
Zhigang XuChang'an University · Information Engineering
Zhigang Xu
PhD
About
143
Publications
76,238
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,526
Citations
Introduction
Dr. Xu is a Professor with School of Information Eng. @Chang’an University(CU). He is leading a Lab of eXtreme & Universal Transportation Systems(XUTS). He had worked in UC, Davis as a visiting scholar for 1 year. His research focuses on CAVs, ITS and Artificial Intelligence. As a co-leader, he built a CAV test site at CU named CAVTest ( http://blog.sciencenet.cn/blog-556706-1133656.html). He also developed an autonomous vehicle named Xinda. His email address is xuzhigang@chd.edu.cn
Publications
Publications (143)
Connected and Automated Vehicles (CAV) platoon is regarded as a promising means of improving traffic efficiency and safety. This study focuses on addressing a Multi-Vehicle Motion Planning (MVMP) problem for CAVs aiming to form a platoon in the mixed traffic flow with both CAVs and Human-Driven Vehicles (HDV), which utilizes the cooperative capabil...
Coordination of vehicles in on-ramp merging scenarios is crucial for preventing traffic bottlenecks, congestion, and accidents. Connected and automated vehicles (CAVs) with vehicle-to-everything (V2X) communication have the potential to improve vehicle coordination and enhance the safety and efficiency of on-ramp merging. While the existing researc...
Failures of the automated driving system (ADS) in automated vehicles (AVs) can damage driver–ADS cooperation (e.g., causing trust damage) and traffic safety. Researchers suggest infusing a human-like ability, active trust repair, into automated systems, to mitigate broken trust and other negative impacts resulting from their failures. Trust repair...
Autonomous vehicles (AVs) must be thoroughly tested to ensure safety and reliability before marketing. Simulation‐based testing has gained widespread recognition as the essential approach for AV testing by providing sufficient testing scenarios in the virtual environment. Vehicle‐in‐the‐loop (VIL) simulation has the ability to perform comprehensive...
This paper proposed a speed harmonization controller for partially connected and automated traffic. It regulates the flow rate of the entire traffic by adjusting only the target cruising speed of Connected and Automated Vehicles (CAVs). The proposed controller bears the following features: i) compatibility enabled with partially connected and autom...
Conventional fuel consumption prediction (FCP) models using neural networks usually adopt driving parameters, such as speed and acceleration, as the training input, leading to a low prediction accuracy and a poor correlation between fuel consumption and driving behavior. To address this issue, the present study introduced jerk (an acceleration deri...
Based on the four-element model, this paper reviewed the important research progress in vehicle platoon, compared the advantages and disadvantages of different models in each element longitudinally, and summarized the linkage between each element horizontally. The stability criteria are briefly reviewed from three dimensions: local stability, strin...
Deep learning-based intelligent vehicle perception has been developing prominently in recent years to provide a reliable source for motion planning and decision making in autonomous driving. A large number of powerful deep learning-based methods can achieve excellent performance in solving various perception problems of autonomous driving. However,...
Automated agents’ errors will cause various negative influences on humans and their relationships with humans (e.g., reducing user experience). They are increasingly required to have social recovery strategies (e.g., human-like apology and explanation) to mitigate the negative impacts of their errors and maintain resilient human–automation relation...
Car-following (CF) behavior is a fundamental of traffic flow modeling; it can be used for the virtual testing of connected and automated vehicles and the simulation of various types of traffic flow, such as free flow and traffic oscillation. Although existing CF models can replicate the free flow well, they are incapable of simulating complicated t...
This paper presents an optimal vehicle speed trajectory generation methodology on an isolated signalized intersection under mixed traffic environment. The proposed model contains platoon management, arrival time prediction, speed trajectory generation and vehicle control. The proposed model considers fuel consumption and driving comfort. Field expe...
Recently, many studies have shown that during the transition period of the coexistence of autonomous vehicles (AVs)/connected automated vehicles (CAVs) and human-driven vehicles (HDVs), a dedicated lane (DL) for AVs/CAVs can improve traffic throughput and lower collision risk, which has become a hot topic in the field of intelligent transportation...
Due to the inevitable existence of wireless communication delay, the string stability of cooperative adaptive cruise control (CACC) platoon systems may not be guaranteed if the controller gains are not tuned in time. Most relevant studies discussed how to determine the stable region of controller gains under different communication delays, but seld...
Paper Published in Ergonomics International Journal: Online communication until now has involved only two of our senses: sight and hearing. However, research is emerging to communicate smell in numerous human-based applications. This paper reviews several general applications of smell, discusses the status of implementing smell to improve road safe...
Automated vehicle (AV) technology is likely to influence transportation, mobility, and society dramatically. The year 2020 was a horizon year for the AV, as manufacturers expected commercial AVs to be available to the general market. However, we experienced one cycle of hyperbole for these “self-driving” cars, which are still unavailable to consume...
Many studies have simulated traffic behavior at signalized intersections using various Car-Following (CF) models. However, the performance of which CF Model is superior at signalized intersections has not been thoroughly analyzed and evaluated. In this study, two novel Artificial Neural Network (ANN) CF models, the Convolutional Neural Network—Long...
The current platoon control strategies of connected autonomous vehicles (CAVs) focus on controlling the fixed intervehicle distance, i.e., the string stability of the platoon system. Here, we aimed to design a CAV platoon control strategy based on a constraint-following approach to solve the problem of platoon starting. As the resistance of the veh...
Automated vehicles (AVs) have potential to impact transportation, mobility, and society considerably in the future. Many beliefs surrounding this technology are criticized as “misconceptions” by transport experts, developers, journalists, and communicators. Understanding how the public views these beliefs offers insights for improving public commun...
Closed field testing of Connected and Automated Vehicles (CAV) is an essential pillar for verifying the functionality and performance of CAV and promoting its large-scale deployment. Recently, many closed test fi elds in the world have been newly built or rebuilt for testing CAV such as M-City in USA and AstaZero in Sweden. However, few constructio...
We are entering an era of automated vehicles (AVs), which has potential to improve road safety considerably. A compelling user experience is crucial to AV adoption in the future commercial market. The automated driving system (ADS) that replaces human drivers should be perceived as very useful before the latter are willing to give up their control...
The V2X and cooperative vehicle infrastructure system (CVIS), which leverage the efficient information interactions through V2V, V2I, V2P, and V2N, are known as the advanced and effective technology in reducing traffic accidents and improving traffic efficiency. The complex technical characteristics of V2X and highly reliable service demand of typi...
Automated vehicles (AVs) will be at the stage of human–machine cooperative driving probably for a long term and their control is shared by two drivers: the human driver and the automated driving system (ADS). ADS failures are a major contributor to the disengagements of AV testing on public roads and influence human–ADS interactions. The impact of...
To solve the problem of performance deterioration for the inertial navigation system (INS) and global navigation satellite system (GNSS) integrated navigation system during GNSS outages, a position prediction algorithm based on empirical mode decomposition (EMD) and a long short-term memory (LSTM) network is presented. First, we propose a filtering...
Vehicle platooning is a perspective technique for intelligent transportation systems (ITS). Connected and automated vehicles (CAVs) use dedicated short-range communication (DSRC) to form a convoy, in which the following vehicles can receive the information from their preceding vehicles to achieve safe automated driving and maintain a short headway....
Traditional image-based traffic congestion estimation methods generally include two steps, which first extract the vehicles from the surveillance images, then calculate the congestion index using the vehicle counts. When working with vast amount of video frames, these approaches are time-consuming and hardly guarantee the real time detection of tra...
Autonomous vehicle (AV) is expected to be the ultimate solution for traffic safety, while autonomous emergency braking (AEB), as a crucial and fundamental active safety function of AV, has excellent potential for reducing fatalities and improving road safety. Although AV has the ability to cope with harsh conditions, it is supposed to be tested ful...
Vehicle detection in traffic surveillance images is an important approach to obtain vehicle data and rich traffic flow parameters. Recently, deep learning based methods have been widely used in vehicle detection with high accuracy and efficiency. However, deep learning based methods require a large number of manually labeled ground truths (bounding...
Compared to traditional adaptive cruise control (ACC), cooperative ACC (CACC) can improve the response sensitivity of the following vehicles by using additional information, e.g., the acceleration of preceding vehicles, that is transmitted via inter-vehicle wireless communications. Thus, a platoon with CACC mode obtains a shorter time headway, ther...
With the rapid growth of the number of vehicles, the traffic problems of expressway are becoming more and more serious. Vehicular platoon technology can effectively solve these problems and it can also improve road capacity and safety. But the current test of vehicular platoon focuses on 2D scenes lacking 3D scenes which can simulate the real envir...
Pavement crack images typically have the characteristics of uneven distribution of illumination, strong noises, and a small proportion of cracks. Differentiating the cracks from the background image with the traditional grayscale analysis and edge detection methods is difficult. To solve this problem, an algorithm based on multi-scale shape analysi...
Frequent lane-change of vehicles can have a serious impact on traffic safety and traffic congestion. In the era of the internet of vehicles, it is helpful to regulate driver’s driving behavior by detecting frequent lane-change behaviors and promptly alerting the driver. In this paper, the accelerometer and gyroscope data collected by the smartphone...
With the implement of Intelligent Vehicle Infrastructure System (IVIS) and automated driving, the requirement of setting a Connected Automated Vehicle (CAV) dedicated lane in highway is increased. However, the penetration of CAVs is low at the beginning of this application, and it will increase gradually in the future. Therefore, it is necessary to...
Precise vehicle localization is critical for various ITS applications. The Global Positioning System (GPS) and the Strap-down Inertial Navigation System (SINS) are two common techniques in the field of vehicle localization, but accuracy, reliability and real-time performance of these two techniques can not satisfy the requirement of some critical I...
Traffic incidents are recognized as a key contributor to non-recurrent congestion, which causes many negative effects in economy, environment, health and lifestyle. In this article, we investigate an incident management policy considering both signal control and route choice, which presents a real-time systematic effort to provide a rapid recovery...
Connected and automated vehicles (CAVs) have attracted much attention of researchers because of its potential to improve both transportation network efficiency and safety through control algorithms and reduce fuel consumption. However, vehicle merging at intersection is one of the main factors that lead to congestion and extra fuel consumption. In...
Purpose
Precise vehicle localization is a basic and critical technique for various intelligent transportation system (ITS) applications. It also needs to adapt to the complex road environments in real-time. The global positioning system and the strap-down inertial navigation system are two common techniques in the field of vehicle localization. How...
Although mixed traffic, including both autonomous vehicles (AV) and human-driven vehicles (HV), is expected to prevail in the foreseeable future, our current understanding of the longitudinal characteristics of mixed traffic is limited and, in particular, lacks evidence from field experiments. To bridge this gap, we designed and conducted a set of...
An accurate fault detection and diagnosis system is of great importance for autonomous vehicles to prevent the potential hazardous situations. In this paper, we propose a fault detection and diagnosis system based on hybrid approaches. First, to detect the state faults of the autonomous vehicle, One-Class Support Vector Machine (SVM) method is adop...
Numerous fast heuristic algorithms, including shooting heuristics (SH), have been developed for real-time trajectory optimization, although their optimality has not yet been quantified. This paper compares the performance between fast heuristics and exact optimization models. We investigate a core trajectory optimization problem as a building block...
Due to the rapid development of vehicular transportation and urbanization, traffic congestion has been increasing and becomes a serious problem in almost all major cities worldwide. Many instances of traffic congestion can be traced to their root causes, the so-called traffic bottlenecks, where relief of traffic congestion at bottlenecks can bring...
Vehicle detection in traffic surveillance images is an important approach to obtain vehicle data 2 and rich traffic flow parameters. Recently, deep learning based methods have been widely used in 3 vehicle detection with high accuracy and efficiency. However, deep learning based methods 4 require a large number of manually labeled ground truths (bo...
This paper presents an offline mapping algorithm for autonomous vehicles (AV) with low-cost sensors. The mapping algorithm consists of five key steps. First, data pre-processing is conducted to calibrate the original odometry data. Then, based on a 2D laser scanner and the calibrated odometry data, a virtual 3D light detection and ranging (LiDAR) i...
Autonomous vehicle (AV) technology is widely studied in both industrial and academic communities since it is regarded as a promising means for improving transportation safety and efficiency. Lane changing is a critical link for higher‐level AV operations. However, few studies on AV lane changing consider the dynamics of surrounding vehicles, partic...
Intelligent Vehicle (IV) is expected to revolutionize the way vehicles operating in the next few decades. The most commonly used method to test the functionality of the IV is to use the IV testbed for operable and economic reasons. However, the traditional testbed only has the ability to test the longitudinal movement and is not capable of studying...
The public had expressed their resistance and negative attitudes to self-driving vehicles (SDVs). Positive change in attitudes is critical for their diffusion. However, it gets limited scholarly attention. In a field experiment (N = 300), we recorded changes in attitude structure (positive, negative, ambivalent, and indifferent) toward the issue of...
It is vital that autonomous vehicles acquire accurate and real-time information about objects in their vicinity, which fully guarantees the safety of the passengers and vehicle in various environments. Three-dimensional light detection and ranging (3D LIDAR) sensors can directly obtain the position and geometric structure of an object within its de...
Co-operative Adaptive Cruise Control (CACC) uses wireless communication between vehicles to form a vehicle platoon. It has been proven that CACC aids in the stability and efficiency of traffic flow, and also reduces the energy consumption of the vehicles by lowering air resistance of the following vehicles. However, communication delay is a natural...
Driving safety has been a hot topic in recent vehicular research. However, research on active control strategy, by which an accident might be avoided before it really happens, is still lacking, especially those appealing to machine learning methods with real traffic data. In addition, previous works constructed models with only one or a few factors...
Based on the technical framework of automated highway systems (AHSs), the influence of different driving factors such as primary application, communications technology, green energy technology, and automated driving technology, the evolution of concepts, development of technology, and future changes in intelligent roads (IRs) were reviewed in this...
Abstract: The bounded rationality characteristic of evolutionary game was used to implement thenetwork selection,and the network resource of heterogeneous vehicular network system wasevenly distributed. The fairness of the system was guaranteed by optimizing evolutionary gamewith two-layer game while some of the vehicles can transmit message in ext...
Abstract: The bounded rationality characteristic of evolutionary game was used to implement thenetwork selection,and the network resource of heterogeneous vehicular network system wasevenly distributed. The fairness of the system was guaranteed by optimizing evolutionary gamewith two-layer game while some of the vehicles can transmit message in ext...
This paper presents a dynamic lane-changing model for Autonomous Vehicle (AV) incorporating human driver behavior in mixed traffic. The proposed model includes four key components, car following (and lane-keeping), lane-changing decision, dynamic path generation, and model-predictive-control- (MPC-) based joint trajectory control. AV longitudinal c...
Recent studies on motion planning methods of intelligent connected vehicle(ICV) are analyzed in this paper. In terms of working space,time,and objective,ICV’s motion planning isdivided into four subtasks:route planning,path planning,maneuver planning,and trajectory planning. Past research and applications of the techniques of vehicle intelligence a...
Intelligent vehicle infrastructure cooperative technique is the key to resolving thedrawbacks of the current intelligent and autonomous vehicles. The development of a connectedand automated highway makes this technique a potential platform. However,it is still a challengeto determine how the road side unit (RSU) disseminates the information from ro...
The vehicle-in-the-loop simulation test methodc.anvalidate the performance ofautonomous vehicles safely and efficiently in complex environments and extreme conditions. Thispaper develops an indoor rapi击testing platform for autonomous vehicles based on vehicle-in-the-loop. This platform is comprised of seven subsystems:front axle rotatable drum benc...
Owing to the advancement in autonomous driving technology,testing tools and testingmethods for conventional automobiles cannot meet the validation requirements of autonomousvehicles. Scenario-based virtual validation methods have technical superiority with respect totesting efficiency and time consumption. Such methods can aid in conducting autopil...
From the four aspects of airport infrastructure construction,airport operation scale,air-port service quality,and airport transportation geography conditions,ten indicators forevaluating airport competitiveness are established,and 36 domestic airports are selected as re-search objects. The weight of 10 evaluation indexes are calculated by entropy w...
With the improvement of the level of automatic driving, the test tools and test methods for traditional cars have been unable to meet the needs of autonomous vehicle testing. The scenario-based virtual test method has great technical advantages in terms of test efficiency and test cost. It is an important means for future auto-driving vehicle test...
Signalized intersections area a key area in the urban traffic networks, but the frequent stop-go behavior of vehicles makes the intersections congested. The paper firstly uses IDM (intelligent driver model) to analyze the string and local stability of the car following model, as well as the conditions for generating traffic oscillation at the signa...
For self-driving vehicles (SDVs), do their benefits to society outweigh their risks? Or their risks outweigh their benefits? Public responses to these questions were not yet surveyed previously. A total of 1032 participants in China were asked this question. Their answers showed that 42.4% thought that the benefits of SDVs are higher than their ris...
We focus on the pathways (affective vs. cognitive) that guide people’s acceptance of road tests (ART) for self-driving vehicles (SDVs) and behavioral intention (BI) to use SDVs, and propose and test a psychological model to explain these two behavioral responses (i.e., ART and BI) based on the trust heuristic and affect heuristic. These heuristics...
Most conventional heterogeneous network selection strategies applied in heterogeneous vehicular network regard the performance of each network constant in various traffic scenarios. This assumption leads such strategies to be ineffective in the real-world performance-changing scenarios. To solve this problem, we propose an optimal game approach for...