Control In Intelligent Transportation Systems Research Articles

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

Regular Vehicle Spatial Distribution Estimation Based on Machine Learning

For the mixed traffic flow, obtaining the distribution of connected vehicles (CVs) and regular vehicles (RVs) is of great significance for road network analysis and cooperative control in intelligent transportation systems (ITSs). However, whether it is based on fixed sensors or based on CVs and traffic mechanism to estimate the spatial distribution of RVs, the implementation complexity and low estimation accuracy are the points that need to be improved. This paper proposes a regular vehicle spatial distribution estimation method using adjacent connected vehicles as mobile sensors. First, to investigate the hidden relationship between the interaction information of adjacent CVs and the spatial distribution of RVs among CVs, the Gaussian mixture model-hidden Markov model (GMM-HMM) is selected as the identification method. Then, three sets of experiments were designed to study the influence of observed features on the identification capability of the model, generalization capability validation, and comparison with other methods, respectively. Finally, the proposed method is verified by the dataset generated by the car-following model. The experimental results show that selecting the relative position and time headway as observed features can effectively reflect the regular vehicle spatial distribution between adjacent CVs. The average accuracy of the proposed method to identify the regular vehicle spatial distribution is over 93.7%, which can provide valuable suggestions for the Internet of Vehicles application.

Optimal Routing with Spatial-Temporal Dependencies for Traffic Flow Control in Intelligent Transportation Systems

In Intelligent Transportation Systems (ITS), controlling the traffic flow of a region in a city is the major challenge. Particularly, allocation of the traffic-free route to the taxi drivers during peak hours is one of the challenges to control the traffic flow. So, in this paper, the route between the taxi driver and pickup location or hotspot with the spatial-temporal dependencies is optimized. Initially, the hotspots in a region are clustered using the density-based spatial clustering of applications with noise (DBSCAN) algorithm to find the hot spots at the peak hours in an urban area. Then, the optimal route is allocated to the taxi driver to pick up the customer in the hotspot. Before allocating the optimal route, each route between the taxi driver and the hot spot is mapped to the number of taxi drivers. Among the map function, the optimal map is selected using the rain optimization algorithm (ROA). If more than one map function is obtained as the optimal solution, the map between the route and the taxi driver who has done the least number of trips in the day is chosen as the final solution This optimal route selection leads to control of the traffic flow at peak hours. Evaluation of the approach depicts that the proposed traffic flow control scheme reduces traveling time, waiting time, fuel consumption, and emission.

Sensing Technologies for Crowd Management, Adaptation, and Information Dissemination in Public Transportation Systems: A Review

Management of crowd information in public transportation (PT) systems is crucial, both to foster sustainable mobility, by increasing the user's comfort and satisfaction during normal operation, as well as to cope with emergency situations, such as pandemic crises, as recently experienced with COVID-19 limitations. This paper presents a taxonomy and review of sensing technologies based on Internet of Things (IoT) for real-time crowd analysis, which can be adopted in the different segments of the PT system (buses/trams/trains, railway/metro stations, and bus/tram stops). To discuss such technologies in a clear systematic perspective, we introduce a reference architecture for crowd management, which employs modern information and communication technologies (ICT) in order to: (i) monitor and predict crowding events; (ii) implement crowd-aware policies for real-time and adaptive operation control in intelligent transportation systems (ITSs); (iii) inform in real-time the users of the crowding status of the PT system, by means of electronic displays installed inside vehicles or at bus/tram stops/stations, and/or by mobile transport applications. It is envisioned that the innovative crowd management functionalities enabled by ICT/IoT sensing technologies can be incrementally implemented as an add-on to state-of-the-art ITS platforms, which are already in use by major PT companies operating in urban areas. Moreover, it is argued that, in this new framework, additional services can be delivered to the passengers, such as, e.g., on-line ticketing, vehicle access control and reservation in severely crowded situations, and evolved crowd-aware route planning.

Three Fog Computing Based Variants of Congestion Control in ITS

The growth of vehicles and inadequate road capacity in the urban area trigger traffic congestion and raise the frequency of road accident. Therefore the need of drastically reducing traffic congestion is a significant concern. Advancement in the technology like fog computing, Internet of Things (IoT) in Intelligent Transportation Systems (ITS) aid in the more constructive management of traffic congestion. Three IoT based Fog computing oriented models are designed in the present work for mitigating traffic congestion. The first two schemes are vehicle dependent as they control traffic congestion depending upon the number of vehicles and their direction of movement across the intersections. The third scheme is environment dependent as the agent senses the environment and controls the sequence of green signal at different routes dynamically. The performances of the three schemes in ITS are analyzed along with the comparison of storage, communication and computation overhead. The efficacy of the schemes is studied theoretically and quantitatively. The quantitative performance of the three schemes is compared with five existing schemes. On the basis of the result of the comparison, it can be concluded that the proposed schemes are capable of alleviating congestion more optimally than existing schemes due to the substantial reduction in vehicle waiting time Traffic signal control, VANET, Congestion con-trol.

An Analysis on Scheduling of Traffic Light at Urban Traffic Intersection Using Fuzzy Control Algorithm

In modern society, private cars have become the first choice for many families because of their convenience and versatility. The volume of vehicles on the road is the basis of traffic accident and traffic congestion. In urban sector the traffic congestion is normally high due to the green light time interval at four road intersections. The traffic light control and time setting are basically timer control operation at current traffic control management system, this shows that, the current system is not intelligent so that there is still heavy traffic congestion. It is vital to implement routinely adjusted schedule as per the real-time position of vehicles at urban cross road intersection. Now, there are various detector systems for traffic monitoring, like Inductive Loop microwave radar, laser, infrared, ultrasonic, magnetometer and video image processing. But they have relevant weakness, such as high cost and complex technology. As a more and more widely used technology, image processing plays an important role in the management and control of intelligent transportation system. Image processing systems are based on motion detection of vehicles, wherein computer vision algorithms extract vehicles from traffic video data for traffic density estimations. This paper is an analysis on scheduling of traffic light of traffic management system using Fuzzy Control Algorithm. With the increase of the number of vehicles and population, it will also improve the traffic jam and the mood of people because of the cause of jam. Rather than previous technology, it will be low cost and simple, which can be adopted in every place as far as possible. MATLAB tool was used to figure out the variables impact on scheduling of traffic light at urban traffic intersection. The vehicle number, vehicle speed, lane length and vehicle type variables are identified and tested against vehicle driving for conclusion on traffic management performance. From findings the results were identified as the vehicle number, vehicle speed, and vehicle type have significant positive relationship with vehicle driving. However, the lane length did not significantly affect the vehicle driving. This indicates that the lane length is less important in scheduling of traffic light at urban traffic intersection.

Multispectral Fusion Approach for Traffic Target Detection in Bad Weather

Visual traffic surveillance using computer vision techniques can be noninvasive, automated and cost effective. Traffic surveillance systems with the ability to detect, count and classify vehicles can be employed in gathering traffic statistics and achieving better traffic control in intelligent transportation systems. This works well in daylight when the road users are clearly visible to the camera, but it often struggles when the visibility of the scene is impaired by insufficient lighting or bad weather conditions such as rain, snow, haze and fog. Therefore, in this paper, we design a dual input faster region-based convolutional neural network (RCNN) to make full use of the complementary advantages of color and thermal images to detect traffic objects in bad weather. Different from the previous detector, we used halfway fusion to fuse color and thermal images for traffic object detection. Besides, we adopt the polling from multiple layers method to adapt the characteristics of large size differences between objects of traffic targets to accurately identify targets of different sizes. The experimental results show that the present method improves the target recognition accuracy by 7.15% under normal weather conditions and 14.2% under bad weather conditions. This exhibits promising potential for implementation with real-world applications.

Image-Based Visibility Estimation Algorithm for Intelligent Transportation Systems

Posted road speed limits contribute to the safety of driving, yet when certain driving conditions occur, such as fog or severe darkness, they become less meaningful to the drivers. To overcome this limitation, there is a need for adaptive speed limits system to improve road safety under varying driving conditions. In that vein, a visibility range estimation algorithm for real-time adaptive speed limits control in intelligent transportation systems is proposed in this paper. The information required to specify the speed limit is captured via a road side unit that collects environmental data and captures road images, which are then analyzed locally or on the cloud. The proposed analysis is performed using two image processing algorithms, namely, the improved dark channel prior (DCP) and weighted image entropy (WIE), and the support vector machine (SVM) classifier is used to produce a visibility indicator in real-time. Results obtained from the analysis of various parts of highways in Canada, provided by the Ministry of Transportation of Ontario, show that the proposed technique can generate credible visibility indicators to motorists. The analytical results corroborated by extensive field measurements confirmed the advantage of the proposed system when compared to other visibility estimation methods such as the conventional DCP and WIE, where the proposed system results exhibit about 25% accuracy enhancement over the other considered techniques. Moreover, the proposed DCP is about 26% faster than the conventional DCP. The obtained promising results potentiate the integration of the proposed technique in real-life scenarios.

On convexity and monotonicity in generalized aggregative games

Large-scale multi-agent systems arise in several control applications, such as demand side management in smart power networks, traffic control in intelligent transportation systems, and congestion control in communication networks. All these systems comprise a large population of noncooperative agents whose decision making process can be modeled as a generalized aggregative game. In this paper, we analyze the usual convexity assumption and the monotonicity of the so-called game mapping. Specifically, we show necessary and sufficient conditions on the problem data such that monotonicity holds. The derived conditions show that monotonicity cannot be expected in general.

Mathematic Modeling and Performance Analysis of an Adaptive Congestion Control in Intelligent Transportation Systems

In this paper, we develop a preventive congestion control mechanism applied at highway entrances and devised for Intelligent Transportation Systems (ITS). The proposed mechanism provides a vehicular admission control, regulates input traffic and performs vehicular traffic shaping. Our congestion control mechanism includes two classes of vehicles and is based on a specific priority ticket pool scheme with queue-length threshold scheduling policy, tailored to vehicular networks. In an attempt to cope with vehicular traffic fluctuation, we integrate an adaptation ticket generation module. The enhanced mechanism is then able to detect road congestion and provide performance metrics to road site units at the highway entrance. Mathematical modeling based on the embedded Markov chain method highlights the benefits of the proposed scheme. Performance analysis demonstrates the mechanism capability to accurately characterize road traffic congestion conditions, shape vehicular traffic and reduce travel time.

A Proactive Parallel Complex Event Processing Method for Large-Scale Intelligent Transportation Systems

Intelligent Transportation Systems (ITS) is one of the important application areas of the Internet of Things (IoT). The key issue is how to process the huge events generated by IoT system to support ITS. In this paper a proactive parallel complex event processing method is proposed for congestion control in large-scale ITS. A Bayesian model averaging method is used to obtain accurate predictions under different event context. Based on the predictive analysis, a parallel Markov decision processes model is designed to support decision making for large-scale ITS. An optimized parallel policy iteration algorithm is proposed based on state partition and policy decomposition. The experimental evaluations show that this method has good accuracy and scalability when used to process congestion control in large-scale ITS.

Visual traffic surveillance framework: classification to event detection

Visual traffic surveillance using computer vision techniques can be noninvasive, automated, and cost effective. Traffic surveillance systems with the ability to detect, count, and classify vehicles can be employed in gathering traffic statistics and achieving better traffic control in intelligent transportation systems. However, vehicle classification poses a difficult problem as vehicles have high intraclass variation and relatively low interclass variation. Five different object recognition techniques are investigated: principal component analysis (PCA)+difference from vehicle space, PCA+difference in vehicle space, PCA+support vector machine, linear discriminant analysis, and constellation-based modeling applied to the problem of vehicle classification. Three of the techniques that performed well were incorporated into a unified traffic surveillance system for online classification of vehicles, which uses tracking results to improve the classification accuracy. To evaluate the accuracy of the system, 31 min of traffic video containing multilane traffic intersection was processed. It was possible to achieve classification accuracy as high as 90.49% while classifying correctly tracked vehicles into four classes: cars, SUVs/vans, pickup trucks, and buses/semis. While processing a video, our system also recorded important traffic parameters such as the appearance, speed, trajectory of a vehicle, etc. This information was later used in a search assistant tool to find interesting traffic events.

Detecting Signals of Bottleneck Activation for Freeway Operations and Control

Any application of intelligent transportation systems (ITS) to freeway operations and control relies on understanding the behavior of freeway bottlenecks. By improving our understanding of the formation and dissipation of queues at active freeway bottlenecks (points characterized by the presence of queued traffic immediately upstream and unqueued traffic immediately downstream) we can improve the techniques used to manage freeway traffic—one of the hallmarks of ITS. It is shown that freeway bottlenecks' activations can be diagnosed definitively using archived inductive loop detector data (measured at 20- or 30-sec intervals) from two sites in Toronto, Canada. Once the bottlenecks' locations and times of activation were determined, potential signals of their activations were explored. It is shown that certain potential signals were evident immediately before upstream queue formation, and that these were reproducible from day to day (over three or four days examined) at the two sites studied. As a result, it is suggested that these signals be used for systematic investigation of bottleneck behavior in either real time or in retrospect, on a more widespread basis as part of a real-time ITS control system.

Modeling and Numerical Simulation of Cellular Automation Traffic Flow Model

In recent years, the traffic is developing rapidly in China, the transportation is more and more convenient, but the traffic safety problem has become the focus problem in public life. Study of the traffic problem, which is beneficial to strengthening our country citizen's traffic safety consciousness, reduce the number of traffic accidents, so as to promote the development of transportation industry in China. First, in order to promote traffic smooth effectively, cellular automation traffic flow model is constructed. By studying the double lane flow, speed, mixed ratio and the conversion rate of driving ways, it is known that the cellular automation traffic flow rule improves the lane usage rate, and stimulate traffic smooth effectively. Second, construct intelligent transportation system cellular automation model. Compare the intelligent and non-intelligent system, and the traffic capacity in different lane-changing probability varies according to density fluctuation. That is, compare the analytical result of the contrastive analysis of figure to know too high lane-changing probability is not suitable for improving the traffic flow. In other words, under the control of intelligent transportation system, the improvement on the traffic flow is not obvious, which applies to the actual situation, because intelligent transportation system has its own limit after all. The last point needed to be highlighted is that cellular automation traffic flow model does not only apply to the double-lane changing situation, but also apply to the three-lane