Connected Vehicle Applications Research Articles

Leveraging public cloud infrastructure for real-time connected vehicle speed advisory at a signalized corridor

In this study, we developed a real-time connected vehicle (CV) speed advisory application that uses public cloud services and tested it on a simulated signalized corridor for different roadway traffic conditions. First, we developed a scalable serverless cloud computing architecture leveraging public cloud services offered by Amazon Web Services (AWS) to support the requirements of a real-time CV application. Second, we developed an optimization-based real-time CV speed advisory algorithm by taking a modular design approach, which makes the application automatically scalable and deployable in the cloud using the serverless architecture. Third, we developed a cloud-in-the-loop simulation testbed using AWS and an open-source microscopic roadway traffic simulator called Simulation of Urban Mobility (SUMO). Our analyses based on different roadway traffic conditions showed that the serverless CV speed advisory application meets the latency requirement of real-time CV mobility applications. Besides, our serverless CV speed advisory application reduced the average stopped delay (by 77%) and the aggregated risk of collision (by 21%) at the signalized intersections of a corridor. These prove the feasibility as well as the efficacy of utilizing public cloud infrastructure to implement real-time roadway traffic management applications in a CV environment.

Efficient content caching for 5G assisted vehicular networks

Traffic congestion is one of the major challenges faced by daily commuters in smart cities. An autonomous transportation system with a 5 G-based Cellular Vehicle-to-Everything (C-V2X) communication system is the solution to meet the traffic challenges faced in smart cities. Vehicular networks provide wireless connectivity to enable a large number of connected vehicle applications. Vehicular networks allow vehicles to share their emergency and infotainment traffic by following vehicle-to-vehicle (V2V) or by using vehicle-to-infrastructure (V2I) communication. The infrastructure of vehicular networks mainly comprises multiple Road Side Units (RSUs). Fog computing nodes are placed adjacent to these RSUs to provide quick access to vehicles. For infotainment traffic, vehicles intend to download their required content from the content provider. Caching the same contents from the nearby fog computing node significantly reduces delay with improved quality of service. As there are millions of contents with varying sizes, caching all demanded contents on these fog nodes is not possible due to their limited caching capacity. In this work, we propose an improved content caching scheme for fog nodes to satisfy vehicles and content providers for fair content placement. The proposed algorithm is based on a modified Gale–Shapley technique that considers factors such as content popularity, vehicle connectivity, and quality of the communication channel to optimize the content caching process. Simulation results show that the proposed technique caches a higher number of popular contents with lower downloading time.

Revolutionizing Mobility: Big Data Applications in Transport Planning

Revolutionizing Mobility: Big Data Applications in Transport Planning

A computation offloading method with distributed double deep Q‐network for connected vehicle platooning with vehicle‐to‐infrastructure communications

AbstractCurrent connected vehicle applications, such as platooning require heavy‐load computing capability. Although mobile edge computing (MEC) servers connected to the roadside intelligence facility can assist such separable applications from vehicles, it is a challenge to coordinate the allocation of subtasks among vehicles and MEC servers on the premise of ensuring communication quality. Therefore, an offloading algorithm is proposed based on a double deep Q‐network to solve the placement of subtasks for vehicle to infrastructure and vehicle to vehicle cases. This algorithm considers the randomness of task generation and is model‐free. The MEC server can assist the vehicle in training the neural network and storing relevant state transitions. To improve the performance of the algorithm, the decaying greedy policy is incorporated for faster convergence. The simulation results showed that this algorithm performed well in reducing the dropped subtask rate, average time delay, and total energy consumption.

Low-complexity enhancement VVC encoder for vehicular networks

In intelligent transportation systems, real-time video streaming via vehicle networks has been seen as a vital difficulty. The goal of this paper is to decrease the computational complexity of the versatile video coding (VVC) encoder for VANETs. In this paper, a low-complexity enhancement VVC encoder is designed for vehicular communication. First, a fast coding unit (CU) partitioning scheme based on CU texture features is proposed in VVC, which aims to decide the final type of CU partition by calculating CU texture complexity and gray-level co-occurrence matrix (GLCM). Second, to reduce the number of candidate prediction mode types in advance, a fast chroma intra-prediction mode optimization technique based on CU texture complexity aims to combine intra-prediction mode features. Moreover, the simulation outcomes demonstrate that the overall approach may substantially reduce encoding time, while the loss of coding efficiency is reasonably low. The encoding time can be reduced by up to 53.29% when compared to the VVC reference model, although the average BD rate is only raised by 1.26%. The suggested VVC encoder is also hardware-friendly and has a minimal level of complexity for video encoders used in connected vehicle applications.

Traffic safety performance evaluation in a connected vehicle environment with queue warning and speed harmonization applications

With the increased adoption of connected vehicle (CV) technologies, safety information is becoming increasingly available to drivers. This study investigates three main questions (1) Do CV-based traffic management applications improve safety on roadways with existing infrastructure-based traffic management systems? (2) Can combining two CV technologies have a greater impact on safety than a single CV technology? and (3) Do geometric and traffic composition factors impact the efficiency of CV technologies? We applied a rarely-used CV dataset and conducted a comprehensive simulation analysis of varying conditions and CV penetration rates that studies have not considered. Two CV applications (queue warning and speed harmonization) implemented in the Intelligent Network Flow Optimization experiment in Seattle, WA were evaluated. Results showed that driver safety performance, based on speed metrics (standard deviation and percentage of extreme values) improved under the CV driving conditions. Combining conventional variable speed limit systems with queue warnings also improved safety for CV drivers. Furthermore, the implementation of a single CV application (queue warning) showed positive changes in the aforementioned speed metrics, congestion mitigation, and reduced conflicts. With the two CV applications combined, no significant differences were observed. Additional tests investigated the impacts of lane changes and roadway attributes on safety in the CV environment.

Analysis Framework to Assess Crash Severity for Large Trucks on Rural Interstate Roads Utilizing the Latent Class and Random Parameter Model

Truck freight has high importance to the national economy as it handles more cargo than other types of freight transportation. To improve the safety of commercial vehicles, several studies have focused on determining factors leading to crashes. Parametric models have been extensively employed to explain crash causal factors for heavy trucks. Unlike studies in the past, a comprehensive framework was proposed in this study to compare crash underlying factors utilizing several statistical approaches. The structural equation modeling approach was used to assess latent factors affecting the crash severity of large trucks. In addition, ordinary (binary) logistic and random parameter models were employed to assess the direct effect of the observed data, and the heterogeneity in parameter means was also estimated. Three crash categories were investigated: single-truck crashes, multi-vehicle truck crashes, and total truck crashes. A total of five years of crash data from 2015 to 2019 were analyzed. The results showed that multiple observed variables were factored to measure crash severity. Direct and indirect effects were identified, in which challenging roadway conditions had an indirect effect on crash severity for single-truck crashes. Random parameter logit models indicated that roadway geometry and adverse weather conditions were among the significant contributing factors increasing crash severity for trucks. This study recommends that improving the situational awareness of truck drivers, providing more frequent rest stops, updating variable speed limit algorithms, and integrating roadway geometry information into connected vehicle applications in Wyoming could be considered to assist stakeholders in promoting safety on rural interstate corridors.

A Functional Approach for Analyzing Time-Dependent Driver Response Behavior to Real-World Connected Vehicle Warnings

Understanding driver response behavior to Connected Vehicle (CV) warnings is one of the fundamental tasks in improving road safety. However, previous studies often used aggregated safety measures and simulation environments to accomplish this task. Consequently, time-dependent driver response behavior under real-world conditions has rarely been investigated. This study proposes a new functional data analysis (FDA) approach to analyze time-dependent driver response behavior to CV warnings obtained from the New York City CV Pilot Deployment (NYC CVPD) project. Sparse functional design that can account for irregularly spaced functional measurements is adopted to accommodate the potential noise contaminated real-world CV data. Functional principal component analysis and nonparametric functional linear regression are used to smooth raw driver behavior profile and estimate time-dependent effect of driver response behavior, respectively. The speed compliance application implemented in the NYC CVPD project is used as the case study. By modeling time series of speed data after receiving warnings as continuous functions, the proposed FDA approach reveals new patterns of driver response behavior over time, such as the diminishing effect of drivers’ speed reduction and the increase in variability of driver response behavior over time, which have rarely been explored using traditional approaches. Moreover, the proposed FDA approach supports the extraction of certain traditional safety measures and has the potential to be generalized to analyze various CV applications. The findings of this study can support the calibration of detailed driver behavior in CV environments and facilitate better CV application design and further investigation of the benefits of CVs.

Detection and Reporting of Wireless Channel Congestion and Interference in Connected Vehicle Networks

Connected vehicle (CV) wireless networks based on dedicated short-range communications (DSRC), European Telecommunications Standards Institute (ETSI) intelligent transportation systems (ITS-G5), and C-V2X technologies are susceptible to interference from both unintentional emitters and non-CV devices that may be authorized to share the same or adjacent bands. Such interference may lead to unreliable communication and disruption of CV services with a particular impact on safety-related applications. Surprisingly, considering the safety-critical nature of CV applications, there is no simple mechanism for detecting congestion or interference in such networks over wide areas. To address this gap, we propose and demonstrate that both interference and congestion in DSRC and ETSI ITS-G5 networks can be detected simply and inexpensively using capabilities that are already incorporated into the IEEE 802.11p standard, specifically the flags and statistics generated mostly in the physical layer (physical layer convergence procedure and physical medium dependent) state machines. Such a capability could be realized through a relatively minor software upgrade but would resolve a longstanding but underappreciated concern that CV networks are vulnerable to both congestion and a variety of short-range interferers but lack the capability to detect or report this. Although our focus was on DSRC and ITS-G5, similar considerations apply to related schemes such as C-V2X.

Design of Resilient Supervisory Control for Autonomous Connected Vehicles Approaching Unsignalized Intersection in presence of Cyber-Attacks

The aim of this paper is to ensure safety in a distributed dynamical system, modeled as a Discrete Events Systems (DES), whose feedback control is compromised by a malicious attacker hijacking the system communication channel, being able to insert or remove sensor reading and/or actuation requests. Our focus is autonomous connected vehicle applications and the synthesis of a supervisor that is robust against a large class attacks. Specifically, we model DES supervisors for managing the interactions among self-driving cars when negotiating access to a traffic junction in the presence of an attacker who can manipulate the outputs from the sensors of the system before they can reach the supervisory controller itself. We propose different supervisor solutions to assess the resilience of the intersection crossing and we disclose the best suitable one for the appraised automotive application, as well as its effectiveness.

The impact of weather data on traffic flow prediction models

<span>Traffic flow prediction is an integral part of the intelligent transportation system (ITS) that helps in making well-informed decisions. Traffic flow prediction helps in alleviating traffic congestion as well as in some connected vehicles applications such as resources allocation. However, most of the existing models do not consider external factors such as weather data. Traffic flow in road networks is affected by weather conditions which affects the periodicity of traffic. These effects introduce some irregularity to the traffic pattern, making traffic flow prediction a challenging issue. In this paper, we present a detailed investigation on the impact of weather data on different traffic flow prediction models. The investigation presented in this paper demonstrates how adding weather data could improve the models’ prediction accuracy and efficiency.</span>

Integrated Sensor Fusion Based on 4D MIMO Radar and Camera: A Solution for Connected Vehicle Applications

This article presents an integrated sensor fusion (ISF) solution based on the multiple-input, multiple-output (MIMO) radar, camera, and on-device computing. The MIMO radar is capable of estimating an object’s attributes in four dimensions—range, velocity, azimuth angle, and elevation angle—which can be further used to estimate the length, width, and height of the object. The camera is responsible for object classification based on deep learning. The respective signal processing pipelines and the fusion of results are carried by the on-device computing platform. These two sensors complement each other very well in detecting and classifying traffic objects. Compared with existing sensor fusion solutions based on multiple distributed devices, ISF exhibits superior performance in terms of latency and the total cost of ownership (TCO). It also simplifies time synchronization among different sensors and facilitates the deeper fusion of the signal processing algorithms of different sensors. The comprehensive roadside sensing capabilities provided by the ISF solution can enhance the safety and efficiency of both the automated driving and human driving of connected vehicles.

A hybrid stochastic model predictive design approach for cooperative adaptive cruise control in connected vehicle applications

Wireless communication among connected and automated vehicles (CAVs) enables cooperative driving, particularly using cooperative adaptive cruise control, hence allowing CAVs to safely move closer to each other and improving traffic flow. However, reducing the gap between vehicles may cause collision, especially when a sudden deceleration in the vehicle platoon occurs. Furthermore, if some of the CAVs in the platoon lose communication, even for a short period, they may detect sudden changes in traffic with delay, and their reaction to avoid collision could be unsuccessful. Hence, an efficient emergency braking system can help preserve safety. This becomes even more important in high-speed driving, where a crash can put human lives in danger. This paper presents a discrete hybrid stochastic model predictive control approach to achieve a safe and efficient traffic system through CAV platooning. Three operational modes for vehicles are considered: free following, warning, and emergency braking. Each CAV in the free-following mode basically follows its preceding vehicle while enforcing maximum allowable deceleration in the emergency-braking mode. In the warning mode, the vehicle aims to slightly increase its headway and velocity difference from its predecessor to avoid possible danger. The warning/emergency-braking mode may be activated when the speed difference between a CAV and its preceding vehicle drops below a threshold. It is further assumed that vehicle distance sensing is subject to error. Each vehicle shares its current location, velocity, and future acceleration profile, calculated by solving a mixed-integer programming problem, with its follower vehicles. Simulation studies demonstrate the efficacy of the proposed control design approach compared to existing controllers in the literature in the presence of intermittent communication.

Calibrating stochastic traffic simulation models for safety and operational measures based on vehicle conflict distributions obtained from aerial and traffic camera videos

Proper calibration process is of considerable importance for traffic safety evaluations using simulation models. Allowing for a pure with and without comparison under identical circumstances that is not directly testable in the field, microsimulation-based approach has drawn considerable attention for the performance evaluation of emerging technologies, such as connected vehicle (CV) safety applications. Different from the traditional approaches to evaluate mobility impacts, safety evaluations of such applications demand the simulation models to be well calibrated to match real-world safety conditions. This paper proposes a novel calibration framework which combines traffic conflict techniques and multi-objective stochastic optimization so that the operational and safety measures can be calibrated simultaneously. The conflict distribution of different severity levels categorized by time-to-collision (TTC) is applied as the safety performance measure. Simultaneous perturbation stochastic approximation (SPSA) algorithm, which can efficiently approximate the gradient of the multi-objective stochastic loss function, is used for model parameters optimization that minimizes the total simulation error of both operational and safety performance measures. The proposed calibration methodology is implemented using an open-source software SUMO on a simulation network of the Flatbush Avenue corridor in Brooklyn, NY. 17 key parameters are calibrated using the SPSA algorithm and are compared with the real-world traffic conflicts extracted using vehicle trajectories from 14 h’ high-resolution aerial and traffic surveillance videos. Representative days are identified to create variation envelopes for performance measures. Four acceptability criteria, including control for time-variant outliers and inliers, bounded dynamic absolute and system errors are adopted for results analysis. The results show that the calibrated parameters can significantly improve the performance of the simulation model to represent real-world safety conditions (i.e., traffic conflicts) as well as operational conditions. The case study also demonstrates the usefulness of aerial imagery and the applicability of the proposed model calibration framework, so the calibrated model can be used to evaluate the safety benefits of CV applications more accurately.

Resilient Cooperative Adaptive Cruise Control for Autonomous Vehicles Using Machine Learning

Cooperative Adaptive Cruise Control (CACC) is a fundamental connected vehicle application that extends Adaptive Cruise Control by exploiting vehicle-to-vehicle (V2V) communication. CACC is a crucial ingredient for numerous autonomous vehicle functionalities including platooning, distributed route management, etc. Unfortunately, malicious V2V communications can subvert CACC, leading to string instability and road accidents. In this paper, we develop a novel resiliency infrastructure, RACCON, for detecting and mitigating V2V attacks on CACC. RACCON uses machine learning to develop an on-board prediction model that captures anomalous vehicular responses and performs mitigation in real time. RACCON-enabled vehicles can exploit the high efficiency of CACC without compromising safety, even under potentially adversarial scenarios. We present extensive experimental evaluation to demonstrate the efficacy of RACCON.

Measuring data sharing intention and its association with the acceptance of connected vehicles

Transportation agencies and researchers are optimistic about the potential use of data collected from connected vehicles (CVs) for a variety of traffic and transportation applications. However, the literature lacks the evaluation of data sharing intention of the public for CV applications and its relationship with CV acceptance. This study investigated this gap by conducting a questionnaire survey of 2400 US adults. The results showed that the intention to share CV data depends upon the use of data but not the type of data. The possible uses of CV data were found to be grouped under four categories: driver information, congestion assessment and reduction, and pavement and infrastructure assessment and improvement (ICP); enforcement of traffic rules and fees based on usage (EF); roadside assistance and crash investigation (RC); and research purposes (RP). The data sharing intention for these four data uses vary, though with some commonality, which reflects the overall data sharing intention in CV technology (CVT). In addition, it was found that data privacy and security issues of CVT lower the data sharing intention and CV acceptance. Thus, a number of ways to improve CV acceptance by minimizing the data issues of CVT are discussed. Significant differences in perception of data privacy and security, data sharing intention, and CV acceptance were observed for individuals of different socio-economic and driving-related characteristics.

Developing Statewide Safety Performance Functions for Commercial Trucks Transporting Hazardous Materials on Interstate Rural Roads in Wyoming

Truck crashes in Wyoming are considered a major issue. Nearly 26% of crashes on rural interstate roads involve hazardous materials (HAZMAT) trucks. Wyoming has a high rate of activities related to the energy industry, as it is considered among the top energy producing states in the U.S.A., and mainly relies on the trucking industry for transportation. A crash involving a HAZMAT shipment might have a catastrophic impact because of the nature of the HAZMAT shipment. Therefore, it is crucial to identify the traffic safety performance of HAZMAT trucks, so suitable countermeasures can be identified to reduce the frequency and severity of these crashes. This study aims to develop safety performance functions (SPFs) for crashes involving HAZMAT utilizing traditional negative binomial (NB) models, as well as variations of the NB model, namely, NB-1 and NB-P. The results indicate that HAZMAT truck crashes are associated with vehicle miles traveled, truck percentage, horizontal and vertical characteristics of road geometry, pavement type, and speed limit. The findings from this study show that the NB-P models outperformed the traditional NB models based on likelihood ratio tests, information criteria, and prediction measures. Relevant insights are made on traditional countermeasures, such as road geometry, warning signs, slippery road surface warnings, and climbing lanes, as well as non-traditional countermeasures including updating variable speed limit (VSL) algorithms, adding variable message signs, and integrating roadway geometry information into connected vehicle applications in Wyoming. These could be considered to assist stakeholders and emergency management agencies in better decision making toward safer operations of HAZMAT trucks.

Securely Sharing and Visualizing Connected Vehicle Analytics: THEA CV Pilot Performance Evaluation Dashboard

Dashboards are increasingly being used by organizations to process and visualize complex information and to reduce data complexity for planning and reporting. Their main function is to synthesize information for rapid and smarter decision making. This paper details the development of an innovative interactive dashboard to process connected vehicle (CV) data securely, report CV application evaluation analytics, and monitor CV infrastructure system performance. We detail the methods used to process complex, high-frequency (up to 10 Hz) information generated by more than 1,000 participants’ vehicles in the Tampa Hillsborough Expressway Authority (THEA) CV Pilot deployment over the course of two and half years of operation. The dashboard provides advanced query capabilities and custom visualization via interactive maps, graphics, and dynamic reporting to help inform decision making and securely share information. Further, individual CV application warnings can be analyzed using the warning profile feature that is equipped with visual animation replay. This novel approach not only compensated for the lack of in-vehicle dashboard cameras integrated into the CV Pilot infrastructure to assess behavioral responses to the human–machine interface, but also sped up manual validation time. The dashboard allows different levels of user access with customized views to meet a variety of stakeholder types and needs. This tool has been successfully used by the THEA CV Pilot evaluation team and U.S. Department of Transportation independent evaluators to perform precursory evaluations and to automate and perform false positive assessments of vehicle-to-vehicle and vehicle-to-infrastructure safety and mobility applications.

Weather-Based Lane-Change Microsimulation Parameters for Safety and Operational Performance Evaluation of Weaving and Basic Freeway Segments

It is well recognized that adverse weather conditions have significant negative impacts on safety and mobility of transportation systems. Microsimulation modeling has emerged as a cost-effective tool to quantify the safety and operational effects arising from adverse weather. Developing a realistic microsimulation model necessitates adjusting driving behavior models through trajectory-level data. This study contributes a methodology to update lane-change parameters to develop weather-specific microsimulation models based on different freeway facilities, and ultimately evaluate the safety and operational performance of the roadways. Representative parameters in various weather and facility types were extracted using an automated process. As part of the comprehensive assessment of the adjusted parameters, a weaving section and a basic freeway segment on Interstate 80 in Wyoming were identified as potential candidates. The safety and operational analyses were conducted using VISSIM. Various simulation scenarios were designed based on the field traffic flow data. The safety analysis using three surrogate measures of safety including time-to-collision, deceleration rate to avoid collision, and post encroachment time revealed that adverse weather generated a higher number of conflicts than did clear weather for both facilities. The operational analysis suggested that adverse weather produced lower average speed and higher total travel time and delay than clear weather. The demonstrated methodology could be used in assessing various connected vehicle applications associated with lane change in microsimulation from safety and operational perspectives and could be adopted by transportation agencies to develop weather-based microsimulation models.

A Review on Cybersecurity of Cloud Computing for Supporting Connected Vehicle Applications

In an Internet of Things (IoT) environment, cloud computing is emerging as a technologically feasible and economically viable solution for supporting real-time and non-real-time connected vehicle (CV) applications due to its unlimited storage, enormous computing capabilities, and cost advantage, i.e., cloud computing costs less than owning such systems. However, maintaining cybersecurity is a major challenge in cloud-supported CV applications as it requires CVs and various transportation or non-transportation services to exchange data with the cloud via multiple wired and wireless communication networks. In this article, we review the cybersecurity requirements of cloud-supported CV applications, such as confidentiality, integrity, availability, authentication, accountability, and privacy. Our review also identifies the associated cybersecurity challenges that might impact cloud-supported CV applications and corresponding solutions to these challenges. In addition, we present future research opportunities to prevent and mitigate cybersecurity issues in cloud computing for CV-related applications.