial conditions) linear. Corresponding linear programming and quadratic programming based solutions to this convex optimization program yield globally optimal solutions to various air traffic management objectives. The proposed method is applied to the maximization of aircraft arrivals and minimization of delays in the arrival airspace due to exogenous capacity reductions. The corresponding linear and quadratic programs are solved numerically using CPLEX for a benchmark scenario in the Oakland Air Route Traffic Control Center. Several computational aspects of the method are assessed-in particular, accuracy of the numerical discretization, computational time, and storage space required by the method.