Kevin Heaslip

Bibek Poudel, Weizi Li, Kevin Heaslip

Human-driven vehicles (HVs) amplify naturally occurring perturbations in traffic, leading to congestion--a major contributor to increased fuel consumption, higher collision risks, and reduced road capacity utilization. While previous research demonstrates that Robot Vehicles (RVs) can be leveraged to mitigate these issues, most such studies rely on simulations with simplistic models of human car-following behaviors. In this work, we analyze real-world driving trajectories and extract a wide range of acceleration profiles. We then incorporates these profiles into simulations for training RVs to mitigate congestion. We evaluate the safety, efficiency, and stability of mixed traffic via comprehensive experiments conducted in two mixed traffic environments (Ring and Bottleneck) at various traffic densities, configurations, and RV penetration rates. The results show that under real-world perturbations, prior RV controllers experience performance degradation on all three objectives (sometimes even lower than 100% HVs). To address this, we introduce a reinforcement learning based RV that employs a congestion stage classifier to optimize the safety, efficiency, and stability of mixed traffic. Our RVs demonstrate significant improvements: safety by up to 66%, efficiency by up to 54%, and stability by up to 97%.

Bibek Poudel, Lei Zhu, Kevin Heaslip et al.

Modern vision systems can detect, track, and forecast urban actors at scale, yet translating perception outputs to urban design remains limited. We introduce DeCoR, a two-stage reinforcement learning framework that leverages flow observations to co-optimize crosswalk layout and network-level signal control. The design stage encodes the pedestrian network as a graph and learns a generative policy that parameterizes a Gaussian mixture model over crosswalk location and width, from which new crosswalks are sampled. For each layout, a shared control policy learns adaptive signal timings to minimize joint pedestrian and vehicle delay. On a 750 m real-world urban corridor with demand sensed from video and Wi-Fi logs, DeCoR learns a layout that reduces pedestrian arrival time to their nearest crosswalk by 23% while using fewer crosswalks than existing configurations. On the control side, DeCoR reduces pedestrian and vehicle wait time by 79% and 65%, respectively, relative to fixed-time signalization. Further, the control policy generalizes to demands outside of training and is robust to layout changes without retraining.

Jose Tupayachi, Mustafa C. Camur, Kevin Heaslip et al.

Transportation remains a major contributor to greenhouse gas emissions, highlighting the urgency of transitioning toward sustainable alternatives such as electric vehicles (EVs). Yet, uneven spatial distribution and irregular utilization of charging infrastructure create challenges for both power grid stability and investment planning. This study introduces TW-GCN, a spatio-temporal forecasting framework that combines Graph Convolutional Networks with temporal architectures to predict EV charging demand in Tennessee, United States (U.S.). We utilize real-world traffic flows, weather conditions, and proprietary data provided by one of the largest EV infrastructure company in the U.S. to capture both spatial dependencies and temporal dynamics. Extensive experiments across varying lag horizons, clustering strategies, and sequence lengths reveal that mid-horizon (3-hour) forecasts achieve the best balance between responsiveness and stability, with 1DCNN consistently outperforming other temporal models. Regional analysis shows disparities in predictive accuracy across East, Middle, and West Tennessee, reflecting how station density, population, and local demand variability shape model performance. The proposed TW-GCN framework advances the integration of data-driven intelligence into EV infrastructure planning, supporting both sustainable mobility transitions and resilient grid management.

Bibek Poudel, Xuan Wang, Weizi Li et al.

Reinforcement learning (RL) holds significant promise for adaptive traffic signal control. While existing RL-based methods demonstrate effectiveness in reducing vehicular congestion, their predominant focus on vehicle-centric optimization leaves pedestrian mobility needs and safety challenges unaddressed. In this paper, we present a deep RL framework for adaptive control of eight traffic signals along a real-world urban corridor, jointly optimizing both pedestrian and vehicular efficiency. Our single-agent policy is trained using real-world pedestrian and vehicle demand data derived from Wi-Fi logs and video analysis. The results demonstrate significant performance improvements over traditional fixed-time signals, reducing average wait times per pedestrian and per vehicle by up to 67% and 52% respectively, while simultaneously decreasing total wait times for both groups by up to 67% and 53%. Additionally, our results demonstrate generalization capabilities across varying traffic demands, including conditions entirely unseen during training, validating RL's potential for developing transportation systems that serve all road users.

Kaveh Bakhsh Kelarestaghi, Mahsa Foruhandeh, Kevin Heaslip et al.

In this study, we attempt to add to the literature of Connected and Automated Vehicle (CAV) security by incorporating the security vulnerabilities and countermeasures of the Vehicular Ad hoc Networks (VANETs) and their access technologies. Compounding VANETs and modern vehicles will allow adversaries to gain access to the in-vehicle networks and take control of vehicles remotely to use them as a target or a foothold. Extensive attention has been given to the security breaches in VANETs and in-vehicle networks in literature but there is a gap in literature to assess the security vulnerabilities associated with VANETs access technologies. That is, in this paper we contribute to the CAV security literature in threefold. First, we synthesize the current literature in order to investigate security attacks and countermeasures on VANETs as an ad hoc network. Second, we survey security challenges that emerge from application of different VANETs access technologies. To augment this discussion, we investigate security solutions to thwart adversaries to compromise the access technologies. Third, we provide a detailed comparison of different access technologies performance, security challenges and propound heterogeneous technologies to achieve the highest security and best performance in VANETs. These access technologies extend from DSRC, Satellite Radio, and Bluetooth to VLC and 5G. The outcome of this study is of critical importance, because of two main reasons: (1) independent studies on security of VANETs on different strata need to come together and to be covered from a whole end-to-end system perspective, (2) adversaries taking control of the VANETs entities will compromise the safety, privacy, and security of the road users and will be followed by legal exposures, as well as data, time and monetary losses.

Sina Dabiri, Kevin Heaslip

Recently, researchers have shown an increased interest in harnessing Twitter data for dynamic monitoring of traffic conditions. Bag-of-words representation is a common method in literature for tweet modeling and retrieving traffic information, yet it suffers from the curse of dimensionality and sparsity. To address these issues, our specific objective is to propose a simple and robust framework on the top of word embedding for distinguishing traffic-related tweets against non-traffic-related ones. In our proposed model, a tweet is classified as traffic-related if semantic similarity between its words and a small set of traffic keywords exceeds a threshold value. Semantic similarity between words is captured by means of word-embedding models, which is an unsupervised learning tool. The proposed model is as simple as having only one trainable parameter. The model takes advantage of outstanding merits, which are demonstrated through several evaluation steps. The state-of-the-art test accuracy for our proposed model is 95.9%.

Kaveh Bakhsh Kelarestaghi, Mahsa Foruhandeh, Kevin Heaslip et al.

Intelligent Transportation Systems (ITS) are critical infrastructure that are not immune to both physical and cyber threats. Vehicles are cyber/physical systems which are a core component of ITS, can be either a target or a launching point for an attack on the ITS network. Unknown vehicle security vulnerabilities trigger a race among adversaries to exploit the weaknesses and security experts to mitigate the vulnerability. In this study, we identified opportunities for adversaries to take control of the in-vehicle network, which can compromise the safety, privacy, reliability, efficiency, and security of the transportation system. This study contributes in three ways to the literature of ITS security and resiliency. First, we aggregate individual risks that are associated with hacking the in-vehicle network to determine system-level risk. Second, we employ a risk-based model to conduct a qualitative vulnerability-oriented risk assessment. Third, we identify the consequences of hacking the in-vehicle network through a risk-based approach, using an impact-likelihood matrix. The qualitative assessment communicates risk outcomes for policy analysis. The outcome of this study would be of interest and usefulness to policymakers and engineers concerned with the potential vulnerabilities of the critical infrastructures.

Sina Dabiri, Kevin Heaslip

Identifying the distribution of users' transportation modes is an essential part of travel demand analysis and transportation planning. With the advent of ubiquitous GPS-enabled devices (e.g., a smartphone), a cost-effective approach for inferring commuters' mobility mode(s) is to leverage their GPS trajectories. A majority of studies have proposed mode inference models based on hand-crafted features and traditional machine learning algorithms. However, manual features engender some major drawbacks including vulnerability to traffic and environmental conditions as well as possessing human's bias in creating efficient features. One way to overcome these issues is by utilizing Convolutional Neural Network (CNN) schemes that are capable of automatically driving high-level features from the raw input. Accordingly, in this paper, we take advantage of CNN architectures so as to predict travel modes based on only raw GPS trajectories, where the modes are labeled as walk, bike, bus, driving, and train. Our key contribution is designing the layout of the CNN's input layer in such a way that not only is adaptable with the CNN schemes but represents fundamental motion characteristics of a moving object including speed, acceleration, jerk, and bearing rate. Furthermore, we ameliorate the quality of GPS logs through several data preprocessing steps. Using the clean input layer, a variety of CNN configurations are evaluated to achieve the best CNN architecture. The highest accuracy of 84.8% has been achieved through the ensemble of the best CNN configuration. In this research, we contrast our methodology with traditional machine learning algorithms as well as the seminal and most related studies to demonstrate the superiority of our framework.