Intelligent Traffic Control Research Articles

English

Autonomous vehicles in public transport can perform a wide range of real-world tasks such as: moving in factories, in public transport, in search and rescue, etc., thus requiring varying degrees of auto-navigation in response to changes in the environment. This paper presents the predictive model (MPC) for the active suspension system, the vehicle's damping system, combined with Deep Q-network (DQN) algorithm reinforcement learning method applied to control self-driving cars in public transport. Intelligent traffic control system to control movement to avoid fixed obstacles or movable obstacles in the event of external interference, taking into account the comfort of the occupants of the vehicle; taking into account the load, the conveying systems; for the purpose of application in the field of intelligent transportation. The research results, built on Matlab Simulink software, show that autonomous vehicles can safely complete intelligent navigation tasks in an unknown environment and become a real system intelligent with the ability to self-study and adapt well to many different environments and various nonlinear factors.

A General Framework for Reconstructing Full-Sample Continuous Vehicle Trajectories Using Roadside Sensing Data

Vehicle trajectory data play an important role in autonomous driving and intelligent traffic control. With the widespread deployment of roadside sensors, such as cameras and millimeter-wave radar, it is possible to obtain full-sample vehicle trajectories for a whole area. This paper proposes a general framework for reconstructing continuous vehicle trajectories using roadside visual sensing data. The framework includes three modules: single-region vehicle trajectory extraction, multi-camera cross-region vehicle trajectory splicing, and missing trajectory completion. Firstly, the vehicle trajectory is extracted from each video by YOLOv5 and DeepSORT multi-target tracking algorithms. The vehicle trajectories in different videos are then spliced by the vehicle re-identification algorithm fused with lane features. Finally, the bidirectional long-short-time memory model (LSTM) based on graph attention is applied to complete the missing trajectory to obtain the continuous vehicle trajectory. Measured data from Donghai Bridge in Shanghai are applied to verify the feasibility and effectiveness of the framework. The results indicate that the vehicle re-identification algorithm with the lane features outperforms the vehicle re-identification algorithm that only considers the visual feature by 1.5% in mAP (mean average precision). Additionally, the bidirectional LSTM based on graph attention performs better than the model that does not consider the interaction between vehicles. The experiment demonstrates that our framework can effectively reconstruct the continuous vehicle trajectories on the expressway.

Opportunities and Challenges in Vehicle Tracking: A Computer Vision-Based Vehicle Tracking System

This study proposes a tracking system for the transportation field utilizing state-of-the-art detection heads and tracking algorithm. We utilize detection heads (YOLO5, FRCNN, DETR) with tracking algorithms (ByteTrack) under different camera settings and three weather scenarios. The tracking results are summarized regarding Recall and precision, IDF1, IDP, IDR, MOTA, MOTP, tracking consistency, and processing time. In this study, we utilize novel Transformer architecture, a deep learning network based on the attention mechanism. Due to its strong capabilities, attention architecture has recently attracted a huge amount of attention in computer vision. This analysis showed that DETR was outperforming other algorithms in terms of tracking consistency, and it was performing similarly to FRCNN in Recall with better performance at the camera installed on intersections. Both FRCNN and DETR were outperforming YOLO5 in terms of Recall. YOLO5 is almost outperforming other algorithms in terms of Precision, MOTA, IDF1, and inference time. Considering intersections and highways, this paper has practical significance in intelligent traffic management and control.

Traffic Safety Oriented Multi-Intersection Flow Prediction Based on Transformer and CNN

Intelligent traffic signal control is one of the important means to ensure traffic safety. Effective signal control can make traffic flow fast and smooth, which first needs current and future traffic information. As the control of one intersection may affect adjacent intersections, this paper proposes to predict future traffic flow with consideration of multi-intersections. It can dynamically improve traffic conditions and reduce traffic congestion. Based on various nonlinear spatial relationships at correlated multi-intersections and the potential time-dependent relationship in traffic volume, a traffic flow prediction method named CNNformer which combines transformer with CNN, is proposed. The convolution neural network (CNN) and transformer are used to extract the spatial and temporal features of correlated multiple intersections. The learnable time code is embedded into transformer’s location code, and the location information and time information are injected into the model to help it learn the time characteristics of traffic volume. This study also considers the impact of cyclical traffic flow pattern and proposes CNNformer+. In the method, all of the data from the previous time window, as well as the data from the prior week and month, are correspondingly entered into the network. Finally, the output is generated through average pooling, realizing the learning of cyclical traffic flow characteristics. In the experiment, CNNformer+ and the state-of-the-art traffic flow prediction methods are compared using simulated data. The results show that the proposed model outperforms the existing models in prediction accuracy and efficiency.

Hybrid Acyclic and Spillback-Aware Scheduling Protocol for Intelligent Traffic Lights Control

Hybrid Acyclic and Spillback-Aware Scheduling Protocol for Intelligent Traffic Lights Control

Deep Reinforcement Q-Learning for Intelligent Traffic Signal Control with Partial Detection

Intelligent traffic signal controllers, applying DQN algorithms to traffic light policy optimization, efficiently reduce traffic congestion by adjusting traffic signals to real-time traffic. Most propositions in the literature however consider that all vehicles at the intersection are detected, an unrealistic scenario. Recently, new wireless communication technologies have enabled cost-efficient detection of connected vehicles by infrastructures. With only a small fraction of the total fleet currently equipped, methods able to perform under low detection rates are desirable. In this paper, we propose a deep reinforcement Q-learning model to optimize traffic signal control at an isolated intersection, in a partially observable environment with connected vehicles. First, we present the novel DQN model within the RL framework. We introduce a new state representation for partially observable environments and a new reward function for traffic signal control, and provide a network architecture and tuned hyper-parameters. Second, we evaluate the performances of the model in numerical simulations on multiple scenarios, in two steps. At first in full detection against existing actuated controllers, then in partial detection with loss estimates for proportions of connected vehicles. Finally, from the obtained results, we define thresholds for detection rates with acceptable and optimal performance levels. The source code implementation of the model is available at: https://github.com/romainducrocq/DQN-ITSCwPD

Multi-View Multi-Attention Graph Neural Network for Traffic Flow Forecasting

The key to intelligent traffic control and guidance lies in accurate prediction of traffic flow. Since traffic flow data is nonlinear, complex, and dynamic, in order to overcome these issues, graph neural network techniques are employed to address these challenges. For this reason, we propose a deep-learning architecture called AMGC-AT and apply it to a real passenger flow dataset of the Hangzhou metro for evaluation. Based on a priori knowledge, we set up multi-view graphs to express the static feature similarity of each station in the metro network, such as geographic location and zone function, which are then input to the multi-graph neural network with the goal of extracting and aggregating features in order to realize the complex spatial dependence of each station’s passenger flow. Furthermore, based on periodic features of historical traffic flows, we categorize the flow data into three time patterns. Specifically, we propose two different self-attention mechanisms to fuse high-order spatiotemporal features of traffic flow. The final step is to integrate the two modules and obtain the output results using a gated convolution and a fully connected neural network. The experimental results show that the proposed model has better performance than eight other baseline models at 10 min, 15 min and 30 min time intervals.

License Plate Recognition via Attention Mechanism

License plate recognition technology use widely in intelligent traffic management and control. Researchers have been committed to improving the speed and accuracy of license plate recognition for nearly 30 years. This paper is the first to propose combining the attention mechanism with YOLO-v5 and LPRnet to construct a new license plate recognition model (LPR-CBAM-Net). Through the attention mechanism CBAM (Convolutional Block Attention Module), the importance of different feature channels in license plate recognition can be re-calibrated to obtain proper attention to features. Force information to achieve the purpose of improving recognition speed and accuracy. Experimental results show that the model construction method is superior in speed and accuracy to traditional license plate recognition algorithms. The accuracy of the recognition model of the CBAM model is increased by two percentage points to 97.2%, and the size of the constructed model is only 1.8 M, which can meet the requirements of real-time execution of embedded low-power devices. The codes for training and evaluating LPR-CBAM-Net are available under the open-source MIT License at: .

Android-based System for Intelligent Traffic Signal Control and Emergency Call Functionality

The aim of the system was to utilize technology to save lives in India by addressing the challenge of transporting patients during emergencies on congested roads. To tackle this problem, we developed two mobile apps - one for users and one for ambulance drivers. The user app requires signup and retrieves their address and location. Similarly, the ambulance driver app also retrieves their location. When the user presses the emergency button, a notification is sent to the ambulance driver via the app. The app then displays the shortest path, and traffic signals along the route are adjusted to facilitate a faster route to the hospital. Overall, our apps were created to aid accident victims in reaching the hospital promptly

IMPROVED TRAFFIC CONTROL SYSTEM THROUGH DETECTION AND CLASSIFICATION OF VEHICLES USING CAMERA BASED CROWD SENSING WITH DEEP LEARNING APPROACH.

Abstract - Intelligent traffic light control system can be considered as one of the main aspects of a smart city. There is significant increase in the number of People that own vehicles and this leads to traffic congestion in urban cities of developing countries. Traffic congestion is one of the highly challenging problems people face in their daily lives which affect their working productivity, causes accident, unnecessary delays and possibly loss of lives. The control of traffics based on the densities and classes of the vehicles using deep learning approach proved to be a better approach in handling traffic jams according to the current state of the studies. However, the current state of the studies did not have special consideration for the class of special vehicles (VIPs) which need special consideration due to their importance and tight schedules. Also, it did not consider allocating time based on the classification. Thus, a model to improve the detection and classification of vehicles on side of intersection as well as special consideration for VIPs was proposed. The proposed model was built using Faster R-CNN based on Tensorflow machine learning framework on a Google Colab environment. The model was able to detect and classify vehicles as “special vehicles (i.e. VIP), Emergency (EV) and Others” classes of vehicles, a time allocation simulator was proposed based on the specified classes with special timing for VIPs. Results show that using the proposed method, 94.43% accuracy was achieved.

БАЗОВА СТРУКТУРА СИСТЕМИ НЕЙРОНЕЧІТКОГО УПРАВЛІННЯ ГРУПОЮ МОБІЛЬНИХ РОБОТОТЕХНІЧНИХ ПЛАТФОРМ

It is shown that the following approaches can be used for group management of mobile robotic platforms (MRP): centralized (concentrated), decentralized (distributed) and hybrid. It was determined that an urgent task is the development of a neurofuzzy management system for the MRP group, which must perform the distribution of tasks between the MRPs, the determination of MRP movement routes, joint planning of works and their synchronization. The requirements for the system of neurofuzzy management of the MRP group are formulated, the main of which are the provision of: effective management of the MRP group; minimization of time for tasks; flexibility and adaptability to changing working conditions; reliable and stable operation when implementing various scenarios; expansion of functions and scaling relative to the number of MRPs; accuracy and reliability of traffic management of each MRP; response to changes in working conditions; uninterrupted work of the MRP group; effective use of MRP resources; reduction of dimensions, weight and energy consumption; management in real time; collecting data on the environment and the state of the MRP; wireless communication between MRP; development of software tools taking into account the distributed architecture; implementation of a programming interface with the possibility of developing additional software and integration with other systems; saving data on the status of all MRPs for further analysis and improving the management of the MRP group. The following main stages of the development of the neurofuzzy control system by the MRP group were identified: problem formulation; analysis of system requirements; hardware design; development of a neurofuzzy control algorithm; software development; testing and tuning; implementation and operation. It is suggested that the development of the system of neurofuzzy control of the MRP group be carried out on the basis of an integrated approach, which includes: methods of neurofuzzy control of the MRP group, artificial neural networks and fuzzy logic; navigation methods, methods of pre-processing and image recognition; methods of intellectual processing and evaluation of data from sensors in conditions of interference and incomplete information; modern methods and algorithms of intelligent traffic control of MRP; modern element base (microcontrollers, systems-on-chip, FPGA, etc.); methods and means of automated design of hardware and software of MRP. It is proposed to implement the neurofuzzy control system by the MRP group on the basis of a problem-oriented approach, which involves a combination of universal software and specialized hardware, which ensures high efficiency of equipment use. The method of time allocation of resources of the storage medium of multiport memory has been improved, which, due to the consideration of the speed of the storage medium and external devices, ensures an increase in the number of devices with conflict-free access to the storage medium.

СТРАТЕГИЯ СНИЖЕНИЯ КОЛИЧЕСТВА ДОРОЖНО-ТРАНСПОРТНЫХ ПРОИСШЕСТВИЙ ПУТЕМ ВНЕДРЕНИЯ ИНТЕЛЛЕКТУАЛЬНЫХ ТРАНСПОРТНЫХ СИСТЕМ

This article discusses options for using subsystems of intelligent traffic control systems and reducing the level of accidents. It is necessary to create all possible conditions to ensure the structural and functional homogeneity of traffic flows within the framework of road safety. The purpose of this article is to review, describe and describe options for using ITS to control the level of collisions and reduce the number of fatal initial loads in road traffic accidents. In addition, these systems can also help improve traffic efficiency, which is the goal of traffic management.

Network-Scale Traffic Signal Control via Multiagent Reinforcement Learning With Deep Spatiotemporal Attentive Network.

The continuous development of intelligent traffic control systems has a profound influence on urban traffic planning and traffic management. Indeed, as big data and artificial intelligence continue to evolve, the traffic control strategy based on deep reinforcement learning (RL) has been proven to be a promising method to improve the efficiency of intersections and save people's travel time. However, the existing algorithms ignore the temporal and spatial characteristics of intersections. In this article, we propose a multiagent RL based on the deep spatiotemporal attentive neural network (MARL-DSTAN) to determine the traffic signal timing in a large-scale road network. In this model, the state information captures the spatial dependency of the entire road network by leveraging the graph convolutional network (GCN) and integrates the information based on the importance of intersections via the attention mechanism. Meanwhile, to accumulate more valuable samples and enhance the learning efficiency, the recurrent neural network (RNN) is introduced in the exploration stage to constrain the action search space instead of fully random exploration. MARL-DSTAN decomposes the large-scale area into multiple base environments, and the agents in each base environment use the idea of "centralized training and decentralized execution" to learn to accelerate the algorithm convergence. The simulation results show that our algorithm significantly outperforms the fixed timing scheme and several other state-of-the-art baseline RL algorithms.

Fuzzy logic and deep Q learning based control for traffic lights

Traffic congestion is a major concern for many metropolises. Although it is difficult to regulate traffic flow because of numerous complexities and uncertainties, the traffic congestion problem must be mitigated in order to reduce the environmental problems related to traffic and the time lost on the roads in big cities. Intelligent traffic control methods, the use of which is increasing with the development of new methods, as opposed to conventional methods, and provide more efficient solutions, especially in traffic intersections with high traffic density. In this paper, we propose a new agent-based Fuzzy Logic assisted traffic light signal timing for traffic intersections. Deep Q-Learning algorithms and Fuzzy Logic Control (FLC) are used together in the proposed method. In this study, the proposed method and many traffic light control methods in the literature were simulated. In order to demonstrate the effectiveness of the proposed method, some of the important metrics of evaluation such as traffic congestion, air pollution, and waiting time were used in the assessment of the simulation results. In addition, with the proposed method, it has been shown that the stability and robustness of the system are increased.

A Novel Hybrid Model for Short-Term Traffic Flow Prediction Based on Extreme Learning Machine and Improved Kernel Density Estimation

Short-term traffic flow prediction is the basis of and ensures intelligent traffic control. However, the conventional models cannot make accurate predictions due to the strong nonlinearity and randomness in short-term traffic flow data. To this end, the authors of this paper developed a novel hybrid model based on extreme learning machine (ELM), adaptive kernel density estimation (AKDE), and conditional kernel density estimation (CKDE). Specifically, the ELM model was employed for nonlinear prediction. Then, AKDE was established to estimate the bandwidth of CKDE (i.e., AKDE-CKDE), which predicted the training residuals obtained by ELM. Finally, the predicted results of the two models were superimposed to derive the final prediction of the hybrid model. Two case studies based on measured data were conducted to evaluate the performance of the proposed method. The experimental results indicate that the proposed method can realize a significant improvement in terms of forecasting accuracy in comparison with the other concerned models. For instance, it performed better than the single ELM model, with an improvement in the evaluation criterion of a mean relative percentage error of 7.46%.

Guest Editorial Introduction to the Special Issue on Intelligent Transportation Systems in Epidemic Areas

The COVID-19 pandemic has posed significant challenges to transportation systems in various aspects, such as transferring patients and medical resources, enforcing physical distancing in public transportation, and controlling virus transmission through transportation networks. To address these challenges, a variety of artificial intelligence technologies, such as autonomous driving, big data analytics, intelligent vehicle routing and scheduling, and intelligent traffic control, have been employed in the design of intelligent transportation systems. This Special Issue provides a forum for researchers and practitioners to present the most recent advances in presenting and applying intelligent technologies to promote transportation systems in large-scale epidemics.

Effects analysis of reward functions on reinforcement learning for traffic signal control.

The increasing traffic demand in urban areas frequently causes traffic congestion, which can be managed only through intelligent traffic signal controls. Although many recent studies have focused on reinforcement learning for traffic signal control (RL-TSC), most have focused on improving performance from an intersection perspective, targeting virtual simulation. The performance indexes from intersection perspectives are averaged by the weighted traffic flow; therefore, if the balance of each movement is not considered, the green time may be overly concentrated on the movements of heavy flow rates. Furthermore, as the ultimate purpose of traffic signal control research is to apply these controls to the real-world intersections, it is necessary to consider the real-world constraints. Hence, this study aims to design RL-TSC considering real-world applicability and confirm the appropriate design of the reward function. The limitations of the detector in the real world and the dual-ring traffic signal system are taken into account in the model design to facilitate real-world application. To design the reward for balancing traffic movements, we define the average delay weighted by traffic volume per lane and entropy of delay in the reward function. Model training is performed at the prototype intersection for ensuring scalability to multiple intersections. The model after prototype pre-training is evaluated by applying it to a network with two intersections without additional training. As a result, the reward function considering the equality of traffic movements shows the best performance. The proposed model reduces the average delay by more than 7.4% and 15.0% compared to the existing real-time adaptive signal control at two intersections, respectively.

Multi-agent broad reinforcement learning for intelligent traffic light control

Intelligent traffic light control (ITLC) aims to relieve traffic congestion. Some multi-agent deep reinforcement learning (MADRL) algorithms have been proposed for ITLC, and most of them use deep neural networks to make decisions. However, the abundant parameters of deep structure lead to the time-consuming training process of MADRL. Recently, a broad reinforcement learning (BRL) approach has been proposed to improve the efficiency of training for an agent. Unlike MADRL algorithms that use deep architecture, BRL utilizes a broad architecture. In this paper, we propose a multi-agent broad reinforcement learning (MABRL) algorithm for ITLC. The MABRL algorithm adopts the broad network to process the joint information and updates the parameters using ridge regression. To increase the effectiveness of interaction among agents, we design a dynamic interaction mechanism (DIM) based on the attention mechanism. The DIM enables agents to aggregate information on particular intersections at appropriate moments. We conduct experiments on three different datasets. The results demonstrate that the effectiveness of MABRL outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time.

An Efficient Real-Time Vehicle Monitoring Method

As the major transportation infrastructure, roads play an important role in intelligent transportation system. However, the intelligent level of roads is insufficient currently, which does not match the development needs of autonomous vehicles in the near future. In order to improve the intelligence level of road infrastructures, a distributed acceleration sensing node array was embedded in the pavement to collect pavement vibration signals under the action of vehicle moving load to sense the traffic information. A complete set of processing algorithms, including raw data preprocessing algorithm, same vehicle judgment algorithm and vehicle information analysis algorithm, is proposed to extract the traffic information from the monitored vibration data. The traffic information such as vehicle speed, axle numbers, wheelbases, load position, and traffic flows are obtained. The acquired traffic information can support intelligent traffic control as well as scientific road maintenance.

DeResolver: A Decentralized Conflict Resolution Framework with Autonomous Negotiation for Smart City Services

As various smart services are increasingly deployed in modern cities, many unexpected conflicts arise due to various physical world couplings. Existing solutions for conflict resolution often rely on centralized control to enforce predetermined and fixed priorities of different services, which is challenging due to the inconsistent and private objectives of the services. Also, the centralized solutions miss opportunities to more effectively resolve conflicts according to their spatiotemporal locality of the conflicts. To address this issue, we design a decentralized negotiation and conflict resolution framework named DeResolver, which allows services to resolve conflicts by communicating and negotiating with each other to reach a Pareto-optimal agreement autonomously and efficiently. Our design features a two-step self-supervised learning-based algorithm to predict acceptable proposals and their rankings of each opponent through the negotiation. Our design is evaluated with a smart city case study of three services: intelligent traffic light control, pedestrian service, and environmental control. In this case study, a data-driven evaluation is conducted using a large dataset consisting of the GPS locations of 246 surveillance cameras and an automatic traffic monitoring system with more than 3 million records per day to extract real-world vehicle routes. The evaluation results show that our solution achieves much more balanced results, i.e., only increasing the average waiting time of vehicles, the measurement metric of intelligent traffic light control service, by 6.8% while reducing the weighted sum of air pollutant emission, measured for environment control service, by 12.1%, and the pedestrian waiting time, the measurement metric of pedestrian service, by 33.1%, compared to priority-based solution.