Search

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%.

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.

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%., Comment: 17 pages, 4 figures, 7 tables

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., Comment: 9 pages, 1 table, 3 figures

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., Comment: 12 pages, 3 figures, 7 tables, Transportation Research Part C: Emerging Technologies

The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. Smart transportation is a framework that leverages the power of Information and Communication Technology for acquisition, management, and mining of traffic-related data sources, which, in this study, are categorized into: 1) traffic flow sensors, 2) video image processors, 3) probe people and vehicles based on Global Positioning Systems (GPS), mobile phone cellular networks, and Bluetooth, 4) location-based social networks, 5) transit data with the focus on smart cards, and 6) environmental data. For each data source, first, the operational mechanism of the technology for capturing the data is succinctly demonstrated. Secondly, as the most salient feature of this study, the transport-domain applications of each data source that have been conducted by the previous studies are reviewed and classified into the main groups. Thirdly, a number of possible future research directions are provided for all types of data sources. Moreover, in order to alleviate the shortcomings pertaining to each single data source and acquire a better understanding of mobility behavior in transportation systems, the data fusion architectures are introduced to fuse the knowledge learned from a set of heterogeneous but complementary data sources. Finally, we briefly mention the current challenges and their corresponding solutions in the smart transportation., Comment: 52 pages, 10 figures