Simulator SUMO Research Articles

Deep Sarsa Replay model for real Time Traffic Control

Traffic congestion is a major factor currently affecting the global economy thereby costing billions of dollars in terms of the time lost in traffic, productivity and fuel wastage. Although, various researchers have made concerted effort to proffer solution to the problems of traffic congestion, in addition, recent reinforcement learning research has also presented multiple possible solutions. However, based on the literature, most of the reinforcement learning traffic control agents do not possess the real-time traffic control capabilities to efficiently deal with the complex and ever-changing nature of traffic on an average urban city road. This paper presents a Real Time deep reinforcement learning model for Traffic Control for optimization of vehicle flow (minimizing waiting time and traffic congestion). The Deep SARSA (DSARSA) learning algorithm with experience replay applied in the training process. The DSARSA replay model is built to extract traffic information from all lanes by applying multilayer perceptron with two hidden layers. Then, at the output layer an approximated qvalue is produced and updated with SARSA algorithm. For training, a random batch of experiences is sampled from the replay buffer. This helps break the correlation between consecutive experiences, stabilizes training and enables the model to be to able deal appropriately with any traffic condition. Experiments on 1000 episode of low, medium and heavy traffic flow was conducted on SUMO traffic simulator. TraCL allows interface with the SUMO simulation using python showed that the proposed DSARSA replay model achieved a state-of-the-art performance compared to other baseline DRL models applied in traffic control in terms of learning stability and reward maximization.

Machine learning solutions for adaptive traffic signal control: A review of image-based approaches

This paper gives an overview and performance evaluation of various machine learning models implemented in management of urban traffic congestions, more specifically, adaptive traffic signal control systems. It considers a review of deep learning algorithms including R- CNN, Fast R-CNN, Faster R-CNN, SSD, YOLO v4, and YOLOv8, with regard to their efficiencies for vehicle detection and traffic prediction under varying scenarios. Certain traffic conditions, camera placements, and environmental factors—related performance for each of the models are discussed. The major performance in most of the scenarios was depicted by the YOLO v4. However, at the same time, YOLOv8 has shown potential to do much better than YOLO v4 on image processing and the resultant accuracy. It also proposes a new algorithm for traffic light timing, whose efficacy is tested using the SUMO simulation platform. While results have shown improvements in urban traffic management, a review underlines that such is in deep need of extensive real-world testing. Future directions should include views from varied angles and weather conditions, and the detection of emergency vehicles, probably with specialized datasets.

Detection of Sybil & DDoS attacks in VANET using intelligent technique

ABSTRACT This paper proposes a novel fuzzy logic controller (FLC) based model referred to as FBM to detect both the DDoS and the Sybil attacks in VANET using an intelligent fuzzy logic controller. A VANET environment is created with different numbers of attackers to check the efficacy of the proposed model using veins, which is used for simulation with an event-based network simulator OMNeT++ and a road traffic simulator SUMO. Furthermore, the performance of the proposed model is compared with a few other machine learning techniques, such as logistic regression (LR), the decision tree (DT), random forest classifier (RF), and the support vector machine (SVM). The proposed FBM model yields better performance than the existing machine-learning techniques. The proposed FBM performs better than RF in accuracy by 0.10492%, precision by 0.08065%, recall by 0.02505%, and F1 score by 0.088243% for the DDoS scenario. It is also observed that the FBM performs better than DT in accuracy by 3.91486%, precision by 14.39994%, and F1 score by 3.819618% for the Sybil scenario. The margin of error for the proposed FBM is also estimated for 95% of the confidence interval and is found to be 0.021691 for the DDoS scenario.

Assessing the impact of communication delays for Autonomous Intersection Management systems

Communication is essential for Cooperative Intelligent Transportation Systems (C-ITS) to achieve better road efficiency, especially for Autonomous Intersection Management (AIM) which coordinates vehicles to pass the intersection safely and efficiently. Communication delays cause severe safety crises (i.e., collisions) and vehicular-performance degradation regarding intersection capacities and vehicular delays. Targeting the delays, network researchers have been working on low-latency communication technologies, and C-ITS researchers have proposed delay-tolerant AIM systems to avoid collisions in intersections. The impacts of communication delays are observed and discussed in the literature; however, models and assessments of the delay requirements for AIM are needed to provide insights for future network and C-ITS research. Here, we model the impact of communication delays on vehicular performance at an autonomous intersection and validate the models with the simulation results from over two million experiments, two types of multi-lane intersections (a typical 4-legged intersection and a roundabout), and four AIM systems. The simulations are conducted with SUMO simulator and AIM systems, where communication delays are inserted into the message exchanges during the simulation. The models are represented in linear, quintic, and cubic polynomials, showing that communication delay between 0 to 100 milliseconds is linearly related to vehicular performance in terms of intersection capacity and vehicular delay. According to the models, we show that by reducing communication delay from 100 to 10 milliseconds, the capacity degradation can be reduced from 7-10% to 0.7-1.0%. Moreover, communication delays must be less than 247 milliseconds to allow AIM systems to outperform traditional traffic lights.

Perspectives on an ALKS Model in SUMO

The UNECE regulation R157 [1] describes the requirements for a successful implementation of an approvable ALKS (Automated Lane-Keeping System) in great detail. This paper reviews some of the content of this document and describes the first steps that would be needed on how to implement such an ALKS as another driver model into the open source microscopic traffic flow simulator SUMO.

Integration Traffic Signal Control From Synchro to SUMO

This study investigates the feasibility and challenges of transferring traffic signal control schemes from the macroscopic signal timing optimization tool Synchro to the microscopic traffic simulator SUMO, focusing on Downtown Seattle as a case study. The research assesses the process of sharing and importing traffic signal timing plans, a crucial aspect of transportation simulations, between these two platforms. We conduct a detailed analysis of the traffic signal characteristics and data formats unique to each simulator and identify elements suitable for conversion. Subsequently, a four-stage framework is developed for semi-automatic integration of traffic signal control between the two. Our results indicate a successful conversion rate of approximately 85% of signalized intersections from Synchro to SUMO. This research not only illustrates the challenges and solutions in converting signal control across different platforms but also paves the way for future studies aimed at improving the interoperability of various traffic simulation tools.

Automatic house location identification using location service based VANET

SummaryThe vehicular ad hoc network (VANET) provides a variety of applications and is gaining popularity due to the reuse of network resources. Exact location identification with optimum delay is the demand of all vehicle users. Currently, individuals are utilizing the Global Positioning System (GPS) to ascertain the precise geographical coordinates of a given location. The drawback of GPS technology is its inability to accurately determine location and use GPS in some remote areas. Searching for the location of a particular house randomly incurs a loss of fuel as well as increases delay. This motivates us to propose one automated method through VANET using location service‐based routing for the location identification of a house. The proposed work involves searching for the location of a house using the open‐source MongoDB database, and the operations on the database are performed using the tool Node‐Red. By simulation using SUMO and Network Simulator 2.35, the proposed work is evaluated and compared with existing location service‐based routing like geographic location service (GLS) and hierarchical location service (HLS). The proposed work performs better in terms of routing efficiency (end‐to‐end latency, packet delivery rate), location efficiency (request sends, query success rate, and request travel time), and routing and location overhead (MAC bandwidth consumption). Also, the performance of the proposed work is presented as stable by increasing the number of vehicles. The statistical analysis of the packet delivery ratio and CBR end‐to‐end latency is carried out using T score.

Innovative On-Demand Transit for First-Mile Trips: A Cutting-Edge Approach

As a result of the lack of access to efficient public transit in suburban areas, residents often have to use their own vehicles to commute either within the area, to neighboring regions, or to a public transit hub (PTH). Thanks to information and communication technologies, on-demand transit (ODT) is a potential solution being proposed and considered by transit agencies. Although ODT has shown the potential to enhance transit level of service, its efficiency depends on different parameters such as demand spatial and temporal distribution or the configuration of the service. In this study, we propose a novel configuration for an ODT service and apply it to the first part of a commuter’s trip, or the commuter’s “first mile.” The proposed configuration depends on the availability of smart devices installed at bus stops. Passengers request their rides via smart devices and receive real-time and personalized information about their ride requests to travel to a PTH. The proposed ODT service is modeled with the Simulation of Urban Mobility or SUMO simulation framework. To evaluate the performance of the ODT service, it is applied to the city of Terrebonne in Quebec, Canada. The proposed service is compared with existing bus transit operating in the area as well as a door-to-PTH service. The results of the comparison analysis reveal that the proposed ODT service may result in a significant 36% reduction in total travel time as well as a 41% reduction in detour time compared with the existing bus transit service. A detailed sensitivity analysis is also conducted to capture the impacts of different parameters, variables, and dispatching algorithms on the service performance.

Towards Safe Autonomy in Hybrid Traffic: Detecting Unpredictable Abnormal Behaviors of Human Drivers via Information Sharing

Hybrid traffic which involves both autonomous and human-driven vehicles would be the norm of the autonomous vehicles’ practice for a while. On the one hand, unlike autonomous vehicles, human-driven vehicles could exhibit sudden abnormal behaviors such as unpredictably switching to dangerous driving modes—putting its neighboring vehicles under risks; such undesired mode switching could arise from numbers of human driver factors, including fatigue, drunkenness, distraction, aggressiveness, and so on. On the other hand, modern vehicle-to-vehicle (V2V) communication technologies enable the autonomous vehicles to efficiently and reliably share the scarce run-time information with each other [ 1 ]. In this article, we propose, to the best of our knowledge, the first efficient algorithm that can (1) significantly improve trajectory prediction by effectively fusing the run-time information shared by surrounding autonomous vehicles, and can (2) accurately and quickly detect abnormal human driving mode switches or abnormal driving behavior with formal assurance without hurting human drivers’ privacy. To validate our proposed algorithm, we first evaluate our proposed trajectory predictor on NGSIM and Argoverse datasets and show that our proposed predictor outperforms the baseline methods. Then through extensive experiments on SUMO simulator, we show that our proposed algorithm has great detection performance in both highway and urban traffic. The best performance achieves detection rate of 97.3%, average detection delay of 1.2 s, and 0 false alarm.

Investigation Performance Analysis and Evaluation of VANET Routing Protocol on Urban Scenario Simulation: A Case Study of Melaka

Vehicles on the road create a VANET network using IEEE 802.11P for wireless data exchange. However, VANET is challenging since the characteristics of VANET such as high mobility and frequent topology making it harder to design an effective routing protocol. The needs of an efficient performance routing protocol are crucial since it is to ensure a better network Quality of Service (QoS). In this paper, the evaluation of the IEEE 802.11P performance is simulated in real-world scenario using the Melaka City roadmap. In an urban setting, the impact of vehicle density on the performance of VANET routing protocols including OLSR, AODV, and DSDV are examined. Reviewing the effectiveness of the current VANET routing protocols is the goal of this research since it is crucial to know which routing has high performance under specific circumstances. Quantitative measurements including Packet Delivery Ratio (PDR), Packet Loss Ratio (PLR), and end-to-end delay are evaluated using the Network Simulator NS-3 and SUMO. Findings from the investigation show that while proactive routing protocols like OLSR and DSDV perform better in terms of end-to-end delay, AODV performs exceptionally well in terms of PDR and PLR.

A Fuzzy Based Intelligent Traffic Light Control (ITLC) Method: An Implementation in Ankara City

The escalating global population and increased vehicle usage have worsened traffic congestion in metropolitan areas, a significant urban challenge. Addressing this, adaptive traffic light control methods, especially at intersections, are being developed to improve traffic flow and reduce waiting times. This study significantly contributes to this field by implementing Fuzzy Logic in intelligent traffic light systems, focusing on Ankara's Polatlı Refik Cesur intersection. Using the SUMO simulation platform and Python programming, it analyzed waiting times and queue lengths. The initial phase used queue length for each intersection arm as an input. Fuzzy logic rules then determined the output, prioritizing street or phase order for optimal flow. The study further proposed an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based control plan. ANFIS merges neural network capabilities with fuzzy logic, using waiting time and queue length as inputs to regulate the green light duration. Compared to existing traffic systems, this model showed a substantial improvement. It achieved a 36.5% reduction in waiting times, underlining the efficiency of the Fuzzy Logic-based method. This approach not only enhances traffic management but also contributes significantly to the literature on intelligent traffic light control systems. By addressing key urban traffic issues, the study paves the way for future advancements in traffic management technologies. The findings highlight the potential of combining advanced computational methods, like ANFIS, with traditional traffic control techniques to optimize urban traffic flow, offering a blueprint for similar challenges in other metropolitan areas.

From novice to expert: advancing step-by-step simulation guideline for urban logistics with an open-source simulation tool

PurposeThis research analyses challenges faced by users at various levels in planning and designing participatory simulation models of cities. It aims to identify issues that hinder experts from maximising the effectiveness of the SUMO tool. Additionally, evaluating current methods highlights their strengths and weaknesses, facilitating the use of participatory simulation advantages to address these issues. Finally, the presented case studies illustrate the diversity of user groups and emphasise the need for further development of blueprints.Design/methodology/approachIn this research, action research was used to assess and improve a step-by-step guideline. The guideline's conceptual design is based on stakeholder analysis results from those involved in developing urban logistics scenarios and feedback from potential users. A two-round process of application and refinement was conducted to evaluate and enhance the guideline's initial version.FindingsThe guidelines still demand an advanced skill level in simulation modelling, rendering them less effective for the intended audience. However, they have proven beneficial in a simulation course for students, emphasising the importance of developing accurate conceptual models and the need for careful implementation.Originality/valueThis paper introduces a step-by-step guideline designed to tackle challenges in modelling urban logistics scenarios using SUMO simulation software. The guideline's effectiveness was tested and enhanced through experiments involving diverse groups of students, varying in their experience with simulation modelling. This approach demonstrates the guideline's applicability and adaptability across different skill levels.

Performance Evaluation of Reinforcement Learning-Based Adaptive Signal Control Deployment in Urban Network

The adaptive traffic control system (ATCS) has shown great potential to address traffic congestion, fuel consumption, and air pollution issues because of its strong adaption to traffic fluctuation. With the popularity of artificial intelligence, Reinforcement Learning (RL) has been applied to ATCS and achieved excellent performance. In RL-based ATCS, the controller collects traffic state information and learns a better signal control policy by minimizing travel delay. For ATCS of an area-wide network, most existing studies assumed that all intersections are installed with ATCS. However, fully ATCS networks are difficult to achieve in the real world due to the high upgrade cost. Therefore, a practical ATCS deployment strategy in a network is needed for agencies with limited budgets. This study proposes a concept of penetration rate, or the percentage of intersections with ATCS in an area, for intelligent intersections. The weighted PageRank algorithm determines a reasonable deployment plan based on road connectivity and link volume. The relationship between penetration rate and traffic performance is investigated in the SUMO simulation. It reveals that the average stopped and control delays gradually decreased with the penetration rate increase. When the penetration rate reaches 75%, the ATSC performance is about 90% of the optimum. However, inequity and inefficiency exist in non-intelligent intersections regarding average queueing time and length at the penetration rate below 40%. Consequently, the suitable range of penetration rate should be between 40% and 75% to balance the costs and benefits of ATCS deployment with budget constraints.

Advantages of Synchronizing Vehicles Intersection Access

An intersection area is a common space that must be efficiently shared over time between vehicles with conflicting trajectories from several road lanes. Numerous traffic light control (TLC) strategies have been presented to address this. The main objective is periodically switching intersection access between road lanes by permitting vehicles sequentially, parallelly, or synchronously. This work addresses which intersection access type is more efficient for throughput, travel delays, fuel consumption, and associated tailpipe emissions. We compare the performance of five state-of-the-art TLC approaches in two types of road networks. Among the five TLC approaches, three are sequential, one is parallel, and the other is synchronous. In the first road network, all four intersections are homogeneous with four legs. The second network is heterogeneous, with two intersections with four legs and the other two with three legs, i.e., T-intersections. We also consider two maximum speeds (30 and 50km/h) representing low-speed urban settings. SUMO simulation results suggest all access types have similar throughput, with a minor advantage of synchronous access (up to 3%). However, compared to the other best approaches, synchronous intersection access significantly reduces travel time loss (up to 130.5%) and fuel consumption (up to 37.2%).

Energy-optimal Speed Regulation for CAVs in Urban Mixed Traffic with Induced Lane Changes

Existing urban energy-optimal vehicle speed regulation (eco-driving) studies were mostly carried out on single-lane roads or did not consider lane changes, delivering overidealized eco-driving results. In addition to lane changes that every vehicle may encounter on roads, the eco-driving connected automated vehicles (CAVs) are subject to induced types of lane changes of manually-driven vehicles (MVs), a cut-in of an MV to the front of a CAV from an adjacent lane, and an escape of an MV from behind a CAV to an adjacent lane. So far, very few studies have considered the impact of lane changes while designing the ecodriving strategies and evaluated the eco-driving performance with respect to lane-changing disturbances in credible simulation environments; and almost no existing work has addressed both lateral and longitudinal disturbances for eco-driving. This paper has developed a generic and deployable eco-driving strategy for CAVs under a unified rolling-horizon optimal control framework that can deal with both longitudinal and lateral disturbances of MVs without assuming communications between CAVs and MVs. The performance of this disturbance-rejection eco-driving strategy was thoroughly evaluated with regard to a multilane urban network, using the microscopic traffic simulator SUMO. The strategy was demonstrated very effective and robust, and similar results were little reported before.

Microscopic traffic models, accidents, and insurance losses

AbstractThe paper develops a methodology to enable microscopic models of transportation systems to be accessible for a statistical study of traffic accidents. Our approach is intended to permit an understanding not only of historical losses but also of incidents that may occur in altered, potential future systems. Through such a counterfactual analysis, it is possible, from an insurance, but also from an engineering perspective, to assess the impact of changes in the design of vehicles and transport systems in terms of their impact on road safety and functionality.Structurally, we characterize the total loss distribution approximatively as a mean-variance mixture. This also yields valuation procedures that can be used instead of Monte Carlo simulation. Specifically, we construct an implementation based on the open-source traffic simulator SUMO and illustrate the potential of the approach in counterfactual case studies.

Road network free flow speed estimation using microscopic simulation and point-to-point travel times

Roads in mesoscopic traffic simulation models are often parametrized by a free speed attribute, which describes the speed at which a vehicle can traverse a road in the absence of congestion. Unlike microscopic models, mesoscopic models do not typically simulate traffic lights, individual driver behavior or acceleration and deceleration of vehicles. In consequence, the free speed parameter of each road must account for all the aforementioned effects. Modeling free speed accurately is important, as it determines the travel time, which in turn affects the decision-making of agents in the simulation.This paper introduces an approach combining microscopic simulation with machine learning models to estimate road segment free speeds. Using the microscopic simulator SUMO, we generate training data for a model search employing Bayesian optimization. Subsequently, these models undergo fine-tuning via gradient-based optimization using real-world point-to-point travel times. A significant advantage is the adaptability of this approach to diverse road networks, including those from OpenStreetMap, and the ability to incorporate routing data from various online providers independently.Our evaluation illustrates a notable decrease in prediction error between 30% and 60% compared to baseline models that assume a uniform free speed reduction for all urban roads. The fine-tuned models are able to generalize well to unseen regions and are therefore applicable to case studies where data for new or altered roads is unavailable.

Developing a comprehensive large-scale co-simulation for replication of automated driving in urban traffic scenarios

Automated Vehicles (AVs) hold substantial potential to revolutionize urban transportation, but their safe and reliable operation in mixed-traffic conditions remains a challenge. While computer-based simulations can provide cost-effective, safe performance evaluations, they often fail to represent the complex realities of large-scale traffic systems. This paper presents a novel co-simulation approach that integrates high-fidelity AVs with adjustable penetration rates into a comprehensive traffic model. The co-simulation, developed by coupling the automated driving simulator CARLA with the microscopic traffic simulator SUMO, allows for the detailed evaluation of AV performance under diverse traffic conditions. It also aids in the estimation of AVs' impacts on traffic patterns. Despite the computational demands, the co-simulation scenario provides a scalable, dynamic, and robust platform for realistic AV performance assessment.

Enhancing traffic signal control with composite deep intelligence

Traffic signal control has always been a hot topic in the field of intelligent transportation. With the increasing complexity of urban traffic conditions due to urbanization, how to develop effective scheduling strategies to adapt to the changing traffic demands has become a key problem in current intelligent transportation. In light of this, this paper focuses on the traffic signal control problem at intersections and proposes a composite intelligent traffic signal control model based on heterogeneous graph neural networks with dual attention mechanisms and deep reinforcement learning. For the first time, the model incorporates the dual attention mechanism in graph neural networks into the traffic signal control, integrating graph neural networks with deep reinforcement learning techniques and traffic intersection scenarios. This allows for the construction of traffic condition models and the scheduling control of traffic resources, catering to the perception and decision-making needs in complex traffic environments. Firstly, the graph relationship representation of intersection resources is established, constructing the graph information structure for traffic flow and signal states. Then, a heterogeneous graph neural network is designed, incorporating both node-level and semantic-level dual attention mechanisms to characterize the traffic state and explore the relationships, enabling the extraction of explicit and implicit information in traffic intersections. Lastly, a deep reinforcement learning algorithm that combines Double Deep Q-Network (DDQN) and Dueling DQN is implemented to improve the algorithm's generalization and execution efficiency, enhancing the adaptability and stability of traffic signal scheduling in complex environments. Simulation tests are conducted on the SUMO simulation platform using real-world application datasets. Compared to four other similar traffic control model, the proposed model demonstrates performance advantages of more than 13% in terms of average reward, average delay, queue length, and waiting time. This validates the effectiveness of the proposed model.

Carbon Dioxide Emission Reduction-Oriented Optimal Control of Traffic Signals in Mixed Traffic Flow Based on Deep Reinforcement Learning

To alleviate intersection traffic congestion and reduce carbon emissions at intersections, research on exploiting reinforcement learning for intersection signal control has become a frontier topic in the field of intelligent transportation. This study utilizes a deep reinforcement learning algorithm based on the D3QN (dueling double deep Q network) to achieve adaptive control of signal timings. Under a mixed traffic environment with connected and automated vehicles (CAVs) and human-driven vehicles (HDVs), this study constructs a reward function (Reward—CO2 Reduction) to minimize vehicle waiting time and carbon dioxide emissions at the intersection. Additionally, to account for the spatiotemporal distribution characteristics of traffic flow, an adaptive-phase action space and a fixed-phase action space are designed to optimize action selections. The proposed algorithm is validated in a SUMO simulation with different traffic volumes and CAV penetration rates. The experimental results are compared with other control strategies like Webster’s method (fixed-time control). The analysis shows that the proposed model can effectively reduce carbon dioxide emissions when the traffic volume is low or medium. As the penetration rate of CAVs increases, the average carbon dioxide emissions and waiting time can be further reduced with the proposed model. The significance of this study lies in its dual achievement: by presenting a flexible strategy that not only reduces the environmental impact by lowering carbon dioxide emissions but also enhances traffic efficiency, it provides a tangible example of the advancement of green intelligent transportation systems.