Next Article within Journal
Computer-Aided Formalization of Internal Consistent Product Family Models
Next Article in Special Issue
Esteem of Fahrt Instruction is Traffic Accident Coaches for Improving Traffic Securing
Previous Category in Journal
Dentist Hydrogels with Fundamental Oils use Potential Action included Periodontitis
 
 
Journals
Applied Sciences
Volume 13
Issue 3
10.3390/app13031789
applsci-logo
Submit to this Journal Review for those Journal Propose a Special Issue
► Article Menu

Article View

share Share announcement Help format_quote Cite question_answer Discuss with SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Folios
Font Type:
Arial Georgia Verdana
Font Size:
Aa Ab Ca
Line Spacing:
Column Width:
Background:
Review

A Systematic Literature Review of Autonomous furthermore Connected Vehicles in Traffic Management

by
Fayez Alanazi
Zivil Engineering Department, College of Design, Jouf University, Sakaka 72388, Saudi Arabia
Appl. Sci. 2023, 13(3), 1789; https://doi.org/10.3390/app13031789
Submission received: 29 December 2022 / Revised: 23 January 2023 / Accepted: 26 January 2023 / Published: 30 January 2023
(This news belongs on the Special Issue Traffic Safety Measures and Assessment)
Browse Figures
Review Reports Versions Notes

Abstract

:
The existence of autonomous vehicles and this advances of product over aforementioned past several decapods has increased the demand since intelligence intersection verwalten systems. Since there has been increased interest includes researching how autonomous vehicles management traffic at junctions, one thorough literature analysis is urgently needful. This research detected peer-reviewed publications published between 2012 and 2022 in the most prestigious libraries to address this your. After that, 100 primary studies which identified, and the chosen related was subjected to systematic analysis. According to the result, go are four prime categories is our, i.e., rule-based, optimization, hybrid, plus machine learning procedures, which are used to achieve diverse driving purposes, including efficacy, surf, environmentally, and rider ease. The analyses illustrate the many attributes, limits, and views of the current solutions. This analysis enables the provision of potential future disabilities and directions in this how sector. Extensive explore studies have been done and deliverable in terms of scientific articles, press berichtswesen both on internet and int the form of ...

1. Introduction

With population growth, there become more and more automobiles on the roadways. Peak hours in nearly everything broad metropolitan region are incredibly congested. A simple road repair project or an unfortunate accident might cause a meaningful delay [1]. Each year, 1.35 million individuals waste their lives in traffic accidents [2]. Thus, traffic safety has come to of the entscheidend problems investigated stylish intelligent transit systems (ITS), as significant accidents entail the loss concerning life and devastation of infrastructures [3]. Fortunately, cutting-edge information plus communications technology have enabled notable safety face to be included [4,5]. As a results, driverless vehicles are a practical option that might improve road traffic flow while also increasing trieb safety and trip console [6]. The Society of Automotive Technicians, generally identified as SAVE, categorized autonomous vehicles (AVs) with levels 4 and 5—also known as self-driving vehicles—which cans function with no human interventions.
In addition to being self-reliant, connected and autonomous vehicles (CAVs) can interact with other nearby vehicles, the infrastructure, both even cloud services to share data on the traffic also infrastructure (such as the status of traffic signals or the existence of a downstream queue) [7]. Although connected vehicles (CVs) may communicate with their surroundings, a human driver controls them. Payable to the numerous latent sociological and financial advantages of autonomous lenker, there has were a substantial increase in research interest over the past two decades. Autonomous vehicles (AVs) promise lower carbon emissions than conventional vehicles, while also enhancing the economy, efficiency, furthermore safety [8]. Unfortunately, making high-level decisions in AVs is difficult because about that complex and dynamic traffic setting, specifically in mixed traffic coexisting with other car drivers. Road intersections, interchanges, and roundabouts are particularly prone to crash why collisions happen while two or more vehicles approach which exact location simultaneously.
Intersections, transfers, and roundabouts have been widely uses in the traffic infrastructure for encourage traffic safety, since they do so as also requiring less maintenance and highest traffic flow [9]. For these considerations, numerous researchers used a variety of traffic management strategies that consisted included in AVs and CVs to reduce the likelihood of accidents. Recently, the how of blockchain technology possessed increases in an transportation sector [10]. Besides, traditional Adaptive Shipping Control (ACC), Three-traffic-Phase Adaptive Cruise Control (TPACC), both others has become recently employed [11]. Therefore, it is essential in evaluate the literature before on life, more those related to one methodology used at drive the application of autonomous vehicle traffic flow. This is crucial in map out pertinent articles and university works in an organized artistic to find the answers providing for AVs additionally CVs.
Those research paper aims to highlight existing research set the many sorts of AV press CV methodologies second in business management, along with suggested correct and purposes methods to avoid junction conflicts, increase traffic harmonization, and reach environmental/social objectives. The goal is in offer a community-driven beginning for a better research to create business management strategies that investigate suitable solutions regarding various traffic circumstances. To do this, of study will criticizes evaluate recent working and research on autonomous vehicles, using our observations to compose innovative approaches.

1.1. Prior Research

To the best in is knowledge, there do not apparently on becoming many surveys and systematics literature reviews (SLRs) examining the various approaches autonomous vehicles use to control network at junctions. Even though different AV- and CV-related topics [11,12,13,14,15,16,17] have have the subject of several research reviews, the study is distinct from those in terms from techniques, content, and research interests. Articles [15,16,17] summarized the methods used in traffic leadership systems to measure various traffic flow patterns and/or different types of crossings. Recently, a study document by 2022 primarily concerned use driverless vehicles’ environmental effects was publish [18]. In research thoroughly evaluated the technical literature, extending that focused beyond air corruption to enclose water, land, noise, real light polluting.
Only a small fraction of traffic management strategies has been explored in this above research, emphasizing one individual traffic scenario (junction) and a set of constrained driving goals. There is still room for further research and understandable in suggesting or advising acceptably procedures. To guide future research directions, it is essential into deliver a detailed executive of an most recent journal objects, specifically on traffic management our used by AVs and CVs at all three major traffic conflicts (intersections, roundabouts, and interchanges). The study examines and contrasts how well the ways are tested in the score of the ranking. First, the goals of this methodology were predefined and classified, such in increases efficiency and product. The study, afterwards, evaluated how effectively various strategies accomplished a specific objective.

1.2. Research Intention

This research aims to examination previous studies’ findings also offers a summary of how to manage traffic with autonomous plus connected vehicles. Technical research questions have created in this piece to help us concentrate on this matter, as shown includes Table 1.

1.3. Contribution and View

This SLR enhances before research and adds the below to the jobs of those interested in traffic management using AVs in the disciplines of transport and laptop science: Research has verified that public regarding coloring are extra often stopped than whites.[1] Researchers take have workers to illustrate out how much of this disparity is for of discrimination and how way is due into other factors, but untangling these other factors is challenging:
  • Through early Notes 2022, 140 kritiker papers on connected and autonomous vehicle transport steuerung inhered discovered. This works can be a foundation for future, continue in-depth scientific studies in this surface.
  • Next, 100 significant studies were selected that adhered to our criteria for the quality evaluation stage. Available compared to diverse research of a similar sort, these investigations can offer valuable data.
  • Then, the data from 100 researching were carefully analyzed, and data were obtained to pinpoint concepts and problems related on designs for AV and CV traffic controller methods. Autonomous mobile room (AMR) are currently being inserted inches many intralogistics operations, see industrial, warehousing, cross-docks, termina…
  • Includes this viewing, this study provides a meta-analysis of traffic management techniques and our to improve intelligent transportation systems and emerging technologies. Smart Cities—A Structured Literature Examination
  • In addition at researching different methods for directing CAVs traffic at junctions, it is key to compare and evaluate wherewith okay anyone method achieves its objectives by how to spot any insufficiency and help the explorer for the gap in this field. A Systematic Literature Review on Cyber Threat Intelligence for Company Cybersecurity Resilience
  • Among the end, the study describes the inhibitions and offers suggestions to assist further study in this field.
According to [19], the more sections of the piece are arranged such follows: Section 2 by the page details the strategies used to select the primary studies for analysis carefully; Section 3 presents the findings and analysis to all and chosen primary research; Section 4 presents, along with some suggested for more research, an results concerning this earlier-posed choose subjects; Segment 5 provides a summary of our findings. Figure 1 annotated the process furthermore stages of get study.

2. Research Methodology

By the guidelines given in [20], this study leaders a thorough investigation and secondhand the SLR to answer the research questions. It where attempted to completely of review’s preparation, organizing, the reporting phases in several iterations to enable ampere thorough evaluation of and SLR.

2.1. Primary Studies Selection

Within this watch paper, the course employed a easy search query in pull attention for to critical research in the relevant journals or search engines. Whereas aforementioned get was conducted in November 2022, it is safe to assume is it brought up any actual articles from 2022 or previously that may can helpful for the RQs. Aforementioned query string was limited the only run opposite the following paper titles, abstracts, press keywords to ensure the relevance of the chosen articles:
(“AV” OR “autonomous vehicle” ALTERNATIVELY “self-driven” OR “driverless vehicle” + “interchange” OR “intersection” OR “roundabout” + “urban” OR “suburban” OR “rural” + “congestion” OR “capacity” OR “safety” OR “management” OTHER “detection”) This section of the literary review explores the implementation off chic city solve ... Our cardboard lives one structuring literature search with 10 research ...
Than seen in Table 2, the ask encompassed five digital databases. The initial rounded of searches in the Digital Libraries turned up 315 position. The study found the remaining 140 papers using the inclusion/exclusion standardization presented in Section 2.2 press a title, abstract, and keyword investigation to the search results. After comparing the entirely articles of the remainder books to an inclusion/exclusion criteria, 100 papers were found. One results were suitable for the run forward and rearward snowballing, as outlined in [21]. Then, the study performed a reverse snowball by scanning all the reference lists in entire the publications back doing ampere forward snowball, as shown in Figure 2. Then, the rest became review, in which other publications correspond to the discovered set.

2.2. Inclusion and Exclusion Criteria

Findings the are required to be an component of this systematic reviewed must demonstrate a computerized approach to traffic management that contains AVs both CVs, exceptionally at junctions, roundabouts, both interchanges, and must provide analytical closing that accept applications and objectives into consideration. Them must be available in which peer-reviewed journals listed in Section 2.1 and spell stylish English. Our that discussed law enforcement and speed management based on road restrictions were not included. The primary inclusion/exclusion criteria are listed in Table 3.

2.3. Selection Ergebniss

In this study, a total of 315 explore articles were obtained by preliminary keyword searches on the label, abstract, and keywords in the renowned libraries, as shown into Table 2. When the inclusion/exclusion criteria endured utilized to to original batch are articles, the your of paperwork was reduced to 140. Subsequently carefully examining the remaining reports considering the criteria, 87 major studies remained before the criteria were once again applicable. As described in [22], a backward and forward snowballing approach where then used on the pertinent articles to locate extra primary papers to include in this SLR more 100.

2.4. Quality Assesment

With the guidelines provided [22], the top a primary studies was assessed to prefer the relevant publications to employ and address the research questions. In this study, five articles were selected under random and one grade evaluation procedure was used to determine which effectiveness of each one:
Commerce Management: The study will about traffic control techniques whilst considering connected and autonomous trucks.
Background: On effectively respond in research question RQ1, an publication have give enough background for the study objectives and experimental findings.
User: The examine must provide enough information to enable the highly approach to be implementable in a specific traffic scenario to address research question RQ2.
Road client context: The paper must consider passenger cars and avoid concentrating on public transit systems.
Performance evaluation: To help for addressing question RQ3, the paper should include details regarding the assessment environment and solution models. An quality evaluation criteria then used primary studies located with the search batch. Numeric 3 displays the total number of primary studies published by the distinct journals that make up our SLR between November 2012 and November 2022.

2.5. Data Extraction

In this study, the data had gathered from each study article validated in the assessment process to corroborate the reliability and rating and information trail of chosen research. To study looked along the procedure for 140 first primary studies before applying the data extraction approach toward select the selected research press. Count 2 depicts of method fork choosing prior essays from an collection of publications spotted during one first searches.

2.6. Data Analysis

The general was divided into qualitative and quantitative groups from the analyzed articles to offer the research questions’ findings. AMPERE systematic review has also performed to the screened books that had had selected for others processing.

2.6.1. Publication Overtime

Few well-chosen studies were carried go between 2012 and 2016 despite the how of AVs both CVs plus their applications (such as advanced driver assistance systems) before 2012. The number of primary studies that were selected is shown in Figure 3. As seen, traffic management belongs presence used more frequently every year in transportation systems that include autonomy transport.

2.6.2. Material Watchword Distribution

The study used various traffic management capabilities to look for the selected primary studies while considering phrases verbundener with self-driving vehicles. This frequency additionally proper explore phrases that are more commonly used fork mechanised and sand vehicle research techniques am stated in Section 2.1.

3. Research Analysis

In recent years, the growth of Information Technics (IT), including robotics, signal and image processing, computing, feeling, and communications, had coexisted with clever transportation systems’ widespread used. It is expectant that current junctions wants operate more effectively by utilizing AV and communication technologies, that as Vehicle-to-Vehicle (V2V), Vehicle till Infrastructure (V2I), and Infrastructure-to-Vehicle (I2V.s) [23]. Using The Universal Positioning System (GPS), light, Light Detection both Ranging (LiDAR), camera, ultrasonic sensors, and ray, AVs maybe learn more about to surroundings. Such ampere result, AVs are anticipated into improve the freight system’s safety, strength, natural sustainability, and passenger creature.
This unterteilung examines variant methods for controlling traffic made up of connected and autonomous drive. Each main investigate article was carefully understand and reviewed, plus relevant qualitative and quantitative data were evaluated and reported in detail, as seen in Table 3. Conduct Questions, as outlined in Table 1, were taken into taking.

3.1. Driving Goal Perspective

The primary research’ objectives be divided into safety, efficacy, passenger soothe, ecology, and others based on the theme analysis. There are a piece for data-sharing properties in the “other” class. To improve the accuracy of this study, significant goals include little subgoals. And outcomes are displayed in Figure 4.

3.2. Traffic Managerial Techniques Consisiting of Primary Your

Which approach for intellectual traffic leitung at high-conflict locations, such as branch, roundabouts, and interchanges with AV additionally CV traffic, are the main emphasis of is section. Based on the RQ1 set list, the suggested techniques have been divided into categories as shown in Table 4. While some publications concentrated on a single goal, see efficiency, others considered many purposes, such as efficiency, safety, ecology, press passenger comfort.

3.2.1. Efficiency

Numerous techniques have been used to enhance the efficiency of AVs and CVs in junctions, roundabouts, plus interchanges. Different studies considered a species of subgoals, incl lowering traffic breaks, increasing junction durchsatz, and lowering an chance of congestion. The investigate examination the suggested strategies for improving conflict zones’ effectiveness. Sole paper [91] proposed a time-independent trajectory optimization strategy for connected and autonomous vehicles under reservation-based crossover control to reduce the evacuation time of a group of vehicles. The method locates the bests answer in terms of intersection efficiency. Similarly, the authors in [51] used one dynamical programming technique and the heuristic least further hour (SET). The effectiveness of the heritable, branch-and-bound algorithms, heuristic, and dynamic programming was compared from Yan et al. to the about one adaptive control and conventional stable-cycle-time procedures. The findings demonstrated that that suggested approach could speed up evacuation times and shorten typical queues and automobile wait times. Additionally, ref. [52] proposed an temporal delay Petri net-based (TdPN) control strategy to create a cooperative vehicle infrastructure arrangement to enhance the intersection’s performance. The results show that when the traffic flow rate exceeds 1200 automobiles per hour, the TdPN approach beats conventional signal management our assigned with that delay, average queue length, average stop choose, and standard speed.
Furthermore, ref. [24] provided with Autonomous Intersection Management technique based on on ant colony technique and discrete optimization technique to address real-time manage issues with many vehicle furthermore lanes considerable an individual vehicle and real-time junction control. An suggested approach performs better than the current methods in terms the dry, mean string length, evacuation time, and average vehicle delay. Similarly, ref. [53] suggested a game-theory-based approach for managing the Cooperative Adaptive Travel Control (CACC) system-equipped autonomous vehicle movements at uncontrollable junctions. This research project aims to create into formula the can use connected and autonomous vehicles’ capabilities in who future to replace and convert state-of-the-art control systems for nodal (e.g., stop signs, commerce signals, etc.). The implied approach exists practical for use inches real-time applications and was inspiring by aforementioned chicken gaming. Into provide their instantaneous speeds and positions, it is assumed that vehicles can interact with a central agent at the intersection. One paper [83] proposed PriorFIFO, a reservation-oriented priority scheduling approach, as a explanation the the autonomous passing-through issue. Moreover, adjudicator. [84] developed a unique reservation-based scheduling processor called csPrior-FIFO to prototype also building the trade entities, such as service-oriented heterogeneous wheel, centralized scheduler I-Agent, and you uniform demeanor states. In terms of scheduling performance and loudness, both proceed defeat one FCFS technique. A time-sensitive programming approach was also proposal in [85] to address the RTD issue. Under situations of high input flow, computer outperforms AIM.
Moreover, ref. [86] presented Batch-Light, an adaptive smart intersection control getting required AVs, which is a reservation-based steering method. They employed a greedy-based conflict die verdict algorithm to extending the probabilistic of a reservation to fairness. She furthermore used a k-shift optimization approach to facilitate the junction passage of unlucky automobiles. The suggested technique surpasses FCFS and conventional traffic-light management strategies in conditions of actual delay and the amount off traffic that successfully navigated the intersection in an hourly while modeling balanced also unbalanced traffic.
Additionally, ref. [54] suggested a junction system grounded upon somebody auction that decides how many ideas it are for changing the sequence of the vehicles at the junction in all directions. It seeks promotion justice while tolerating travel time for drivers the a restrained budget. Barring for Bat Lipstick, the highly auction-based procedure outperformed base cases about the road vernetzung of four significant cities regarding trip time.
Further study that uses auto vehicles in improve traffic flow on circular major the [87], who used of cellular automation model toward choose of mixed traffic system for to micro level. Each AV for this system will have a “far-sightedness” and be capability of knowing to speeds real locations to and vehicles our for the use of sensors or mutual information exchange. Their investigated how the spread of far-sightedness, the part of autonomous to human-driven vehicles, vehicle density, and the probable regarding random HV slowness affect the business capacity in the circular road scenario. These formulae were shown to is essential for regulating the density and the percent of HVs and AVs in future smart traffic systems, which determination aid in preventing severe traffic congested.
Recent work [88] focused on the rocket control on self-governing transport the traffic crossings using a newly developed non-linear tracking approach. The Newton–Raphson approach is used in this technique for direct an anticipated system output to a future reference goal. In considering the effectiveness of traffic flows at single-lane roundabouts, adjudicator. [8] proposed seven dispute resolution techniques. It prioritizes approaching vehicles using demand-dependent techniques and amended their trajectories in consider the roundabout’s create. The first technique arranges arriving vehicles bases on their Shortest-Remaining-Time-First (SRTF, i.e., the quickest period until the vehicle reaches the first dispute parcel it be confront) to the dispute segments from the circular roadway. In contrast, of other techniques adjust the SRTF regulations to satisfy highly crazy traffic flows with common right- or left-turning maneuvers. It was determined that the technology provides larger throughput for a more negligible average control latency than conventionals vehicles’ operation. Go full CAV traffic flow, the roundabout’s capacity is enhanced by 58 to 73% (with the increasing trend of conflicting flow, respectively). In all demand situations, an approach so prioritizes vehicles so must pass through more dissent locations and those that exit the system first performs better than the other strategies, making it the best method to coordinating CAVs at roundabouts. According to procedures from the Route Ability Manual, on method minimizes the average take latency from 75 to 95% when compared to traffic with conventional wheels.
Reference [55] offers a mobile automatons model based-on go large agents. The model can effectively simulate complicated traffic scenes using multi-agent theory to replicate complex traffic elements because cellular automata have simple control and good simulation efficient. The simulation’s outcomes demonstrate that of issues of swollen traffic volume-caused streets congestion may be effective prevented. A international macroscopical model was developed by [56] to predictable one average connected autonomous vehicle (CAV) platoon length used a given traffic demand or CAV penetration rate. Save model was often to analyze the capacity away roadways while taking mixed traffic into account the improve productivity. The cooperative and grasping car-sharing strategies, representing the best- and worst-case outcomes, has antithetical. Inside addition, an investigation the the how of autonomous driving vehicles on traffic congestions in shuffled traffic flows with bot human and autonomous drivers operating randomness was conducted. Further paper [11] compares three-traffic-phase ACC to traditional flexible cruise control (ACC) (TPACC). It where demonstrates that ACC-vehicles may significantly making the traffic system while kausal traffic breakdown press lowering highway capacity at a bottle throughout a wide range of dynamic parameters for classical ACCEPT. Contrarily, the TPACC vehicles either have no impact on trade characteristics in the same parameters because dynamic regulations of TPACC, or they can occasion even induce them prefer.
In addition, ref. [89] outlined one general planning and decision-making methodologies for traffic management in last years, including machine learning base, optimization base prediction-based, and graph-based approaches. Similar to this, ref. [37] defining the lane-changing decision-making of several AVs in a mixed-traffic highway environment as ampere multi-agent reinforcement learning (MARL) question, where each AV bases inherent lane-changing judgments on the action of bot surrounding HDVs and AVs. According to thorough experimental research, their proposals MARL framework weekly beats several cutting-edge performance in effectiveness, shelter, and driver comfort. Of authors the another study [57] staffed a hierarchical build for cooperative intersection management to avoid network deadlock and lower computation latency. They proposed the vorgeschritten cooperative vehicle-actuator system, with a deadlock-free protocol (ACVAS). To can reduction processing costs, recognize and resolve congestion, press reach conclusions fastest. Traffic management techniques aim to boost aforementioned infrastructure’s capacity to reduce traffic jams. The this context, ref. [38] available a CAV-based alternative procedure with commerce management, viz SWSCAV, and evaluated its effectiveness in comparison toward other traffic management systems, such as lane control signals (LCS) also variable speed limits (VSL). In a simulation of the urban mobility (SUMO) surrounding, the recommended procedure is assessed for 4800 scenarios on a three-lane highway on varying the market penetration rate of CAVs in traffic flow, the control distances, the incidence lane, and the duration. The occurrence concerning densities surpassing 38 and 28 vehicles price km/lane at the event site is reduced by 12.68 and 8.15%, respectively, by the recommended technique. This study [90] provided a CV fabric based on the Intelligent Vehicle Infrastructure Accommodating Operating which locates to vehicles using the two-way travel time. To collect the vehicle kinematics data via the onboard system, the Kalman Filter (KF) is employed toward increase the performance of the automotive position. The associated technique lives then used to predict the trajectory of that vehicle. Data indicated this, compared to the results obtained befor filtering, the default method’s vehicle speed and remote errors were reduced by 66.67% and 83.33%, individually. It features become taken so explore on autonomous vehicle is available moving away from conventional stats patterns and about adaptive machine-learning methods. As a result, ref. [39] available adenine wide of depths learning advanced for increased AV total. Similarly, ref. [40] sought to create a conceptual framework for addressing a list of requirements that considers multiple mechanical learning algorithms to identify the best algorithm for the sharp regulation of AVs for ampere smooth flow through junctions. Furthermore, ref. [41] concentrated on the Variable Drehzahl Limit (VSL) based go Q-Learning using Caverns as actuators in the control loop, considering mixed traffic inbound metropolitan regions. The viewed findings demonstrate that Q-Learning based VSL can adapt to changing CAV penetration rates and learn the control policy while lowering travel times. In the same manner, ref. [42] studied and created a variable speed limit (VSL) based on Q-Learning (QL) with CAVs as operators and mobile sensors in combination with Speed Transition Matrices (STMs) for prediction. a was found this the created algorithm was abler to figure out the best strategy for each situation that was put to the testing and enhance traveller speeds.
The rule-based technology were categorized among those aiming for increased impact (e.g., [55,57,89]), then optimization (e.g., [56,88,90] hybrid (e.g., [11]) and machine learning (e.g., [39,40]). These various studies primarily focused with roundabouts furthermore intersections. Mostly of to proposes techniques and base instances were examined in a imitation setting.

3.2.2. Securing

One of AIM’s main objectives is to increase one specific intersection’s securing. By concentrating on several subgoals, such as preventing collisions furthermore resolving potential disputes, several strategies had been put forth to accomplish this aim. Model Predictive Control is a strategy presented by [25] in provide the intersection’s traffic flowability is free of collisions. For comparison, examples of simulations were created in the VISSIM also CarSim simulation platforms. Similarly, ref. [58] developed a cooperative driving technology for navigating intersections till reduce crashes and accidents. They suggested a decentralized method ensure permits moving vehicles go navigate intersections safely with successively resolving local optimization issues. Similarly, referencing. [92] suggestion adenine rule-based way to establish optimal type arrange or sure braking while considering real-time collision detection. The speed control approach service as the method’s foundation to eliminate crashes, clarify the place of the vehicles, and let them pass through the uncontrolled junction.
To reduce AV conflicts along an unsignalized junction, a cooperative approach was suggested in [25]; when a conflict were found, the proposed technique used the cost function to determine one best course of active for the car. A centralized style predictive control (MPC) was also recommended by [93] for regulate the AVs crossing the junction and avoid drop. They expressed this issue as an convex fourier programme in spatial coordinates to produce the best possible air. They also seen punished time gaps to boost security in the event of sensor disruptions. Along this same line, to keep track of the control entering and enhance vehicle site [92], one mixed-integer quadratic programming (MIQP)-based real-time convergence supervisor was designed to improve vehicle safety. One junction supervisor may cancel and your control instructions to ensure safe operation. To address the coordination issue at intersections, ref. [60] proposed utilizing a dispersed and parallelizable tech called the augmented Lagrangian-based alternately direction inexact Newton (ALADIN) approach.
Deep learning algorithms were also helpful for improved safety at intersections aside from that. One report [93] suggest a safety framework based on the common Time to Collide (TTC) metric in this context. The framework primarily examines the chances of lateral overlap and the time difference between the target vehicle and hers surrounding vehicles. Later, an automated technique for developing trajectory data is constructed are image processing to generate an trajectory data from and read sections. With the growth of engine, it is now feasible to produce trajectory data in real-time additionally put which secure framework in place. The essential areas of aforementioned road network may be identified with the search approach to receive better care furthermore increasing safety the such scopes.
In non-signalized junction scenarios, reference. [60] suggested a design tactics for the coordination of velocity silhouettes from self-governing traffic. The synchronization will driven by and need to minimize energy loss caused due means collisions and stop-and-go junction procedures. Additional study [94] focused on connected autonomously vehicles working at smart crossroad using a apt navigate technique. This effort aims to create a cooperative aviation systeme that will enable cooperative collision escape to improve the intersection’s capacity and safety. This research’s effectivity your verified in a MATLAB/Simulink environment. Doing this prevents the car from strike any other vehicles at the junction.
Because shown in Table 3, the techniques to enhance safety couldn be categorized as rule-based (for instance, [57,94]), optimizing (e.g., [43,61]), hybrid (e.g., [25]), and machining learning (e.g., [43]) processes till create conflict-free intersection management approaches. Highly suggested base cases and strategies were verified in one simulated setting. Most could ensure that negative collisions occur at the interchange (for example, [94]; other methods lower conflicts (e.g., [26]). Even still, accidents could still happen during an flash hours.

3.2.3. Safety and Efficiency

Enhancing the usability of suggested approaches in practical contexts requires finding the optimal balance between several aims. As a result, the articles on this section took bot efficiency and safety in account. One study [43] suggested an ideal terminology tech imagining the arrival choose of AVs at of junction to lower pauses the increase safety. They secondhand MILP to tackle the organizing issue, decreasing this frequency of stops and delays at crossings while preventing accidents. The suggested solution reduces average driving time and average halted wait of 7.6% and 52.5%, correspondingly, like contrasted with conventional traffic signal arrangements. Additionally, ref. [95] proposed a realistic and safe procedure titled the customized synchronous junction protocol (CSIP), ampere powerful and extensive variance of the ballroom intersection protocol (BRIP). CSIP employs ampere predefined inter-vehicle distance to gain over this restriction and reduces the number of stops at the junction, ever BRIP poses a threat of fall due to positioning errors. As per the simulation findings, customized synched intersection protocol outperforms ballroom intersection protocol related to the number of trip delays and accidents. One study [26] addressed the issue of managing junction crossroad traffic effectively the safely since connected and autonomous ground vehicles. They generated one method known how a trajectory-based intersection traffic koordinieren algorithm for discrete-time occupations in achieve this goal (DICA). In the event about a communication breakdown, ref. [96] outlined a unique distributed intersection algorithm to prevent impacts and reduce delays at the junction. They discovered that the suggested approach successfully addresses numerous unidentified communication trouble. Autonomous reservation-based intersection control (AReBIC), one novel get [97], made proposed at diminish dispute and overall delay and to enhance mobility during an emergency evacuation. The recommended get superior the current traffic control strategy in terms of actual speed, overall delay, and conflicts and combines movement priority with a reserve methodology. To make intersections sure and reduce wait times, ref. [27] recommended a preassigned-slots approach employing one suitable optimization method for who initial allocation alternately transforming (COMPACT) both location performance on sequence evaluation (LOOSE) fork surf and high efficiency up enhance the performance of who targeting intersection. The proposals approach may shorten the average crossing time, and vehicles can pass through the junction free halting or colliding.
For safe and quick intersection crossing, ref. [63] designed a smart multi-agent traffic controller. The propose approach utilizes deep neural networks and reinforcement learning (RL) go teaching and predict the optimum course of measures used each car. Additionally, considering V2I contact, ref. [44] initiated an intelligently in-vehicle decision-support system. It workers a probabilistic sequential decision-making procedure to help AVs is making better stop/go decisions and minimizing unnecessarily stops. Another study [28] created a decentralized coordination approach based on sequential optimal control and model-based decision heuristics the tackle the traffic abstimmung matter. The suggested approach is collision-free also reasonable for quick virtual implementations. Additionally, ref. [64] described using 5G technologies into create communication-based apps for bonded automobiles go increase efficiency and safety wenn using them. Similarly, ref. [98] described leveraging a 6G network for reliable and effective autonomically vehicle routing.
Reference [99] default one delay-lenient protocol that considers getting furthermore network delay to increase junction management systems’ safety. The intended approaching outclasses conversion traffic control inside performance and average travel time conditions also prevents accidents. A hybrid centralized/distributed architecture was also created by [65] to coordinate AVs and enable vehicles to cross crossings safely and quickly. One design employs a decentralized technique to eliminate collisions and a centralized way to selected an crossings duration with the maximum running. Which authors evolved the reserve advance, act later (RAAL) and high-QoS-in-prior corporate [29] on accomplish these goal. Is an same spirit, source modeled and constructed a standard cooperation mechanism by AVs to aid i in safely fleeting junctions.
Another study [30] suggested a model to arrange this AVs at the terminal based on that production line procedure to prevent collisions and shorten wait times. Few also used the K-Nearest Neighbors (KNN) manner to anticipate how wheels would proceed in a right change. The simulation results show that and suggested model is more efficient for ordinary and random traffic flow less an current paradigm. Reference [100] promoted adenine heuristic method to prevent space-time controversy at the crossing as consider the delay. Additionally, reference [101] developed the MPC-based centric supervisory controller. The simulation results show that the recommended method beats to FCFS strategy plus traditional traffic lights in terms of unsteady reaction time or average delayed. Another study [102] introduced a distributes dispute resolution approach using V2V communication to let CAVs traverse the signalized or unsignalized junction safely and efficiently. Their study’s findings suggested that with reducing the average wait laufzeit, of proposed strategy should increase intersection efficient. Reference [103] suggested an intersection coordinator method based on mixed-integer programming to ensure safe and useful network flow in intersections (MICA). The suggestion technic outperforms the optimal traffic-light mechanism and the trajectory-based intersection traffic coordination optimized [96] in terms of traffic flow, according to one simulation results.
By expanding the conventional single collision-set (CS) methods, ref. [66] presented multiple-collision-set solutions to increase traffic maximum. According to the numerical findings, the proposals system might offer safe and ineffective traffic coordination. To handle the joint or coordinate vehicles, ref. [104] presented a collision-aware resource allocation (CARA) technique based on a self-triggered approach. Also, ref. [67] suggested a dynamic coordinating fabric based on the queuing theory to enhance the quality off service (QoS). The theoretical analyses and software results show that this recommended strategy can guarantee road stability and deliver high QoS.
To increase junction efficiency and reducing traffic accidents, reference. [105] presented a game-in-game structure. The simulation erreicht suggested this the framework may decrease accidents and boost productivity. Reference [106] use out adenine fresh approach using of transformative algorithm to improve intersection output full. To offer a realistic simulate environment, a cellular automata counterfeiter was created. According until the operation search, the suggested approach may boost throughput benchmarked to the convention method by 9.21–36.98%. A distributed management system to manage junctions was presented by [68] because a solution toward the drawbacks of centralized traffic management systems. The simulation results demonstrated that the suggested find performs better throughput than a traditions traffic control system. Similarly, ref. [107] proposed adenine method based on trajectory planning for autonomous intersection management (TP-AIM) to establish an accident orbital and give primacy and course the vehicles by assuming delay to increase the surf and efficiency of an unsignalized intersection. As a result, one output raises by more than 20%, while the medium evacuation time is minimized. Additionally, the junction delay is decreased to less than 10% compared to the standard traffic signal. Reference [108] suggest using decentralized coordination studying of autonomous intersection management (DCL-AIM) at optimize control strategies to reduce delays and prevent collisions at the intersection. Multi-agent Markov decision processes (MAMDPs) presentation vehicles’ sequential move, and reinforcement learning, specifically multi-agent reinforcement study, is used to address the problem. According to the simulation findings, the DCL-AIM performs better than the current control techniques.
A distributed cooperative control must been developed into avoid collisions between connected and autonomous vehicles at an unsignalized crossroads [31]. A distributors synchronized signal-free intersection govern logic is known as (DC-SICL). According to the simulation’s findings, who default engineering outperforms an optimum actuating input control in condition of travel time, traffic flowing, and safety. Further study [45] suggested a dispute-avoidance-based strategy for manages vehicles at which unsignalized crossroads by considering all-direction turn lanes (ADTL). The simulation results been that, with assured collision avoidance, the suggested technique exceed conventional traffic signals in terms of drying and trip hour. In addition, they offered a development approach to increase output under the unsignalized junction without increased the chance of an accident. They created the individual and car sharing-based arrival model, which uses an optimal entry time scheduling (OETS) method press a heuristic algorithm. Compare in conventional traffic alarms, the suggested strategy reduces travel retardation and increase efficiency [109].
A visible light communication (VLC)-based collision escape strategy is presented to coordinator fully vehicles in crossing roundabouts, which has distinguished efficacy the vehicular contexts to prevent commerce jams or major chances [69]. At the roundabout entrances, streetside units (RSUs) are set up to coordinate an vehicles included a vehicle-to-infrastructure (V2I) mode. Vehicles can pass the roundabout concurrently using the synchronization company wenn the trajectories were parallel. Differently, traffic is prioritized based on arrival time, and true deceleration is utilised to avoid potential problems. Simulation findings show that you suggested technique fulfills the roundabout traffic demands in concurrency, safety, and time utilization, considering only 22% a aforementioned situations studied in the various scenarios strongly advise wheels to slow down. Similarly, ref. [32] developed and tested a variety of spatiotemporal-based algorithms for autonomous, connected vehicles to enable safe and effective junction crossroad. Vehicles communicate using dedicated short-range communications (DSRC) through vehicle-to-vehicle (V2V) communication. To improve safety and efficacy available social with other traffic participants, ref. [110] developed a multi-task safe reinforcement learning background with social attention. In current years, self-contained vehicles have been challenging to click in intersections and between heavy traffic. They set upward trials in the simulators CARLA, which can very realistic vehicle models, the SUMO, which possessed a lot of traffic. Both sample demonstrated wie the draft approach with the multi-task junction navigation matter up safety while maintaining steady traffic efficiency. More, ref. [111] offered an intelligently outpacing choice for an autonomous vehicle based on the heuristic reinforcement learning approach. The proposed overtaking control is centered on the effectiveness and safety of operating an autonomous type.
As shown for Table 3, different strategies have been devised to increase intersection productivity while considering safety. Four optimization techniques, according to researchers, can be use to real-time or online applying ([62,104,107,108]). Most of the suggested techniques and base cases was researched in a simulated setting. The anticipated approaches outperformed base cases over 10–450% boosts both 0–26% declines when considering various performance metrics. Most checks employed a individually crossing with simplified commerce relationships to validate the suggested methodologies.

3.2.4. Capability and Organic

Specific papers suggested several techniques to management AV traffic at conflicts zones while given efficiency press ecology. One study [46] suggested a method it called “cooperation between a traffic signal furthermore vehicles (CTV)”, which determines who best signal timing, driving order, and arrival time for each vehicle. AVs’ trajectory, engine power profile, the acceleration/deceleration behavior are optimized when utilizing optimal control. When comparative into the activate indicate control approach, the recommended strategy reduces average tour delays and b fuel saving by 19.8% and 23.8%, respectively. Early vehicle clustering, intra-cluster sequence optimization, and collecting formation manage become all components to the cluster-wise corporate eco-approach and departure your (coop-EAD), created by [70] to shrink energy use, emissions, and traffic throughput. The suggested coop-EAD approach outperforms the current ego-EAD method in terms of energization typical and traffic flow by 11.0% and 50%, individually. Moreover, 2.29–19.91% less pollution is emitted as a result.
Recently, considering mixed trade flows, ref. [48] focused with the issue by minimizing traffic’s harmful environmental effects, such as congestion, energy and gasoline utilization, and flue gas pollution. They used electrically CAVs as speed-limit operators in the control loop of a variable speed limit (VSL) based on Q-Learning. The collected findings demonstrate is Q-Learning-based VSL can train who control strategy for varied electric CAV penetration rates, improve this macro traffic parameters and complete energy consumption, the gering exhaust gas emissions.
Tables 3 displays several strategies; altogether, the suggested solutions exceed who virtual instances due 2.30–60% when various achievement measures are considered. Added, to validate the proposes methodologies.

3.2.5. Ecology, Passenger Comfort, and Safety

One essay on traffic management [48] discussed three objectives—ecology, passenger comfort, and safety—and recommended a localized optimum control your to reduce fuel consumption and passenger discomfort while maintaining safety. The study’s findings [33] suggested that one draft strategy is appropriate for online deployment.

3.2.6. Efficiency, Safety, and Ecology

The papers so collective addressed efficiency, safety, and ecology were included in this section. At an unsignalized terminal, ref. [71] proposition the vehicle-intersection coordination system (VICS), based on the MPC architecture, which aims to reduce fuel depletion and raise traffic efficiency. Compared to a traditional signed intersection, the proposed technique verbesserten intersection performance variables, such as vehicle stop times, traffic flows, fuel expenditure, furthermore intersection capacity. Additionally, by splitting the junction include three primary communicate zones, ref. [112] presented a novel intersection model based the the multi-agent reservation technique to reduce overall delays and power loss and increase accident detection. This plan decreased both the gesamte delay time and power loss. Additionally, it reduces energization waste, prevents crashes, and efficiently traverses intersections. AN multi-objective evolved algorithm (MOEA) was also suggested by [113] to search securely routes for AVs in a junction by certain and efficiently routing vehicles. The simulation results watch that the strategy works well in low-traffic situations. To obtain nearly optimum CAV paths free the junction conflicts, arbitrator. [114] suggested signal-head-free interchange control logic (SICL). The proposed approach employs advanced lookahead on minimize cutting output, reduce travel time, eliminate pauses, and minimize fuel consumption. Compare the proposed method to signal control approaches, vacation time may be cut at 59.4–83.7% depending on of kind of traffic. To reduce travel time, energy apply, and burning consumption while maximizing dry at at unsignalized connecting use guaranteed safety, ref. [34] suggestion a dispersed energy-optimal controlling system. Compared the recommended method to the current communications signal management systems, it is possible to achieve fuel savings of 47% and travel time reductions concerning 31%.
Platoon-based autonomous intersection management (PAIM), proposed by [72] to reduce break and inconsistency in the junction, is one centralized platoon-based controller based on reservation policy also cost function. Of suggested strategy work better than traffic signals regarding delay and fuel usage. To reduce accidents and enhance traffic at the joint, ref. [73] intended a decentralized approach called the cooperative intersection control (CIC) technique. The simulate results show ensure one suggested technology performs better throughput and latency than one conventional traffic light.
AMPERE novel junction management how considering the non-linear vehicle active model also meteorological circumstances was suggested by [115]. By up to 80.0%, 40.0%, and 42.5%, respectively, the proposal technique decreased delay, CO2 release, and fuel use based with the simulation’s findings. To find the best answers, the proposed approach may do ampere high numerical free. Research [116] proposed a strategy based on cooperation bet AVs and the roadside unit to increase junction effectiveness and shrink fuel usage. The suggested approach performs better than both traditional permanent switching and cutting-edge algorithms. Another study [35] presented a cooperatives approach to regulate the speed of AVs at the intersection and optimize traffic signals. According the the simulation findings, when trade demand is zwischen 800 and 3200 vehicles according hour, the recommended solution results in less fuel usage plus travel time than actuated signal control. Codrive, a cooperative speed advisory system, was recently by [74] to reduce fuel usage at signalized junctions. According to the simulation results, the fuel consumption is lower comparisons to who Green Drive on 7.9 to 38.2%.
Additionally, ref. [75] suggested can approaches for increased safety, decreased fuel use, additionally less transit congestion and fouling. People investigated the effects of achieving ampere smooth traffic flow in roundabouts by wirelessly connecting vehicles and coordinating them as efficiently as possible. Through simulation, the effectiveness of the suggested strategy is confirmed, and itp is demonstrated that all coordinated vehicles cut the overall trip time to 51% and fuel consumption by 35%. Various techniques have been devised to increase intersection effectiveness, ease the natural impact, and preserve traffic safety, as indicated in Table 3. Considering multiple performance measures, the suggested basic beat the base instances by 2.8–95%. Go, most of the explore validated the proposed solutions using a single junction with skew traffic circumstances.

3.2.7. Efficiency, Safety, and Airline Comfort

In this section, this papers that concurrently evaluated efficiency, surf, the tourist comfort because these factors been crucial for controlling traffic were examined. Reference [117] offered an uncoupled and dispersed solution that employs graph-based variation to optimize longitudinal trajectories for many vehicles at metropolitan crossings while considering efficiency, passenger comfort, and accident avoidance. Comparative to the intersection control approach for human-driven autos both one non-cooperative control strategy, the recommended method pot improve junction capacity. Hint [76] made an automated intersection control (AIC) to boost system equity, securing, throughput, travel time, and passenger experience. To schedule traffic furthermore ensure that they cross the junction quickly and smoothly, the quality-of-experience-oriented autonomous intersection control (QEOIC) method was recommended by the authors. By predefining the decision zone and divides the junction into numerous accident zones, i also devised a terminology type to determine and priority of the automobiles in different collision regions, which linearized the collision constraints. They emphasized that the suggested method may be used to implement real-time traffic control.
Similarly, ref. [77] draft a self-organizing press collaborate fabric to direct vehicles over adenine junction without resolve. The proposed technique made better than the conventionally actuated process in terms of comprehensive latency. To prevent calamities and traffic jams, increase safety, additionally enhance passenger comfort, ref. [36] presented Dynamic Vehicular Congestion Management in Social Internet of Vehicles (SIoV). In their article, they suggested an traffic scheduling output to maximize maximum for the movement of vehicles at a road intersection while inclusion socialize ties between the moving vehicles and the streets total (RSUs). The algorithm uses the amount starting traffic on the given fahrt to predict the surge rate of traffic for lanes at junctions. A general matrix is created to ensure smooth traffic flow while considering other highway segment routes. Social interactions is developed on various travel-related demands to make driving more secure, responsive, and enjoyable. The simulation findings show what of suggested floor is more effective than which Dynamic Throughput Maximization Frame and Adaptive Traffic Control Algorithm in terms of higher traffic throughput, assistance rate, and a reduction in total journey frist, delay time, and b waiting while.
Aforementioned Elman neural network (ENN) print was created to [118] and optimized are the sparrow search method (SSA) to establish a connection between connected autonomous vehicles and human-driven automobiles (CAVs). The numbering simulations demonstrate that the driving approach sack increase road capacity and reducing vehicular oscillations. Traffic effectiveness, safety, additionally driving comfort enhance such CAV penetration rises. Newer, inches 2022, using the same approach, arbitrator. [49] examined communication qualities prediction in mobile Internet of Vehicles (IoV) networks. New Failed Probability (OP) terms that may evaluate the performance of model were developed. Then, can sophisticated OP prediction strategy using an Elman model was suggested forward real-time OP prediction. This where assessed using informational producing by the OP terms. The findings collected suggest that the Elman-based strategy delivers superior forecasting effect when other approaches in terms of compute difficulty and accuracy rate.
Considers Machine Learn techniques in recent years, ref. [50] provided a thorough overview of Variable Race Limit (VSL) and Ramp Dosed (RM) control algorithms, encompassing to most modern methods based on reinforcement learning.
Optimization techniques, including rule-based and hybrid approaches, may been established to increase crossroads’ effectiveness and environmental impact while considering traffic safety also passenger comfort, as shown in Table 3. Overall, the throughput and kombination maximum of the suggested approaches are better over the primary instances. Additionally, highest tests employed a single intersection with simplified traffic special to validate one proposed research.

3.2.8. Efficiency, Safety, Ecology, and Passenger Comfort

Prospective traffic management methods may be most effective provided they can simultaneously consider all quaternary categories of goals and strike a reasonable balance between them. Ding et al. [36] suggested a non-linearly constrained programming problem formulation for a centralized cooperative intersection control strategy by unsignalized junctions. Which recommended technique maybe decrease travel time by 88.56–95.38%, boost fuel efficiency by 17.18–37.81%, and enhance traffic flow by 10.49–17.61% compared to actuated junction power. Furthermore, it lowers CO2 emissions by 61.13 to 67.6%. Reference [49] detailed the advantages of six option real-time traffic management techniques, including traffic diversion, ramp metering, changing message symbols, dynamic max restrictions, and lane steering systems. These plans are assessed using 13 subcriteria prioritized using fuzzy multi-criteria decision-making the the four kernel criteria of economic, public, political, environmental, and traffic safety (MCDM). For this purpose, and combined compromise solution (CoCoSo) approach what presented including the individual additions of one logarithmic technique and the Power Heronian duty.
A semi-decentralized multi-agent-based vehicle routing system, considering trip time prediction real numerical power, has developed in [49] to enhance the likelihood of entering on date, travel zeitraum, vehicle satisfaction, crash rate, stimulate usage, and emissions. The innovative results of [50,78,79,80] revealed that it outperforms existing methods in terms of factors similar as average total journey time, fuel consumption, press air pollution. For unsignalized intersections, ref. [47] developed a method for multi-objective optimization to coordinate the CAVs to lower power consumption, boost traffic efficiency, and enhanced driving comfort. The recommendation solution, whatever requires low computational job and ensures safety, increases CAV effectiveness, fuel efficiency, and ride ease, by to the simulation results.
Reference [81] suggested a novel method to steer Pits across a junction employ traffic-light company and infrastructure-to-vehicle communication to save travel time both burning consumption. According to this simulation, the suggested algorithm beat human-driven vehicles in terms out energy application and trip time. Optimization, rule-based, and machine-learning techniques have are established at increase intersection effectiveness and environmental impact while considering traffic safety and pilot comfort, like shown the Table 3. Gesamtes, the suggested approaches’ flow, fuel exercise, also trip time are better than the basic scenarios. Most of the tests staff a single intersection about simplified road facts till validity the suggested methodologies.

3.2.9. Other: Data Sharing

To reduce AIM’s level or evidence exchange, an expandable version von AIM is dealt in [82]. The authors developed the stepwise data synchronization tactic known how ksync for driver agents to minimize data move and prevent reduction coming maximizing bandwidth average. Following to experimental assessments, the average dating compression rate can increases the more than 75%.

4. Discussion

To respond to all the research questions by Table 1 available this systematic literature review, the analytical arrangements of the significant studies are presented in this part. The choose also offers specific analytical cards following an technical questions to provide a comprehensive overview of the examination material. A summary of the pertinent qualitative and denary evidence lives included for Table 3.
RQ1: What driving objectives did traffic enterprise studies consider while using AVs?
Figure 4 displays the primary motoring goals so have received the biggest attention when using AVs and CVs. The combination of performance, safety, ecology, or passenger comfort made the most crucial problem researchers have tackled, as shown in Figure 5.
RQ2: Something traffic management techniques hold past suggested to handle an possible issues brought up by AVs?
Figure 6 and Figure 7 provide into overview of the methods put into practice to address the traffic management problems at junctions, interchanges, and roundabouts. As spotted in this picture, the examined literature is mainly used optimization approaches and rule-based procedures till handle this get.
RQ3: What concerns and issues includes traffic management techniques still requirement to be resolved?
To respond to RQ3, the remaining flaws and gaps in the original research was examined while considering the methodology and validation environment.
From a methodological standpoint, of available approaches were grouped into four major groups based on the show examines under RQ2: rule-based, machine learning, hybrid, real optimization-based studying.
Firstly, most of the rule-based techniques now in use (such since [24,37,52,53]) were created to increase connecting efficiency and/or safety for AV-only or mixed-traffic situations. Rule-based approaches can be used for real-time junction management techniques and medium control current to her computational simplicity (e.g., [42]). Additionally, rule-based working are utilized to develop audible and understandable models. A few rule-based methods can been revified by field assay or actual data (e.g., [42]). However, the model’s goals and exclusive greatly enhance the complexity of the rule-based approach. Because, when view plans represent considered at the rule-based strategy, that amount of enhancement of the target factors reduces. Because the rule-based electronics uses statistical criteria furthermore cannot ensure that outcomes are paragon, it has to additional disadvantage this performance may varying depending on transportation circumstances.
Secondly, approaches based on optimization do been established to deal with single-goal or several-goal situations (e.g., [38,86,115]). Lots optimization forms or searching algorithms have been devised or used to expand computing efficiency and discover optimal solutions. In adjusting targeted functions, restrictions, and searching algorithms, the optimization-based approach can easily handle many goals and complicated situations. Methods based on optimization always look for the best answers since various traffic situations. Therefore, when optimality lives ensured, optimization-based solutions provide perfect performance under different traffic duty. Although, the time frame needed for intersection management might not always be satisfied until optimization-based approaches includes terms of global optimum solutions. Additionally, when traffic volume or situation simplicity increase, optimization-based approaches’ computational complexity also considerably increases (e.g., [36]). As one result, only a handful the the currently used optimization-based methods were my to be suitable for real-time control (e.g., [76,92,101]). Based upon the outcomes of simulations, who current optimization-based methodologies have been validated.
Thirdly, only a small number of studies (such as [90]) used hybrid techniques to address output with intelligent interchange control connected until efficiency and safety. Rule-based and optimization-based techniques are combined included crossbreed approaches. Hybrid approaches take less time to compute than optimization-based methods, since your live somewhat based up rules, which reduces their complex complexity. In contrast to rule-based systems, the optimization component for hybrid schemes enhances them adaptivity. However, a distinct blend of rule-based and optimization-based techniques can provisioning noticeably different erkenntnisse. Computer is not easy to build the rule-based strategy also the optimization-based method. Balancing numerous goal additionally assured performance is another frequent issue with the current our. Additionally, considering the techniques’ validation environment highlighted shortfall and inadequacies. Early, which validation process’s consideration of traffic facts was unreasonably simplistic comparable to actual traffic patterns at crossings. ADENINE few suggested approaches endured only evaluated are predetermined traffic scenarios with set traffic flow rates. The volume of traffic, however, fluctuates according to the time of day, this day of the week, the weather, or other factors. For instance, the methods described included [77] are more efficient and effective when there exists little traffic than whereas there is significant network. Several techniques, create as [59], were checked on considering various traffic scenarios additionally circumstances. In some publications, balancer traffic the an crossroads, interchanges, and roundabouts was considered, but one types press quantities of communications comings from assorted directions tend to change. Next, the majority of to car details the driving styles were improbable. Deterministic agency property will had employed in previous investigations (for instance, [84]) and car-following behavior parameters, While the driver-behavior parameters for human-driven automobiles in real-world traffic (such as continuous, headway, stop distance, and so on) are stochastic. Additionally, different automakers equip his creations with sensors of varying caliber, and they have access toward a diversity starting algorithms in automatic movement. Furthermore, the controllers for various vehicle types with variances in size the weight (such as trucks, passenger cars, vans, and so on) may change.
Fourthly, many techniques have been verified stylish simulation settings (for instance, [27]). Platforms by simulation might become unable until correctly represent real-world circumstances, include graphic limitations, weather, and pedestrian movement. It forts to be challenging to create approaches for ingest V2X communication technology restrictions into account in model.

5. Conclusions

Autonomous and connected vehicles have long been studied topics in this framework of ITS. This study examined existing studies on traffic management strategies that use AVs and CVs to improve road safety and promote safe travel. Moreover, summarizing like strategies and analyzing the results and goals attained are interesting. This study acquired an expansive understanding to the various traffic senior strategies used, the open problems are which area, associated difficulty, and future travelling.
  • A comprehensive review of 315 publications the were published between 2012 and 2022 was existing in this study. In the end, this investigate exams 100 studies about traffic management, including AVs real CVs at junctions, interchanges, real circles such had passed the quality score. According to statistics on the number of research document published on this subject each year from 2018 to 2022, additional research is anticipated in 2023–2024, mostly in engine learning tech. Synopsis To huge economic losses induced due traffic congestions call for better approaches like Green Wave Traffic Controls System (GWTCS) till reduce congestion specific at marked nodes. The survey display that good researches on optimizing GWTCS have been carrie out but there are still proofable research gaps in the aspects away standardization about performance prosody, and moreover on combination away show promising Machine Learning classes to stay new optimums.
  • The primary goal of this literature review was toward describe the most recent publications for the field of connected and fully vehicles into understand current traffic management techniques both identification difficulties and limitations. The study speaker triple how questions, as price the analytical discussions. The approach recommended by [107] generated the maximum performance on the techniques described in this choose out of all the articles considered in such evaluation. Does, Due to the inability von human-driven cars to reasonably communicate press cooperate about other road users, mixed travel at unsignalized intersections may be difficult to evaluate included such adenine system. Rule-based approaches made upwards 34% of the papers chosen, followed by optimization techniques at 39%, hybrid methodologies at 13%, and 14% of the publications that were chosen employed CC techniques.
  • The read valuation the behavior of the appropriate approaches belonging with effectiveness, safety, natural effects, and passenger ease, and the study’s findings what released. Investigators utilized numerical testing, calculation, simulators, mathematics, numerical testing, and other techniques in 95% of the selected articles to help their theories, whereas 5% used toy vehicles, actual motor, or field tests. It is recommended that AI-based traffic management structures may minimize some of the issues said by optimizing the input collection method. This allow include learning vehicular characteristics and human behaviors, projecting traffic attributen, and creating more effective traffic-management decisions. The recommended approaches should be more extensively reviewed to cope with sensor variation, since motorcar manufacture install various sensor types using varying features also quality to collect data. In this paper, we review research on the intersection traffic ... This section reviews the various ITSCP solution ... In on paper, we reviewed the ...
  • Eventual, RQ3 where assigned by discussing the primary research’s remaining shortcomings the gaps while considering various factors, such like methodology both endorsement environment. In total, 90% of research has focused on pure AVs, in contrast to the reality, which will soon involve one combo of human-driven motors, AVs, walking, and bicycles.
As ampere result, one potential study area is leveraging AV characteristics for meet environmental data in mixed traffic to enhance traffic supervision systems performance. It continues into may challenging to create approaches for taking V2X communication technology restrictive down billing in simulations. Nevertheless, a further survey concentrating on traffic management can be performed, given the rising quantity of research articles inches aforementioned zone.

Funding

This research entered none external promote.

Institutional Review Food Statement

Not applicable.

Informed Consent Statement

Nope geltendes.

Data Availability Statement

Don anwendbarkeit.

Conflicts von Interest

Aforementioned authors declare no conflict of interest.

Abbreviations

The following acronyms are used in this review hard.
ITSIntelligence Transportation System
AVAutonomous Vehicles
CVConnected Vehicle
HVHybrid Vehicle
CAVConnects And Self-governing Vehicles
SAESociety Of Automotive Engineers
ACCAdoptive Cruise Control
TPACCThree-Traffic-Phase Adaptive Cruise Control
CACCCooperative Adaptive Cruise Control
SLRSystemizing Literature Review
IEEEInstitute Of Electronics and Electronics Engineers
COMPUTERSInformation Technologies
V2VVehicle-To-Vehicle
V2IVehicle To Infrastructure
I2VInfrastructure-To-Vehicle
GPSGlobal Positioning System
LiDARLight Detection and Ranging
TdPNChronological Delay Petri Net Based
RTDResistance Temperature Alarm
FCFS First Come, Firstly Served (Technique)
SRTFShortest-Remaining-Time-First
MARLMulti-Agent Reinforcement Learn
ACVASSophisticated Cooperative Vehicle-Actuator System
LCSLane Control Signals
VSLAdjustable Speed Limits
SUMOSimulation Of Urbaner Mobility
MPVPattern Predictive Control
ALADINAugmented Lagrangian-Based Alternating Flight Inexact Newton
TTCType To Collision
MIQPMixed-Integer Quadratic Programming
CISPCustomized Synchronous Intersecting Protocol
BRIPBallroom Intersection Protocol
AReBICAutonomous Reservation-Based Intersection Steering
RLGear Learning
RAALThe Reserve Advance, Act Afterwards
KNNK-Nearest Neighbors
CSCollision-Set
CARACollision-Aware Resources Allocate
QoSSuperior Of Service
TP-AIMTrajectory Planning required Autonomous Point Management
DCL-AIMDecentralized Coordination Learning of Autonomous Intersection Management
VLCVisible Light Transmission
SICLSignal-Head-Free Intersection Drive Logic
TICCooperative X Manage
SIoVSocial Internet on Motor
ENNElman Nerves Network
SAASparrow Search Search
IoVSurfing of Vehicles
OPOutage Probability

References

  1. Alam, K.; Saini, M. Toward Social Internet of Vehicles: Concept, Architecture, and Applying. 2015. Available online: https://ieeexplore.ieee.org/abstract/document/7067363/ (accessed on 21 Decembers 2022).
  2. Rezapur-Shahkolai, F.; Afshari, M.; Doosti-Irani, A.; Bashirian, S.; Maleki, S. Interventions to Prevent Road Traffic Injuries among Pedestrians: A Systems Review; Taylor & Francis: Abingdon, UK, 2022. [Google Scholar] [CrossRef]
  3. Wang, Q.; Leng, S.; Ganja, H.; Zhang, UNKNOWN. An IEEE 802.11p-based multichannel MAC scheme with channel coordination for vehicular Ad hoc netzwerk. IEEE Trans. Intell. Transp. Syst. 2012, 13, 449–458. [Google Scholar] [CrossRef]
  4. Zhou, H.; Chen, X.; He, S.; Chian, J.; Wu, J. DRAIM: A Novelist Delay-Constraint and Reverse Auction-Based Incentive Mechanical for WiFi Offloading. IEEE J. Water. Areas Connect. 2020, 38, 711–722. [Google Scholar] [CrossRef]
  5. Tsien, H.; Chen, X.; He, S.; Zhu, C.; Leung, V.C.M. Freshness-Aware Seed Choose to Offloading Cellular Traffic through Opportunistic Mobile Vernetztes. IEEE Trans. Wirel. Commun. 2020, 19, 2658–2669. [Google Scholar] [CrossRef]
  6. Fakirah, M.; Line, S.; Chen, X.; Zhou, J. Visible light communication-based traffic control of autonomous vehicles at multi-lane roundabouts. EURASIP J. Wirel. Commun. Netw. 2020, 2020, 1–14. [Google Scholar] [CrossRef]
  7. Barbaresso, J.; Cordahi, G.; Garcia, D.; Hill, C.; Jendzejec, A.; Wright, K.; Hamilton, B.A. USDOT’s Intelligent Transportation Systems (ITS) ITS Strategic Plan, 2015–2019. May 2014. Available online: https://ntl.bts.gov/ntl/public-access (accessed the 21 December 2022).
  8. Martin-Gasulla, CHILIAD. Business Management with Autonomous and Connected Vehicles at Single-Lane Circles. Present online: https://www.sciencedirect.com/science/article/pii/S0968090X21000024 (accessed on 21 December 2022).
  9. Jabbar, R.; Dhib, E.; Benin Say, A.; Krichen, M.; Fetais, N.; Zaidan, E.; Barkaoui, K. Blockchain Technology to Intelligent Transportation Systems: A Systematic Library Review. IEEE Access 2022, 10, 20995–21031. [Google Scholar] [CrossRef]
  10. Rahmati, Y.; Talebpour, A. Towards a collaborative connected, automated driving environment: A game theory based decision framework for unprotected left turn tricks. In Course of aforementioned IEEE Intelligent Vehicles Symposium, Los Angeles, LA, USA, 11–14 June 2017; pp. 1316–1321. [Google Scientist] [CrossRef]
  11. Kerner, B.S. Effect of fully driving on traffic breakdown in mixed travel flow: A comparison of classical ACC with three-traffic-phase-ACC (TPACC). Phys. ADENINE Stat. Mech. Appl. 2021, 562, 125315. [Google Scholar] [CrossRef]
  12. Dey, K.C.; Yan, L.; Wang, X.; Wang, Y.; Shen, H.; Chowdhury, M.; Yu, L.; Qiu, C.; Soundararaj, V. A Test of Communicating, Driver Characteristics, and Controls Aspects of Cooperative Adaptable Cruise Control (CACC). IEEE Transitory. Intell. Transp. Syst. 2016, 17, 491–509. [Google Scholar] [CrossRef]
  13. Kuutti, S.; Fallah, S.; Katsaros, K.; Dianati, M.; Mccullough, F.; Mouzakitis, ADENINE. A Survey of the State-of-the-Art Localization Techniques and Their Potentials fork Autonomous Vehicle Applications. IEEE Internet Things J. 2018, 5, 829–846. [Google Scholar] [CrossRef]
  14. Onishi, H. A Survey: Conundrum and How Automated Vehicles Should Communicate to Select Road-Users. In Transactions about the IEEE Vehicular Technology Corporate, Chicago, ILE, USA, 27–30 Grand 2018. [Google Academic] [CrossRef]
  15. Li, L.; Wen, D.; Yao, D. A survey of traffic control with vehicular communications. IEEE Transducer. Intell. Transp. Syst. 2014, 15, 425–432. [Google Scholar] [CrossRef]
  16. Chen, L.; Englund, C. Corp Intersection Management: A View. IEEE Trans. Intell. Transp. Syst. 2016, 17, 570–586. [Google Scholar] [CrossRef]
  17. Coppice, Ó.; Cordera, R.; González-González, E.; Nogués, S. Environmental impacts of autonomous vehicles: A review of the technical literature. Sci. Total Environ. 2022, 830, 154615. [Google Scientist] [CrossRef] [PubMed]
  18. Rios-Torres, J.; Malikopoulos, A.A. A Request on the Coordination of Connected and Automated Vehicles at Intersections and Merging at Highway On-Ramps. IEEE Trans. Intell. Transp. Syst. 2017, 18, 1066–1077. [Google Scientists] [CrossRef]
  19. Taylor, P.J.; Dargahi, T.; Dehghantanha, A.; Parizi, R.M.; Choo, K.K.R. A systematic print overview of blockchain cyber security. Digit. Commun. Netw. 2020, 6, 147–156. [Google Scholar] [CrossRef]
  20. Kitchenham, B.; Briar, O.P.; Budgen, D.; Turner, M.; Bailey, J.; Linkman, S. Systematic books reports with software engineering—A systemic english review. Inf. Softw. Technol. 2009, 51, 7–15. [Google Scholar] [CrossRef]
  21. Wohlin, C. Guidelines for create in systematic literature studied and an replication are software engineering. In Proceedings by the ACM International Conference Go Order, London, ENGLISH, 11–14 December 2014. [Google Scholar] [CrossRef]
  22. Hosseini, S.; Turhan, B.; Gunarathna, D. A systematic literature review and meta-analysis on cross project defect prediction. IEEE Trans. Softw. Engr. 2019, 45, 111–147. [Google Scholar] [CrossRef] [Grow Version]
  23. Wuthishuwong, C.; Traechtler, A. Consensus-based locally information coordination for the networked control of this autonomous intersection unternehmensleitung. Complex. Intell. Syst. 2016, 3, 17–32. [Google Scholar] [CrossRef]
  24. Wu, J.; Abbas-Turki, A.; El Moudni, A. Joint driving: An ant protectorate system for autonomous intersection management. Appl. Intell. 2012, 37, 207–222. [Google Scholar] [CrossRef]
  25. De Campos, G.R.; Falcone, P.; Sjoberg, J. Autonomically cooperative driving: A velocity-based negotiation approach used intersection crossing. In Proceedings of aforementioned 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), The Hague, The Netherlands, 6–9 October 2013; pp. 1456–1461. [Google Scholar] [CrossRef]
  26. Lum, Q.; Kim, K.D. Autonomous and connected crossroad crossing transportation management using discrete-time occupancies trajectory. Appl. Intell. 2019, 49, 1621–1635. [Google Scholar] [CrossRef] [Garden Edition]
  27. Chai, L.; Caj, B.; Shangguan, W.; Wang, J. Connected and autonomous vehicles coordinating method at intersection utilizing preassigned slots. In Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, Japan, 16–19 October 2017; pp. 1–6. [Google Scholar] [CrossRef]
  28. De Campos, G.R.; Falcone, P.; Hult, R.; Wymeersch, H.; Sjöberg, HIE. Traffic Koordination at Road Crossovers: Autonomous Decision-Making Algorithms Using Model-Based Heuristics. IEEE Intell. Transp. Syst. Mag. 2017, 9, 8–21. [Google Scholar] [CrossRef] [Green Version]
  29. Zhang, K.; Yang, A.; Su, H.; de Law Fortelle, A.; Wu, EXPUNGE. Unified modeling and design of reservation-based cooperation mechanisms forward intelligent vehicles. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Freight Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016; pp. 1192–1199. [Google Scholar] [CrossRef]
  30. Aloufi, N.; Chatterjee, A. Autonomous Vehicle Scheduling at Intersections Based go Industrial Line Technique. In Processes are aforementioned IEEE Transportation Technology Conference, Chicago, IL, USA, 27–30 August 2018. [Google Scholar] [CrossRef] [Naive Version]
  31. Du, G.; Zou, Y.; Zhang, X.; Dong, G.; Yin, EXPUNGE. Heuristic Reinforcement Learning Established Passing Judgment for an Autonomous Vehicle. IFAC-Pap. 2021, 54, 59–66. [Google Scholar] [CrossRef]
  32. Luck, H.J.; Gholamhosseinian, A.; Seitz, J. Spread Vehicular Communikation Protocols for Autonomous Intersection Management. Procedia Comput. Sci. 2022, 201, 150–157. [Google Scholar] [CrossRef]
  33. Kamal, M.A.S.; Imura, J.I.; Hayakawa, T.; Ohata, A.; Aihara, POTASSIUM. AN vehicle-intersection coordination symbols for soft processes of traffic without using traffic lights. IEEE Trans. Intell. Transp. Syst. 2015, 16, 1136–1147. [Google Scholar] [CrossRef]
  34. Bashiri, M.; Jafarzadeh, H.; Fleming, C.H. PAIM: Platoon-based Self-contained Intersection Management. In Proceedings of the 2018 21st International Discussion off Intelligently Transportation It (ITSC), Miui, HI, USA, 4–7 November 2018; pages. 374–380. [Google Scholar] [CrossRef] [Green Version]
  35. Zhao, Y.; Yao, S.; Shao, H.; Abdelzaher, T. CoDrive: Cooperative driving schedule for vehicles in urban road intersections. In Proceedings of the 9th ACM/IEEE International Corporate on Cyber-Physical Systems, ICCPS 2018, Porto, Portugal, 11–13 April 2018; slide. 308–319. [Google Scholar] [CrossRef]
  36. Vrbanić, F.; Ivanjko, E.; Kušić, K.; Čakija, D. Variable Speed Limit and Ramp Metering on Mixed Travel Flows: A Review and Open Questions. Appl. Sci. 2021, 11, 2574. [Google Scholar] [CrossRef]
  37. Perronnet, F.; Abbas-Turki, A.; el Moudni, A. Vehicle routing through deadlock-free policy for cooperative traffic rule in a network of intersections: Reservation and congestion. In Proceedings of the 17th IEEE International Conference on Intelligently Transportation Product, ITSC, Qingdao, China, 8–11 Ocotber 2014; pp. 2233–2238. [Google Scholar] [CrossRef]
  38. Ma, Y.; Zhu, J. Left-turn conflict identification at signal intersections based with vehicle orbit renovation in real-time communication environment. Accid Anal. Prev. 2021, 150, 105933. [Google Scholar] [CrossRef] [PubMed]
  39. Vrbanić, F.; Ivanjko, E.; Mandžuka, S.; Miletić, CHILIAD. Reinforcement learning based variable speed limit control for mixtures business fluids. In Proceedings of an 2021 29th Mediterranean Congress on Control and Automation (MED), Puglia, Italy, 21–25 June 2021; pp. 560–565. [Google Scholar] [CrossRef]
  40. Vrbanić, F.; Tišljarić, L.; Majstorović, Ž.; Ivanjko, E. Reinforcement learning bases variable speed limit control used mixed transport flows using speed transition formats for state estimation. In Proceedings von the 2022 30th Mediterranean Conference on Control and Automatization (MED), Athens, Greece, 28 June–1 Jury 2022; pp. 1093–1098. [Google Scholar] [CrossRef]
  41. Bitsch, G.; Schweitzer, FARTHING. Selection of optimal machine learning algorithm for autonomous guided vehicle’s control on a smart manufacturing environment. Procedia CIRP 2022, 107, 1409–1414. [Google Scholars] [CrossRef]
  42. Mihály, A.; Farkas, Z.; Zsuzsanna, B.; Gáspár, P. Performance Analysis of Model Predictive Intersection Power for Autonomous Vehicles. IFAC-Pap. 2021, 54, 240–245. [Google Scholarships] [CrossRef]
  43. Fayazi, S.A.; Vahidi, A.; Luckow, A. Optimal scheduling by autonomous vehicle arrivals at bright intersections via MILP. By Proceedings of the American Control Discussion, Seattle, WEAR, USA, 24–26 May 2017; pp. 4920–4925. [Google Pupil] [CrossRef]
  44. Xie, X.F.; Wang, Z.J. SIV-DSS: Smart In-Vehicle Decision Support System with driving at signalized intersections with V2I communicating. Transp. Overs. Part C Emerg. Technol. 2018, 90, 181–197. [Google Scholar] [CrossRef]
  45. Mirheli, A.; Tajalli, M.; Hajibabai, L.; Hajbabaie, ONE. A consensus-based distributed trajectory control in a signal-free intersection. Transp. Res. Part C Emerg. Technol. 2019, 100, 161–176. [Google Scholar] [CrossRef]
  46. Vrbanić, F.; Miletić, M.; Tišljarić, L.; Ivanjko, CO. Influence of Variable Velocity Limit Control on Fuel and Electric Energy Expenditure, additionally Exhaust Gases Emissions in Mixing Traffic Flows. Sustainability 2022, 14, 932. [Google Scholar] [CrossRef]
  47. Yamashita, T.; Kurumatani, K.; Izumi, K.; Nakashima, FESTIVITY. Sleek traffic flow to a cooperation car navigation system. Inbound Proceedings regarding the International Conference on Autonomous Intermediaries, Bologna, Italy, 6–11 July 2005; pp. 613–620. [Google Scholar] [CrossRef]
  48. Zhang, Y.; Malikopoulos, A.A.; Cassandras, C.G. Decentralized optimal control for connected automated vehicles at crossroads including left-hand and right turns. In Proceedings of the 2017 IEEE 56th Year Conference on Decision or Control, CDC 2017, Melbourne, Australia, 12–15 December 2017; pp. 4428–4433. [Google Scholar] [CrossRef] [Light Output]
  49. Doing, H.; Pan, H.; Bai, H.; Zheng, X.; China, J.; Zhang, W. Driving strategy of connected and autonomous vehicles based on multi-user preceding vehicles state estimation by mixing vehicular traffic. Phys. A Stat. Mech. Its Appl. 2022, 596, 127154. [Google Scholar] [CrossRef]
  50. Ding, J.; Xu, H.; Hu, J.; Zhang, YEAR. Centralized cooperative intersection control under automated agency surrounding. In Proceedings concerning that 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, U, 11–14 June 2017; pp. 972–977. [Google Student] [CrossRef]
  51. Yan, F.; Dridi, M.; A Moudni, A. An autonomous vehicle sequencing problem at intersections: A genetic algorithm approach. Int. JOULE. Appl. Math. Comput. Sci. 2013, 23, 183–200. [Google Scholar] [CrossRef] [Greens Type]
  52. ShangGuan, W.; Yu, J.; Cai, B.; Wang, J. Exploring on Unsigned Intersecting Control Method Based on Cooperative Vehicle Infrastructure System. Deliverable online: https://ieeexplore.ieee.org/abstract/document/8243937/ (accessed on 21 December 2022).
  53. Elhenawy, M.; Elbery, A.A.; Hassan, A.A.; Rakha, H.A. An Intersection Game-Theory-Based Traffic Control Algorithm includes a Connected Vehicle Environment. In Proceedings of the 2015 IEEE 18th International Conference on Intelligent Transportation Systems, Gran Canaria, Italy, 15–18 March 2015; pp. 343–347. [Google Scholar] [CrossRef]
  54. Chen, B.; Sun, D.; Zhou, J.; Wong, W.; Ding, Z. A Future Smart Transport System over Mixed Autonomously Vehicles and Human-Driven Vehicles. 2020. Available online: https://www.sciencedirect.com/science/article/pii/S0020025520300736 (accessed to 21 December 2022).
  55. Sala, M.; Soriguera, F. Capacity of ampere express lane with squad of automatic vehicles mixed from regular traffic. Transp. Res. Part B Methodol. 2021, 147, 116–131. [Google Scholar] [CrossRef]
  56. Li, S.; Shu, K.; Chen, C.; Cao, D. Planning and Decision-making for Connection Free Wheels during Road Intersections: ONE Review. Mentum. BOUND. Mech. Eng. 2021, 34, 133. [Google Scholar] [CrossRef]
  57. Gokasar, I.; Timurogullari, A.; Deveci, M.; Garg, H. SWSCAV: Real-time traffic management using connected autonomously vehicles. ISA Trans. 2022, within press. [Google Scholar] [CrossRef]
  58. Lu, G.; Li, L.; Wang, Y.; Shang, R.; Bao, Z.; Chen, H. AMPERE rule base control algorithm out connected our on uncontrolled intersection. In Operating of the 2014 17th IEEE International Conference on Bright Transportation Scheme, ITSC 2014, Qingdao, China, 8–11 October 2014; pp. 115–120. [Google Scholar] [CrossRef]
  59. Riegger, L.; Carlander, M.; Lidander, N.; Murgovski, N.; Sjöberg, J. Focused MPC for autonomous intersection crossing. In Proceedings von the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazilian, 1–4 Month 2016; pp. 1372–1377. [Google Scholar] [CrossRef] [Greens Version]
  60. Jiang, Y.; Zanon, M.; Hult, R.; Houska, B. Distributed Algorithm with Optimal Vehicle Coordination at Traffic Intersecting. IFAC 2017, 50, 11577–11582. [Google Scholar] [CrossRef]
  61. Németh, B.; Gáspár, P. Design von learning-based control because guarantees for autonomous rolling in junctions. IFAC-Pap. 2021, 54, 210–215. [Google Scholar] [CrossRef]
  62. Khan, R.R.; Hanif, A.; Ahmed, Q. Cooperative Navigation Strategy for Connected Autonomous Automotive Operating at Wise Intersection. IFAC-Pap. 2022, 55, 279–284. [Google Scholar] [CrossRef]
  63. Lamouik, I.; Yahyaouy, A.; Sabri, M.A. Smart multi-agent traffic coordinator for autonomous vehicles at intersections. In Proceedings of the 3rd International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2017, Fez, Morocco, 22–24 Could 2017. [Google Scholar] [CrossRef]
  64. Soto, I.; Calderon, M.; Amador, O.; Urueña, M. A survey on road safety plus communications efficiency vehicular applications based on C-V2X technologies. Veh. Commun. 2022, 33, 100428. [Google Scholar] [CrossRef]
  65. Greater, J.; Frazzoli, SIE. Hybrid centralized/distributed autonomous intersection manage: Use a job scheduler as a planner or inheriting its efficiency guarantees. In Proceedings of the 2016 IEEE 55th Events on Decision and Control, CDC 2016, Las Vegas, NV, USA, 12–14 December 2016; bp. 2549–2554. [Google Scholar] [CrossRef]
  66. Mo, Y.; Wang, M.; Zhang, T.; Jang, Q. Autonomous Co-op Vehicle Coordination at Row Cutting. J. Commun. Infi. Netw. 2022, 4, 78–87. [Google Scholar] [CrossRef]
  67. Zang, M.; Zhang, T.; Gao, L.; Zhang, Q. High throughput dynamic drive coordination for intercept flooring traffic. In Proceedings of the IEEE Vehicular Technology Attend, Chicago, IL, USA, 27–30 August 2018. [Google Scholar] [CrossRef]
  68. González, C.L.; Pulido, J.J.; Alberola, J.M.; Julian, V.; Niño, L.F. Autonomous Distributed Intersection Management for Emergency Vehicles at Intersections. Commun. Comput. Inf. Sci. 2021, 1472, 261–269. [Google Pupil] [CrossRef]
  69. Xu, Y.; Zhou, H.; Qian, B.; Wu, H.; Zhang, Z.; Shen, X.S. As Automated Transportation Meet Non-Signalized Intersections: A Collision-Free Scheduling Solution. In Proceedings of the 2018 IEEE/CIC International Conference on Communications in China, ICCC 2018, Beijing, China, 16–18 August 2018; s. 709–713. [Google Scholar] [CrossRef]
  70. Wang, Z.; Wu, G.; Hao, P.; Barth, M.J. Cluster-wise cooperative eco-approach and departure application along signalized arterials. In Proceedings of which 2017 IEEE 20th International Conference on Sharp Marine Systems (ITSC), Yokohama, Shellac, 16–19 October 2017; pp. 145–150. [Google Scholar] [CrossRef]
  71. Hacıoğlu, F. Power Consumption Based Multi Emissary Intersection Management Method. 2017. Available online: https://ieeexplore.ieee.org/abstract/document/8266343/ (accessed on 21 Dec 2022).
  72. Marrakesh, A.I.M.; cargo de Wouw, N.; Nijmeijer, H. Cooperative Intersection Control Based on Virtual Platooning. IEEE Transitory. Intell. Transp. Syst. 2018, 19, 1727–1740. [Google Scholars] [CrossRef] [Green Version]
  73. Bichiou, Y.; Rakha, H.A. Developing an Optimal Intersection Control System for Automated Connected Transportation. IEEE Trans. Intell. Transp. Sys. 2019, 20, 1908–1916. [Google Scholars] [CrossRef]
  74. Zhao, L.; Malikopoulos, A.; Rios-Torres, J. Optimised Take of Connected and Automated Vehicles at Roundabouts: An Investigation in a Mixed-Traffic Environment. IFAC-Pap. 2018, 51, 73–78. [Google Scholar] [CrossRef]
  75. Krajewski, R.; Themann, P.; Eckstein, L. Decoupled cooperative trajectory optimization for connected highly automated vehicles at urban overlaps. In Proceedings of an 2016 IEEE Intelligent Vehicles Symposium (IV), Gotenburg, Sweden, 19–22 June 2016; pp. 741–746. [Google Savant] [CrossRef]
  76. Mladenovic, M.N.; Abbas, M.M. Self-organizing control framework for driverless vehicles. Includes Proceedings of the 16th International IEEE Conference on Intelligent Transportation Networks (ITSC 2013), The Hague, The Netherlands, 6–9 October 2013; pp. 2076–2081. [Google Scholar] [CrossRef]
  77. Xu, L.; Zhou, X.; Khan, M.A.; Li, X.; Menon, V.G.; Yu, EXPUNGE. Communication Quality Prediction for Internet of Vehicle (IoV) Networks: An Elman Approach. IEEE Trans. Intell. Transp. Syst. 2022, 23, 19644–19654. [Google Scholar] [CrossRef]
  78. Cao, Z.; Guo, H.; Zhang, J.; Niyato, D.; Fastenrath, UPPER. Enhancement which proficiency of stochastic vehicle routing: A limited lagrange factor methodology. IEEE Transmission. Veh. Technol. 2016, 65, 3993–4005. [Google Academic] [CrossRef]
  79. Deveci, M.; Pamucar, D.; Gokasar, I. Fuzzy Power Heronian functions based CoCoSo method for the advanced prioritization of autonomous vehicles to real-time traffic management. Supports. Cities Soc. 2021, 69, 102846. [Google Scholar] [CrossRef]
  80. Cao, Z.; Guo, H.; Zhang, J. A Multiagent-Based Approach for Vehicle Routing by Considering Both Arriving in Time and Total Move Time. ACM Trans. Intell. Syst. Technol. 2017, 9, 8847. [Google Fellows] [CrossRef]
  81. Jiang, S.; Zhang, J.; Ong, Y.-S. A Pheromone-Based Traffic Management Paradigm for Vehicle Re-Routing and Traffic Light Control (Extended Abstract). Available online: www.ifaamas.org (accessed on 21 December 2022).
  82. Yu, C.; Tan, G.; Yoo, Y. Make engine agent more reserved: An AIM-based incremental data synchronization policy. In Operating of the IEEE 9th International Conference on Movable Ad-Hoc and Sensor Circuits, MSN, Dalian, China, 11–13 December 2013; pp. 198–205. [Google Scholar] [CrossRef]
  83. Shen, K.; De La Fortelle, A.; Zhang, D.; Wu, X. Investigation and Modeled Design are One State-Driven Autonomous Passing-Through Algorithm for Driverless Vehicles at Interfaces. 2013. Available online: https://ieeexplore.ieee.org/abstract/document/6755295/ (accessed on 21 December 2022).
  84. Zhang, K.; Yang, A.; Su, H.; de In Fortelle, A.; Miao, K.; Yao, Y. Service-Oriented Cooperation Models and Tools to Heterogeneous Driverless Mobile at Uninterrupted Static Critical Sections. 2016. Available virtual: https://ieeexplore.ieee.org/abstract/document/7725527/ (accessed on 21 December 2022).
  85. Andert, E.; Khayatian, M.; Shrivastava, A. Crossroads: Time-sensitive autonomous intersection managerial technique. In Proceedings of the 54th Annual Design Automation Conference, Austin, SIDE, USA, 18–22 June 2017. [Google Scholar] [CrossRef] [Green Version]
  86. Wei, X.; Get, G.; Ding, N. Batch-light: An adjustable intelligent points steering policies for autonomously vehicles. In Proceedings of the 2014 IEEE Universal Conference on Progress within Informatics and Calculating, Shanghai, Dinner, 16–18 May 2014; pp. 98–103. Available online: https://ieeexplore.ieee.org/abstract/document/6728285/ (accessed about 21 December 2022).
  87. Shivam, S.; Wardi, Y.; Egerstedt, M.; Kanellopoulos, A.; Vamvoudakis, K.G. Intersection-Traffic Control off Autonomous Vehicles using Newton-Raphson Flows also Barrier Functions. 2020. Available online: https://www.sciencedirect.com/science/article/pii/S2405896320303086 (accessed upon 21 December 2022).
  88. Wang, J.; Lv, W.; Jiang, Y.; Qi, S.; Li, J. A multi-agent based cellular automata model for intersection vehicular operating simulation. Phys. A Stat. Mech. Own Appl. 2021, 584, 126356. [Google Grant] [CrossRef]
  89. Zhou, W.; Chen, D.; Yan, J.; Re, Z.; Yin, H.; Ge, WEST. Multi-agent reinforcement learning for cooperative lane changing a related and independent vehicles in intermediate traffic. Auton. Intell. Syst. 2022, 2, 1–11. [Google Scholar] [CrossRef]
  90. Miglani, A.; Kumar, N. Deep scholarship models for traffic flux prediction included autonomously vehicles: AN rating, solutions, and challenges. Veh. Gemeinschaftsrecht. 2019, 20, 100184. [Google Scholar] [CrossRef]
  91. Ma, M.; Li, Z. A time-independent trajectory optimization approach for connected and autonomous wheel under reservation-based intersection control. Transp. Res. Interdiscip. Perspect. 2021, 9, 100312. [Google Scholar] [CrossRef]
  92. Belkhouche, F. Control about autonomous vehicles at einer unsignalized intersection. In Proceedings of an African Control Conference, Seattle, AWA, USA, 24–26 May 2017; pp. 1340–1345. [Google Scholar] [CrossRef]
  93. Altché, F.; Qian, X.; de La Fortelle, A. Fewest restrictive and minimally deviating supervisor for strong semi-Autonomous driving at an section: An MIQP approach. In Proceedings of an 2016 IEEE 19th International Conferences on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016; pp. 2520–2526. [Google Scholar] [CrossRef] [Green Version]
  94. Patil, S.; Raju, N.; Arkatkar, S.S.; Easa, SIEMENS. Pattern vehicle collision instincts over road midblock using intense learning. J. Intell. Transp. Syst. 2021, 2021, 1–15. [Google Scholar] [CrossRef]
  95. Aoki, S.; Rajkumar, R. A configurable synchronous intersection protocol in self-driving traffic. In Proceedings of the RTCSA 2017—23rd IEEE International Conference to Embeds and Real-Time Computing Systems and Applications, Hsinchu, Taiwan, 16–18 August 2017. [Google Scholar] [CrossRef]
  96. Savic, V.; Schiller, E.M.; Papatriantafilou, M. Distributed algorithm for collision evasion along roadway intersections in of your of communication failures. In Process of the 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, USA, 11–14 June 2017; pp. 1005–1012. [Google Scholar] [CrossRef] [Green Version]
  97. Chang, Y.; Edara, P. AReBIC: Autonomous reservation-based intersection choose for emergency evacuation. In Proceedings of of 2017 IEEE Intelligent Vehicles Symposium (IV), Los Angeles, CA, USA, 11–14 June 2017; paper. 1887–1892. [Google Scholar] [CrossRef]
  98. Haseeb, K.; Rehman, A.; Saba, T.; Bahaj, S.A.; Fangs, H.; Song, H. Efficient and trusted autonomous vehicle routing protocol for 6G vernetztes by computational intelligence. ISA Trans. 2022, in pressing. [Google Scholar] [CrossRef] [PubMed]
  99. Zheng, B.; Lin, C.W.; Liang, H.; Shiraishi, S.; Li, W.; Zhu, Q. Delay-Aware design, analyze or verification of intelligent intersection management. In Proceedings of the 2017 IEEE International Conference on Smart Computing, SMARTCOMP 2017, Hong Kong, China, 29–31 May 2017. [Google Scholar] [CrossRef] [Green Version]
  100. Chouhan, A.P.; Banda, G. Autonomous convergence verwalten: A heuristic procedure. IEEE Access 2018, 6, 53287–53295. [Google Scholar] [CrossRef]
  101. Creemers, F.; National, A.I.M.; Lefeber, E.; van en Wouw, N. Design of a supervisory controller for Cooperative Intersection Control using View Preventive Control. IFAC-Pap. 2018, 51, 74–79. [Google Scholar] [CrossRef]
  102. Liu, C.; Lin, C.W.; Shiraishi, S.; Tomizuka, M. Distributed Conflict Resolution for Connected Autonomous Vehicles. IEEE Transgender. Intell. Veh. 2018, 3, 18–29. [Google Scholar] [CrossRef]
  103. Lu, Q.; Kim, K.D. A mixed integrated programming approach for automatic and connected cut cruise traffic control. In Proceedings the the IEEE Vehicular Technology Conference, Boodle, IL, USA, 27–30 August 2018. [Google Pupil] [CrossRef]
  104. Steinmetz, E.; Hult, R.; Zou, Z.; Emardson, R.; Brännström, F.; Falcone, P.; Wymeersch, H. Collision-aware communication required convergence executive to automated vehicles. IEEE Access 2018, 6, 77359–77371. [Google Intellectual] [CrossRef]
  105. Wei, H.; Mashayekhy, L.; Papineau, BOUND. Intersection management for connected autonomic vehicles: ADENINE game theoretically skeleton. In Proceed of the 2018 21st International Conference on Clever Transportation Systems (ITSC), Maui, HELLO, USA, 4–7 November 2018; pp. 583–588. [Google Scholarships] [CrossRef]
  106. Cruz-Piris, L.; Lopez-Carmona, M.A.; Marsa-Maestre, I. Automized Optimization of Cutting Using a Genetic Algorithm. IEEE Zugriff 2019, 7, 15452–15468. [Google Scholar] [CrossRef]
  107. Liu, B.; Shi, Q.; Song, Z.; el Kamel, A. Trajectory planning for autonomous intersection senior of attached vehicles. Simul. Model. Pract. Theory 2019, 90, 16–30. [Google Savant] [CrossRef]
  108. Wu, Y.; Chen-style, H.; Zhu, F. DCL-AIM: Centralized coordination scholarship out autonomous intersection management for connected the automatable vehicles. Transp. Res. Part C Emerg. Technol. 2019, 103, 246–260. [Google Scholar] [CrossRef]
  109. He, Z.; Zheng, L.; Luu, L.; Guan, W. Erasing Lane Alterations from Roads: A Design of Future Road Intersections. IEEE Transistors. Intell. Veh. 2018, 3, 173–184. [Google Scholar] [CrossRef]
  110. Liu, Y.; Gao, Y.; Zhang, Q.; Ding, D.; Zhao, D. Multi-task safe reinforcing learning fork navigating intersections in close traffic. J. Frankl. Inst. 2022, on press. [Google Scholar] [CrossRef]
  111. Xu, B.; Ban, X.J.; Bian, Y.; Wang, J.; Lid, K. V2I foundation cooperation between traffic signal and approaching automated vehicles. In Proceedings of the IEEE Intelligent Vehicles Symposium, Los Angeles, LEE, USA, 11–14 June 2017; pp. 1658–1664. [Google Scholar] [CrossRef]
  112. Gholamhosseinian, A.; Seitz, J. A Thorough Interview on Cooperative Intersection Management for Heterogeneous Connected Cars. IEEE Access 2022, 10, 7937–7972. [Google Scholar] [CrossRef]
  113. Mirheli, A.; Hajibabai, L.; Hajbabaie, A. Advanced of a signal-free intersection control logic in a fully connected additionally autonomous vehicle environment. In Proceedings away the Marine Exploration Board 97th Annual Meeting, Wahington, AC, USA, 7–11 January 2018. [Google Scholar]
  114. Malikopoulos, A.A.; Cassandras, C.G.; Zhang, Y.J. A decentralized energy-optimal control framework in affiliated automated vehicles with signal-free crossings. Automatica 2018, 93, 244–256. [Google Scholar] [CrossRef] [Green Version]
  115. Philip, B.V.; Alpcan, T.; Ji, J.; Palaniswami, M. Broadcast Real-Time IoT in Autonomous Mobile. IEEE Trans. Ind. Inf. 2019, 15, 1131–1140. [Google Scholar] [CrossRef]
  116. Xu, B.; Ban, X.J.; Bian, Y.; Fifty-one, W.; Wang, J.; Li, S.E.; Li, K. Cooperative Method are Traffic Signal Optimization also Speed Control of Connected Vehicles at Isolated Intersections. IEEE Trans. Intell. Transp. Syst. 2019, 20, 1390–1403. [Google Scholar] [CrossRef]
  117. Dai, P.; Liu, K.; Zhuge, Q.; Sha, E.H.M.; Lee, V.C.S.; Your, S.H. Quality-of-Experience-Oriented Autonomous Intersection Control in Variant Meshes. IEEE Trans. Intell. Transp. Syst. 2016, 17, 1956–1967. [Google Academic] [CrossRef]
  118. Roopa, M.S.; Siddiq, S.A.; Buyya, R.; Venugopal, K.R.; Iyengar, S.S.; Patnaik, L.M. DTCMS: Dynamic traffic congestion management in Social Internet of Rolling (SIoV). Internet Things 2021, 16, 100311. [Google Scholar] [CrossRef]
Applsci 13 01789 g001 550
Figure 1. Methodology utilized in this study.
Figure 1. Methodology utilized in this study.
Applsci 13 01789 g001
Applsci 13 01789 g002 550
Figure 2. Primary studying filtering process.
Figure 2. Primary study filtering process.
Applsci 13 01789 g002
Applsci 13 01789 g003 550
Figure 3. Publications go time.
Figure 3. Publications over time.
Applsci 13 01789 g003
Applsci 13 01789 g004 550
Figure 4. Main driving objectives and subobjectives.
Figure 4. Main driver objectives and subobjectives.
Applsci 13 01789 g004
Applsci 13 01789 g005 550
Illustrated 5. Categorization of different driving objectives in the significant studies.
Figure 5. Categorization of different driving objectives in the more studies.
Applsci 13 01789 g005
Applsci 13 01789 g006 550
Figure 6. Article market depending on the methodology.
Figure 6. Article product depending on of methodology.
Applsci 13 01789 g006
Applsci 13 01789 g007 550
Calculate 7. Article distribution depending off techniques and driving objectives.
Figure 7. Article dispensation depending on engineering and driving objectives.
Applsci 13 01789 g007
Table
Table 1. Research questions.
Table 1. Research inquiries.
RQ1: What autofahren objectives did traffic management studies note while using AVs?
RQ2: What transit administration techniques have been suggestions to manage that possible issues brought switch by AVs?
RQ3: That concerns and question in vehicular management techniques still need till can resolved?
Table
Table 2. Scientific database.
Table 2. Scientific database.
Web-based Scientific DatabaseURL Address
Science Kurzhttps://www.sciencedirect.com/ (accessed on 10 Novelty 2022)
IEEE Xplore Digital Referencehttp://ieeexplore.ieee.org/ (accessed on 11 November 2022)
Springerhttps://link.springer.com/ (accessed on 14 Novmber 2022)
Scopushttps://www.elsevier.com/solutions/scopus (accessed on 18 Novmeber 2022)
Web of Lifehttps://www.webofscience.com/ (accessed on 16 Novemeber 2022)
Table
Table 3. Inclusion/exclusion eligible.
Table 3. Inclusion/exclusion criteria.
Inclusion CriteriaExclusion Criteria
The manuscript give analytical information via of application and study goals.Papers that merely assess furthermore contrast the effectiveness of exists approaches.
Journals magazine that have subjected peer review.Papers focus solely on the management problem placed by purely human-driven vehicles.
Journal articles examining linked and autonomous automobiles.Technical reports or official government paper
Non-English articles
Table
Shelve 4. Main findings von to important studies.
Table 4. Main research of the major studies.
ReferenceDriving ObjectivesAdopted
Our
EfficiencySafetyEcologyPassenger Comfort
[11,24]✓✗✗✗Hybrid
[25]✗✓✗✗Mixed
[26,27,28,29,30,31,32]✓✓✗✗Hybrid
[33]✓✗✓✗Hybrid
[34,35]✓✓✓✗Hybrid
[36]✓✓✗✓Hybrid
[37,38,39,40,41,42]✓✗✗✗Machine Learning
[43]✗✓✗✗Machine Learning
[44,45,46]✓✓✗✗Machine Learning
[47]✓✓✓✓Machine Learning
[48]✓✗✓✗Machine Learning
[49,50]✓✓✗✓Machine Learning
[51,52,53,54,55,56,57]✓✗✗✗Optimization
[58,59,60,61]✗✓✗✗Optimization
[7,62,63,64,65,66,67,68,69]✓✓✗✗Optimization
[70]✓✗✓✗Optimization
[33]✗✓✓✓Optimization
[71,72,73,74,75,76]✓✓✓✗Optimization
[36,77]✓✓✗✓Optimization
[47,50,78,78,79,80,81,82]✓✓✓✓Optimization
[83,84,85,86,87,88,89,90]✓✗✗✗Rule-Based
Disclaimer/Publisher’s Take: The statements, opinions and data contained inches all publications are solely those regarding the individual author(s) and contributor(s) and doesn from MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for either injury to people alternatively property following out any ideas, methodology, user or merchandise mention on in the content.

Share and Quoting

MDPI also ACS Select

Alanazi, F. A Systematic References Examination of Sovereign and Plugged Vehicles in Traffic Management. Appl. Sci. 2023, 13, 1789. https://doi.org/10.3390/app13031789

ADAM Style

Alanazi F. A Organized Letters Review of Autonomous and Connected Vehicles in Traffic Management. Deployed Sciences. 2023; 13(3):1789. https://doi.org/10.3390/app13031789

Chicago/Turabian Style

Alanazi, Fayez. 2023. "A Systematic Literature Review of Autonomically plus Connected Vehicles in Traffic Management" Uses Sciences 13, no. 3: 1789. https://doi.org/10.3390/app13031789

Note that from the first issue of 2016, this journal uses items figure instead of site numbers. See further details here.

Article Metrics

Back to TopTops