This paper introduces RACER, the Rational Artificial Intelligence Car-following model Enhanced by Reality, a cutting-edge deep learning car-following model, that satisfies partial derivative constraints, designed to predict Adaptive Cruise Control (ACC) driving behavior while staying theoretically feasible. Unlike conventional models, RACER effectively integrates Rational Driving Constraints (RDCs), crucial tenets of actual driving, resulting in strikingly accurate and realistic predictions. Against established models like the Optimal Velocity Relative Velocity (OVRV), a car-following Neural Network (NN), and a car-following Physics-Informed Neural Network (PINN), RACER excels across key metrics, such as acceleration, velocity, and spacing. Notably, it displays a perfect adherence to the RDCs, registering zero violations, in stark contrast to other models. This study highlights the immense value of incorporating physical constraints within AI models, especially for augmenting safety measures in transportation. It also paves the way for future research to test these models against human driving data, with the potential to guide safer and more rational driving behavior. The versatility of the proposed model, including its potential to incorporate additional derivative constraints and broader architectural applications, enhances its appeal and broadens its impact within the scientific community.

Demand variations throughout the day and area popularity differences across the city result in spatiotemporal changes in traffic flow. One of the well-known phenomena arising from these changes is tidal traffic, characterized by an imbalance between inbound and outbound traffic on a given road. It reflects the fluctuation in the alignment between transportation system supply and demand. Lane reversal control has been a common supply-side measure for dealing with this urban traffic “sickness” by adapting road capacity allocation to the demand imbalance between two directions of a road. This study investigates the dynamic network capacity allocation control problem in the era of connected and autonomous vehicles (CAVs), which integrates dynamic traffic signal splits and lane reversal controls. Considering the high dimensionality and non-linearity of urban transportation systems, we apply the sparse identification of nonlinear dynamics (SINDy) technique to construct a sparse yet sufficiently accurate surrogate model. This model estimates the forthcoming network traffic state based on the current state and implemented control decisions. The surrogate model is integrated into a model predictive control (MPC) method, forming a SINDy-MPC framework to assist in optimal decision-making in real time. The experiments show that the system identified by SINDy exhibits stability in the presence of Gaussian noise disturbances. The proposed dynamic network allocation control scheme can effectively reduce traffic imbalance, improve traffic efficiency, and enhance traffic resilience against cyberattacks.

Automated Vehicles (AVs), particularly those with Adaptive Cruise Control (ACC), are increasingly integral to intelligent transportation systems, but they bring new cybersecurity challenges. This study explores the subtleties of cyberattacks targeting ACC vehicles, specifically through false data injection, and assesses their impact on traffic dynamics. We innovatively adapt and implement strategically designed cyberattacks in simulations, providing a realistic evaluation of their effects on traffic. Our approach not only synthesizes these attacks but also rigorously tests their detectability against state-of-the-art detection algorithms. The findings reveal the intrinsic difficulty in detecting such stealthily designed attacks, highlighting a significant gap in current cybersecurity measures. Despite the precision of our detection methods, the low recall rates emphasize the stealthiness of these attacks. The open-sourced experiment code is made available at https://github.com/tianyi17/simulations_IV24. This research accentuates the urgent need for more sophisticated detection and defense strategies to protect ACC vehicles against evolving cyber threats, ensuring the reliability and safety of future transportation systems.

Automated vehicles (AVs) hold the potential to significantly improve traffic flow, reducing travel time, energy consumption, and emissions. However, until AVs achieve high market penetration rates, navigating the transition to mixed-autonomy traffic — comprising both AVs and human-driven vehicles (HVs) — presents substantial challenges. While numerous studies have concentrated on AV control within mixed-autonomy environments, human-AV interactions have been largely neglected. To understand the benefits of considering the impact of AVs on their followers in mixed traffic control, we introduce a general framework focused on social interaction-aware benefits. Through this framework, we develop an interaction-aware control approach aimed at optimizing socially compatible traffic flow. The results demonstrate that as social interactions between the AV and its following HVs are considered, the benefits (i.e., vehicle speed mean squared error) for the AV may decrease. In contrast, HVs can gain more benefits when the interaction-aware control strategy is not solely focused on the AV.

While automated vehicles (AVs) are expected to revolutionize future transportation systems, emerging AV technologies also open the door for malicious actors to compromise intelligent vehicles. As the first generation of AVs, adaptive cruise control (ACC) vehicles are particularly vulnerable to cyberattacks. Although recent efforts have been made to understand the impact of attacks on transportation systems, little work has been done to systematically model and characterize the malicious nature of these attacks. In this study, we develop a general framework for modeling and synthesizing two types of candidate attacks on ACC vehicles: direct attacks on vehicle control commands and false data injection attacks on sensor measurements, with explicit characterization of their adverse effects. Based on linear stability analysis of car-following dynamics, we derive analytical conditions that characterize the malicious nature of potential attacks. This ensures a higher degree of realism in modeling attacks with adverse effects, as opposed to simply considering constant or random attacks. The conditions derived provide an effective method for synthesizing strategic candidate attacks on ACC vehicles. We conduct extensive simulations to examine the impacts of intelligently designed attacks on microscopic car-following dynamics and macroscopic traffic flow. Numerical results illustrate the attack mechanism, offering useful insights into understanding the vulnerability of future transportation systems. The methodology developed allows for further study of the widespread impact of strategically designed attacks on traffic cybersecurity, inspiring the development of efficient attack detection techniques and advanced vehicle controls.

The emergence of automated vehicles (AVs) with driver-assist features, such as adaptive cruise control (ACC) and other automated driving capabilities, promises a bright future for transportation systems. However, these emerging features also introduce the possibility of cyberattacks. A select number of ACC vehicles could be compromised to drive abnormally, causing a network-wide impact on congestion and fuel consumption. In this study, we first introduce two types of candidate attacks on ACC vehicles: malicious attacks on vehicle control commands and false data injection attacks on sensor measurements. Then, we examine the energy impacts of these candidate attacks on distinct traffic conditions involving both free flow and congested regimes to get a sense of how sensitive the flow is to these candidate attacks. Specifically, the widely used VT-Micro model is adopted to quantify vehicle energy consumption. We find that the candidate attacks introduced to ACC or partially automated vehicles may only adversely impact the fuel consumption of the compromised vehicles and may not translate to significantly higher emissions across the fleet.

In this work we present a traffic model to simulate network-level traffic evolution under the impact of controlled autonomous vehicles acting as moving bottlenecks. We first extend the Newell-Daganzo method to track the trajectories of moving bottlenecks and calculate the cumulative number of vehicles passing each moving bottleneck. By integrating the solutions to the cumulative number of vehicles passing moving bottlenecks and link nodes as boundary conditions in the link-transmission model, we can incorporate the impact of moving bottlenecks into the flow of traffic at a network scale. We present numerical simulation results that illustrate the effectiveness of the developed model to track the trajectories of the moving bottlenecks and simulate their impact on freeway traffic. Lastly, we present control applications of the developed model to trajectory optimization. The reduced fuel consumption associated with the careful control of AV trajectories in the moving bottleneck framework indicates the potential to considerably improve the flow of traffic by controlling the AVs in a mixed human and autonomous environment.

Adaptive cruise control (ACC) vehicles are proving to be the first generation of driver-assist enabled vehicles. In order to study the impacts of ACC vehicles on string stability and traffic flow characteristics, accurately calibrating microscopic car following models is crucial to simulate inter-vehicle dynamics. While many car following models have been used to simulate car following behavior, a single, continuous function may not describe both acceleration and braking realistically. We propose an asymmetric model which is based on the symmetric optimal velocity relative velocity (OVRV) model and switch parameters under different conditions to realize and reproduce car following dynamics of ACC vehicles. We conduct an analytical string stability analysis and the string stability criterion is derived. The calibration and simulation results show that the proposed asymmetric ACC model reduces model spacing error by up to 38% compared with the symmetric OVRV model. Compared with other commonly used asymmetric car following models in the transportation community, the proposed asymmetric ACC model can reduce spacing error by 44.8%. Furthermore, we validate the derived string stability criterion with a numerical test simulating with a string of vehicles. We conclude that an asymmetric car following model shows more accurate performance in the capture of ACC car following behavior.

Uniform traffic flow has been shown to be unstable in certain flow regimes due to collective behaviors of human drivers, resulting in the well-observed stop-and-go waves. These traffic waves can arise even in the absence of merges, bottlenecks, or lane changing, and may lead to higher vehicle fuel consumption and emissions. In this article, we aim to smooth unstable traffic flow via optimal control of autonomous vehicles (AVs) in a predominantly human-driven traffic flow. These controlled AVs act as mobile actuators in the traffic without changing the way human-driven vehicles (HVs) normally operate. We develop a dynamic model to describe mixed traffic flow in the presence of both HVs and AVs, whose dynamics follow general nonlinear car-following principles. Based on this general framework, we formulate an optimal control problem with the objective of minimizing vehicle speed perturbation, and prove the existence of optimal AV control policy. Following the necessary conditions of optimality prescribed by the well-known Pontryagin’s minimum principle, we present a computational algorithm to determine the optimal AV control strategy and prove its convergence. The mathematical model is further illustrated using the intelligent driver model (IDM) and optimal velocity with relative velocity (OVRV) model for HVs and AVs, respectively. Numerical results are presented to show the effectiveness of the proposed approach on traffic smoothing, as well as the improvement on vehicle fuel economy.

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.

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.

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.