Collaborative Attack Sequence Generation Model Based on Multiagent Reinforcement Learning for Intelligent Traffic Signal System

Traffic signal systems are employed to continuously manage traffic flow and promote a safe and smooth flow of transport. Traditional traffic signal system provides instructions to stop the vehicle, but if a person breaks the traffic network system, then this system cannot apprehend them, and there are chances of malpractice. Due to the continuous increase in traffic congestion, it is necessary to evaluate the current system and implement improvised technologies to provide an intelligent traffic signal system. Hence, to increase the security of traffic signals, reduce human errors, and avoid malpractices, an intelligent traffic signal system in which the Dijkstra algorithm is practised is introduced. This paper analyzes how to resist a malicious software assault on an intelligent traffic signal system that leads to collision avoidance and check signal latency while adjusting the system during the attack.

The intelligent traffic signal (I-SIG) system aims to perform automatic and optimal signal control based on traffic situation awareness by leveraging connected vehicle (CV) technology. However, the current signal control algorithm is highly vulnerable to CV data spoofing attacks. These vulnerabilities can be exploited to create congestion in an intersection and even trigger a cascade failure in the traffic network. To avoid this issue, timely and accurate congestion attack detection and identification are essential. This work proposes a congestion attack detection approach by combining empirical prediction and analytical verification. First, we collect a range of traffic images that correspond to specific traffic snapshots which are vulnerable to potential data spoofing attacks. Based on these traffic images, an improved generative adversarial network is trained to predict whether a forthcoming attack will cause congestion with a high probability. Meanwhile, we define a group of traffic flow features. After exploring features and conducting a thorough analysis, a TGRU (tree-regularized gated recurrent unit)-based approach is proposed to verify whether congestion occurs. When we find a possible attack that can cause congestion with high probability and subsequent traffic flows also prove congestion, we can say there is a congestion attack. Thus, we can realize timely and accurate congestion attack detection by integrating empirical prediction and analytical verification. Extensive experiments demonstrate that our approach performs well in congestion attack detection accuracy and timeliness.

Intelligent traffic signal system plays an indispensable role in the current intelligent system of urban transportation, and it plays a vital role in urban development and economic construction. PLC (Programmable Logic Controller) is a general-purpose industrial control device widely used in the design of automatic control systems for industrial automation and mechanical production. With its various functions, low price and easy to use, PLC has become more and more important in industrial production. This paper will design an intelligent traffic signal system based on PLC that can handle complex traffic conditions at intersections.

With connected vehicle(CV) technology, the next-generation transportation system is stepping into its implementation phase via the deployment of Intelligent Traffic Signal System (I-SIG). Since the congestion attack was firstly discovered in USDOT (U.S. Department of Transportation) sponsored I-SIG, deployed in three cities including New York, such realistic threat opens a new security issue. In this work, from machine learning perspective, we perform a systematic feature analysis on congestion attack and its variations from last vehicle of different traffic flow pattern. We first adopt the Tree-regularized Gated Recurrent Unit (TGRU) to make explainable congestion attack prediction, in which 32-dimension features are defined to character a 8-phase intersection traffic. We then develop corresponding software-level security reinforcements suggestions, which can be further expanded as an important work. In massive experiments based on real-world intersection settings, we eventually distill 384 samples of congestion attacks to train a TGRU-based attack prediction model, and achieve an average 80% precision. We further discussed possible reinforcement defense methods according to our prediction model.

One critical issue of traffic control is the optimization of signalized intersections for improved multimodal safety and operations. Accommodating pedestrian traffic at intersections is challenging because the demands of multimodal service compete fiercely on limited green time resources. The Highway Capacity Manual prescribes that the parallel vehicle green must exceed “Walk” plus pedestrian clearance interval (PCI) timed by a design walking speed. This static PCI timing is unsafe because seniors and children are likely to be slower than the design pedestrian. Furthermore, a vehicle-flow issue arises when the prolonged PCI exceeds the operationally efficient parallel green: additional vehicle right-of-way, unnecessary for operational efficiency, preempts green time from conflicting phase(s) and increases intersectionwide queuing delays. Queuing delays necessitate a trade-off between competing multifaceted traveler needs. Fuzzy logic control (FLC) proves effective, flexible, and robust in handling competing objectives. With the dynamic PCI concept, this research developed an intelligent traffic signal system that performed friendly pedestrian accommodation and also incorporated FLC into fulfilling multifaceted vehicle needs. The potential benefits from the new system optimized with a genetic algorithm were quantified through a comparison with a standard dual-ring, eight-phase, vehicle-actuated controller, conventionally cited as NEMA (National Electrical Manufacturers Association) control. Microsimulation experiments revealed that the current countermeasure, which lowered PCI timing design speed to strengthen crossing safety, was operationally deficient. The existing timing standard cannot offer adequate safety for all pedestrians, and the NEMA system omits multifaceted vehicle needs in control logic. In contrast, the FLC system fully protects all pedestrians through dynamic PCI and smartly serves manifold vehicle needs well. The FLC system outperforms the NEMA control by embodying a reasonable trade-off between competing objectives in the management of an isolated intersection.

The study demonstrated the multimodal intelligent traffic signal system (MMITSS) simulation tool to assess the potential effects of a broader MMITSS deployment that would ultimately facilitate the site-independent analysis of MMITSS applications. The study also identified the most beneficial operational conditions for each MMITSS operational scenario by considering a combination of simulation variables and traffic demand levels. The MMITSS simulation platform consists of the Vissim microscopic traffic simulation software, the basic safety message distributor program, an Econolite ASC/3 traffic controller emulator that runs on a Windows platform, and a roadside equipment module that runs on a Linux platform. The study demonstrated that the intelligent traffic signal system reduced vehicle delay by up to 35% and increased average traffic stream speed by up to 27%. In addition, transit signal priority (TSP) reduced travel time for both transit and passenger vehicles on the corridor by up to 29% and 28%, respectively. However, TSP can increase systemwide delay because it reduces green times on the side streets. Freight signal priority (FSP) can be used effectively along major freight routes. Although FSP significantly reduced truck delay, networkwide delay was increased substantially, especially in the scenario with a large percentage of trucks in the traffic composition. The TSP and FSP bundle simulation study demonstrated that the bundle operation successfully executed a hierarchical level of priority and provided higher priority for trucks. MMITSS applications effectively improve vehicle travel time and delay for equipped and potentially nonequipped vehicles, depending on the scenarios considered. Typically, systemwide disbenefits are observed when TSP, FSP, or both are applied.

Based on the urban traffic congestion problem, this study takes 143 intersections in Haidian District and 289 intersections in Futian District as practical objects, constructs an intelligent traffic signal evaluation index system, and uses multi-source data collection and machine learning analysis methods to quantitatively evaluate the implementation effect of the system. The study finds that the average travel time is reduced by 32.5%, the energy consumption index is decreased by 28.7%, and the annual economic benefit is 4.43 billion yuan. The survey data shows that the public satisfaction rate reaches 87.6%, and the system reliability reaches 99.2%. The evaluation results indicate that the intelligent traffic signal system has significant effects on improving traffic operation efficiency and enhancing social benefits.

As a key component of next-generation transportation systems, the intelligent traffic signal system is designed to perform dynamic and optimal signal control. The USDOT (U.S. Department of Transportation) has sponsored a kind of such system - I-SIG based on Controlled Optimization of Phases (COP). Unfortunately, it has been revealed that a serious congestion attack can be caused just by one vehicle’s data spoofing. However, the existing methods focus on detecting the congestion attack and have a certain disadvantage of delay even facing periodic attacks. Thus, how to timely detect and even predict the congestion attack has become a key issue. Considering that a practical and effective congestion attack is usually continuous and periodic, we propose a novel approach for congestion attack prediction. Firstly, we set up a spoofing attack environment and collect traffic flows of variable spoofing frequencies. Among congestion attack-caused flows, we define and extract 30 important features and implement ensemble learning to build correlations between traffic flow features and abnormal congestion and attack frequency. Through supervised learning of historical data, we can recognize the current attack frequency and further realize the prediction of the subsequent congestion attack. We also report on necessary and experienced tricks for performance improvement. Extensive experiments and analyses have been conducted to demonstrate the prediction capability of our proposed approach.KeywordsCongestion attackPredictionSupervised learningSecurity analysisTraffic signal system

Recently, there has been a huge spike in the number of automobiles in the urban areas of many countries, particularly in India. The number of vehicles are increasing rapidly and with the existing infrastructure, the traffic systems stand still during peak hours. Some of the main challenges for traffic management are the movement of overloaded vehicles beyond their restricted zone and time, reckless driving, and overlooking road safety rules. This paper proposes an Internet of Things (IoT)-based real-time Intelligent Traffic Signal System (ITSS), which consists of inductive loops and a programmable micro-controller to determine traffic density. Inter-communication in the centralized control unit sets the timer of the traffic light and synchronizes with the traffic density in real-time for smooth mobility of vehicles with less delay. Additionally, to prioritize emergency vehicles over other vehicles in the same lane, a pre-emption mechanism has been integrated through infrared sensors. The result of traffic density determines the timer of the light post in real-time, which in result enhances the smooth flow of vehicles with reduced delay for travelers. Using its automatic on-demand traffic signaling system, the presented solution has advantages over fixed systems.

the technology of radio frequency identification (RFID) is an automatic non-contact identification technique, which uses radio frequency signal to recognize target automatically, and access to data of relevant information, and can effectively complete the rapid identification of traffic information system. In this paper, the characteristics and basic principle of radio frequency identification technology are described, the application of RFID in intelligent traffic management system for identifying vehicle identity information, automatic peccancy disposal, non-stop electronic toll collection are analyzed. The results show that, the application of RFID in intelligent traffic management system, greatly improves the management efficiency of traffic system, has bright application prospect.

The traffic system has an important influence on the sustainable development of urban social economy and people's life. At present, the traffic problem has become one of the major issues concerned by the government and the whole society. The application of GIS in urban intelligent traffic management system is a leap forward of traffic management system. With the gradual maturity of geographic multimedia information system, applying geographical multimedia information system to urban intelligent traffic management information system and urban traffic sharing information platform can make it possible to store, organize and process the multimedia information of the whole intelligent traffic management system through the shared multimedia information platform, which can realize the unified management and real-time update of traffic information, and ensure the correctness and comprehensibility of data relation more effectively, so as to avoid the redundancy of data relation, and improve the utilization rate and transmission speed of multimedia information in the system. This paper first briefly analyzes the current traffic situation and the development of intelligent traffic multimedia information system in China. Then the concepts urban intelligent traffic system based on GIS are introduced. At last, the possibility of building an urban intelligent traffic sharing multimedia information platform based on GIS is analyzed. The system framework and the basic function of the urban intelligent traffic sharing information platform based on GIS are put forward, and the key technologies of applying GIS in the urban traffic common information platform are discussed. This paper systematically expounds the application of GIS technology in the construction of urban traffic sharing multimedia information.

From the past few decades, technology is out breaking with its significant application in each and every field. Gradually, technology is becoming integral part of human life and effectively used to address many societal issues. One such issue is traffic in urban areas that leads to elongated waiting time at road intersections. An Intelligent Traffic Signal System (ITSS) can mitigate the urban traffic congestion. Already many researchers are working towards and proposed various solutions or techniques. The solution involves combination of different technologies such as Fuzzy Logic, Wireless Sensor Network, Machine Learning, Artificial Neural Networks, Internet of Things, Microcontrollers and high level computing environments. The proposed ideas are capable of adapting to the traffic demands based on real time situations on the road, resulting in efficient utilization of the available road infrastructure. In this paper, an attempt has been made to classify the traffic control signal system deployed at the intersections based on technology adopted and various research contribution for developing ITSS are also summarised.

Agent-based approaches have gained popularity in engineering applications, but its potential for advanced traffic controls has not been sufficiently explored. This paper presents a multi-agent framework that models traffic control instruments and their interactions with road traffic. A constrained Markov decision process (CMDP) model is used to represent agent decision making in the context of multi-objective policy goals, where the policy goal with the highest priority becomes the single optimization objective and the other goals are transformed as constraints. A reinforcement learning-based computational framework is developed for control applications. To implement the multi-objective decision model, a threshold lexicographic ordering method is introduced and integrated with the learning-based algorithm. Moreover, a two-stage hybrid framework is established to improve the learning efficiency of the model. While the proposed approach is potentially applicable for different road traffic operations, this paper applies the framework for traffic signal control in a network of Stockholm based on traffic simulation. The computational results show that the proposed control approach can handle a complex case of multiple policy requirements. Meanwhile, the agent-based intelligent control has shown superior performance when compared to other optimized signal control methods.

Traffic congestion and delayed emergency response remain major challenges in urban transportation due to the limitations of conventional fixed-time traffic signal systems. These systems operate with predefined signal duration and failed to adapt to real-time traffic density or provide automatic priority to emergency vehicles. This paper presents “Green Lane – Smart Signal with Emergency Priority”, an intelligent traffic signal system that dynamically controls signal timing based on real-time vehicle density while enabling priority passage for emergency vehicles. The proposed system integrates camera-based vehicle detection using Python and Open CV with an ESP32 microcontroller for adaptive traffic signal control. Emergency vehicle detection triggers an immediate signal override to create a dedicated green lane, ensuring faster clearance. Experimental results obtain from a prototype implementation show reduced waiting time improve traffic flow efficiency and quicker emergency vehicle movement compared to traditional fixed time systems. The system is low-cost, scalable, and suitable for smart city traffic management applications.

With the rise of intelligent devices within Industrial Cyber-Physical Systems (ICPS), encompassing applications in traffic signal control, the vulnerability of devices such as On-Board Units and Roadside Units to attacks of data spoofing becomes a critical issue. Congestion attacks pose a significant threat to traffic security, capable of causing traffic jams by manipulating traffic signal control methods on the Internet of Vehicles. One such method is the Controlled Optimization of Phases algorithm, which is susceptible to congestion attacks. In this paper, we propose a security enhancement approach integrating advantage actor-critic reinforcement learning with a long short-term memory network. Our work extends the application of security enhancement methodologies to the context of intelligent traffic systems, that synchronously detects and disposes of attacks, ensuring the physical safety and reliable operation of ICPS. The experimental results and analysis exhibit the efficiency of our approach in terms of processing time and effectiveness.