Urban Traffic Scenarios Research Articles

Does Prosocial Automation Increase Driver’s Well-being?

As societies transition to hybrid mobility systems, interactions between automated vehicles (AVs) and human users in public spaces become more complex, highlighting the critical role of prosocial behaviors. These behaviors are essential for the seamless operation of interdependent transportation networks, helping to address integration challenges of AVs with human-operated vehicles and enhancing well-being by creating more efficient, less stressful, and inclusive environments. This study explores the impact of receiving prosocial behaviors on the cognition, riding performance, and well-being of micromobility users in simulated urban traffic scenarios. Using a mixed-method design, the research contrasts two types of social interactions—prosocial and asocial—across three temporal conditions: relaxed, neutral, and urgent. The Structural Equation Modeling underscored the intricate relationships between prosocial behaviors, satisfaction, cognition, riding performance, and well-being. Incorporating social factors into driving systems could enhance safety and improve urban mobility solutions.

Probabilistic model for high-level intention estimation and trajectory prediction in urban environments

To enable successful automated driving, precise behavior prediction of surrounding vehicles is indispensable in urban traffic scenarios. Furthermore, given that a vehicle’s behavior is influenced by the movements of other road users, it becomes crucial to estimate their intentions to anticipate precise future motion. However, the elevated complexity resulting from interdependencies among traffic participants and the uncertainty arising from the object recognition errors present additional challenges. Despite extensive research on inferring intentions, many studies have concentrated on estimating intentions from interactions, resulting in a lack of practicality in urban traffic environments due to low computational efficiency and low robustness against recognition failure of strongly interacting road users. In this paper, we introduce a practical stochastic model for intention estimation and trajectory prediction of surrounding vehicles in automated driving under urban traffic environments. The trajectory is forecasted based on hierarchically computed and probabilistically estimated intentions, which represent an interpretation of vehicle behavior, utilizing only the kinematic state of the focal vehicle and HD maps to ensure real-time performance and enhance robustness. The evaluated results demonstrate that the proposed model surpasses straightforward methods in terms of accuracy while maintaining computational efficiency and exhibits robustness against the recognition failure of traffic participants which strongly influence the focal vehicle.

Research on the strategy of cruise control system for urban traffic jam assistant

This paper proposes a hierarchical cruise control strategy that can adapt to urban traffic scenarios. Firstly, the perception layer defines a target selection strategy by using a novel trapezoidal dangerous area. Then, the upper controller contains speed follow mode and distance follow mode. An improved PI mode with integral separation and saturation terms is developed to achieve the desired speed following control, a safe distance mode via variable time headway is developed to facilitate the safe and smooth distance following control. The lower controller is designed based on feedforward and PI feedback. Finally, the experimental results demonstrate that the strategy can effectively select suitable target vehicles in complex urban scenarios. With the improved safe distance model and the third-order Bessel actuator response delay model, the strategy exhibits adaptability and stability. This study offers valuable suggestions and guidance for designing and applying the cruise control strategy for urban traffic scenarios.

Cellular automaton model for the analysis of design and plan of bus station in the mixed traffic environment

With the quick development of Connected Autonomous Vehicles (CAVs), CAVs would gradually become an important part of urban traffic. Hence, the impacts of CAVs on urban traffic should be further explored. This study aims to analyze the mixed traffic comprising CAVs and human-driven vehicles (HDVs) in different urban scenarios in which different bus station types (i.e., roadside and bay bus stations) and capacities are considered. To do this analysis, this study proposes a cellular automaton model which simulates car following behaviours of vehicles using a two-state safe speed model, and designs specific modeling rules for lane-changing behaviours and vehicle behaviours near bus stations with consideration of the differences between CAVs and HDVs. The analysis results indicate that the impacts of various bus station types and capacities on the mixed traffic flow vary with traffic volumes, while increasing the CAV penetration rate can reduce the traffic congestion caused by bus stop-and-go. Furthermore, the study explores the optimal number of bus routes for different types of bus stations in different urban traffic scenarios, and several possible policy implications have been given according to the analysis results.

Game-Based Flexible Merging Decision Method for Mixed Traffic of Connected Autonomous Vehicles and Manual Driving Vehicles on Urban Freeways

Connected Autonomous Vehicles (CAVs) have the potential to revolutionize traffic systems by autonomously handling complex maneuvers such as freeway ramp merging. However, the unpredictability of manual-driven vehicles (MDVs) poses a significant challenge. This study introduces a novel decision-making approach that incorporates the uncertainty of MDVs’ driving styles, aiming to enhance merging efficiency and safety. By framing the CAV-MDV interaction as an incomplete information static game, we categorize MDVs’ behaviors using a Gaussian Mixture Model–Support Vector Machine (GMM-SVM) method. The identified driving styles are then integrated into the flexible merging decision process, leveraging the concept of pure-strategy Nash equilibrium to determine optimal merging points and timing. A deep reinforcement learning algorithm is employed to refine CAVs’ control decisions, ensuring efficient right-of-way acquisition. Simulations at both micro and macro levels validate the method’s effectiveness, demonstrating improved merging success rates and overall traffic efficiency without compromising safety. The research contributes to the field by offering a sophisticated merging strategy that respects real-world driving behavior complexity, with potential for practical applications in urban traffic scenarios.

Improving real-time object detection in Internet-of-Things smart city traffic with YOLOv8-DSAF method

With the rise of global smart city construction, target detection technology plays a crucial role in optimizing urban functions and improving the quality of life. However, existing target detection technologies still have shortcomings in terms of accuracy, real-time performance, and adaptability. To address this challenge, this study proposes an innovative target detection model. Our model adopts the structure of YOLOv8-DSAF, comprising three key modules: depthwise separable convolution (DSConv), dual-path attention gate module (DPAG), and feature enhancement module (FEM). Firstly, DSConv technology optimizes computational complexity, enabling real-time target detection within limited hardware resources. Secondly, the DPAG module introduces a dual-channel attention mechanism, allowing the model to selectively focus on crucial areas, thereby improving detection accuracy in high-dynamic traffic scenarios. Finally, the FEM module highlights crucial features to prevent their loss, further enhancing detection accuracy. Additionally, we propose an Internet of Things smart city framework consisting of four main layers: the application domain, the Internet of Things infrastructure layer, the edge layer, and the cloud layer. The proposed algorithm utilizes the Internet of Things infrastructure layer, edge layer, and cloud layer to collect and process data in real-time, achieving faster response times. Experimental results on the KITTI V and Cityscapes datasets indicate that our model outperforms the YOLOv8 model. This suggests that in complex urban traffic scenarios, our model exhibits superior performance with higher detection accuracy and adaptability. We believe that this innovative model will significantly propel the development of smart cities and advance target detection technology.

Achieving accurate trajectory predicting and tracking for autonomous vehicles via reinforcement learning-assisted control approaches

In complex urban traffic scenarios, autonomous vehicles face significant challenges in adapting to diverse and dynamic traffic conditions. Reward-based reinforcement learning has emerged as an effective approach to tackle these challenges. This paper presents a novel method that combines deep reinforcement learning with automotive dynamics systems. Building upon the Double Deep Q-learning algorithm, our approach integrates a Recurrent Neural Network with Gated Recurrent Units to enhance the environmental exploration capabilities of autonomous vehicles. To obtain more precise reward values, we introduce a trajectory tracking algorithm based on a combination of proportional-integral-derivative control and feedforward control within the automotive dynamics system. The proportional-integral-derivative controller is utilized for longitudinal control, while the Error-Optimized feedforward controller enhances lateral control, thereby improving trajectory tracking accuracy. Finally, extensive simulation experiments are conducted to evaluate the proposed method, comparing it against other baseline methods in terms of vehicle following and lane-changing scenarios. The results demonstrate that our approach significantly improves both the reward values and control performance of the algorithm.

Efficient Eco-Driving Control for EV Platoons in Mixed Urban Traffic Scenarios Considering Regenerative Braking

Efficient Eco-Driving Control for EV Platoons in Mixed Urban Traffic Scenarios Considering Regenerative Braking

Autonomous Driving Control for Passing Unsignalized Intersections Using the Semantic Segmentation Technique

Autonomous driving in urban areas is challenging because it requires understanding vehicle movements, traffic rules, map topologies and unknown environments in the highly complex driving environment, and thus typical urban traffic scenarios include various potentially hazardous situations. Therefore, training self-driving cars by using traditional deep learning models not only requires the labelling of numerous datasets but also takes a large amount of time. Because of this, it is important to find better alternatives for effectively training self-driving cars to handle vehicle behavior and complex road shapes in dynamic environments and to follow line guidance information. In this paper, we propose a method for training a self-driving car in simulated urban traffic scenarios to be able to judge the road conditions on its own for crossing an unsignalized intersection. In order to identify the behavior of traffic flow at the intersection, we use the CARLA (CAR Learning to Act) self-driving car simulator to build the intersection environment and simulate the process of traffic operation. Moreover, we attempt to use the DDPG (Deep Deterministic Policy Gradient) and RDPG (Recurrent Deterministic Policy Gradient) learning algorithms of the DRL (Deep Reinforcement Learning) technology to train models based on the CNN (Convolutional Neural Network) architecture. Specifically, the observation image of the semantic segmentation camera installed on the self-driving car and the vehicle speed are used as the model input. Moreover, we design an appropriate reward mechanism for performing training according to the current situation of the self-driving car judged from sensing data of the obstacle sensor, collision sensor and lane invasion detector. Doing so can improve the convergence speed of the model to achieve the purpose of the self-driving car autonomously judging the driving paths so as to accomplish accurate and stable autonomous driving control.

Optimization Control of Adaptive Traffic Signal with Deep Reinforcement Learning

The optimization and control of traffic signals is very important for logistics transportation. It not only improves the operational efficiency and safety of road traffic, but also conforms to the direction of the intelligent, green, and sustainable development of modern cities. In order to improve the optimization effect of traffic signal control, this paper proposes a traffic signal optimization method based on deep reinforcement learning and Simulation of Urban Mobility (SUMO) software for urban traffic scenarios. The intersection training scenario was established using SUMO micro traffic simulation software, and the maximum vehicle queue length and vehicle queue time were selected as performance evaluation indicators. In order to be more relevant to the real environment, the experiment uses Weibull distribution to simulate vehicle generation. Since deep reinforcement learning takes into account both perceptual and decision-making capabilities, this study proposes a traffic signal optimization control model based on the deep reinforcement learning Deep Q Network (DQN) algorithm by considering the realism and complexity of traffic intersections, and first uses the DQN algorithm to train the model in a training scenario. After that, the G-DQN (Grouping-DQN) algorithm is proposed to address the problems that the definition of states in existing studies cannot accurately represent the traffic states and the slow convergence of neural networks. Finally, the performance of the G-DQN algorithm model was compared with the original DQN algorithm model and Advantage Actor-Critic (A2C) algorithm model. The experimental results show that the improved algorithm increased the main indicators in all aspects.

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.

Numerical model for vibro-acoustics analysis of tyre-road noise generation caused by speed bumps

Electric vehicles, particularly when driving at low speeds, present a solution to mitigate the impact of road traffic on noise pollution. However, specific urban traffic scenarios still give rise to increased noise levels due to road irregularities such as speed bumps. To address this issue, a model that combines a dynamic analysis using FEM with an acoustic analysis using BEM is developed. The dynamic analysis simulates a quarter vehicle, employing a 3D tyre model equipped with a suspension system, to replicate impacts against obstacles. The resulting tyre vibration serves as a sound source for the study of acoustic propagation. To validate this model, low-speed track tests were conducted using an electric vehicle driving over a speed bump. The instrumentation used was an acoustic camera, which allowed the evaluation of the sound pressure level reached during the tests.

A Comprehensive Review on Object Detectors for Urban Mobility on Smart Traffic Management

This comprehensive review explores the landscape of object detectors in the context of urban mobility for smart traffic management. With the increasing complexity of urban environments and the integration of intelligent transportation systems, the demand for accurate and efficient object detection algorithms has surged. This paper provides a thorough examination of state-of-the-art object detectors, evaluating their performance, strengths, and limitations in the specific context of urban mobility. The review encompasses a wide range of detectors, including traditional computer vision methods and modern deep learning approaches, discussing their applicability to real-world urban traffic scenarios. By synthesizing insights from diverse methodologies, this review aims to guide researchers, practitioners, and policymakers in selecting suitable object detectors for enhancing smart traffic management systems in urban settings.

Driver mental load identification model Adapting to Urban Road Traffic Scenarios

Abstract Objective At present, most research on driver mental load identification is based on a single driving scene. However, the driver mental load model established in a road traffic scene is difficult to adapt to the changes of the surrounding road environment during the actual driving process. We proposed a driver mental load identification model which adapts to urban road traffic scenarios. Methods The model includes a driving scene discrimination sub-model and driver load identification sub-model, in which the driving scene discrimination sub-model can quickly and accurately determine the road traffic scene. The driver load identification sub-model selects the best feature subset and the best model algorithm in the scene based on the judgement of the driving scene classification sub-model. Results The results show that the driving scene discrimination sub-model using five vehicle features as feature subsets has the best performance. The driver load identification sub-model based on the best feature subset reduces the feature noise, and the recognition effect is better than the feature set using a single source signal and all data. The best recognition algorithm in different scenarios tends to be consistent, and the support vector machine (SVM) algorithm is better than the K-nearest neighbors (KNN) algorithm. Conclusion The proposed driver mental load identification model can discriminate the driving scene quickly and accurately, and then identify the driver mental load. In this way, our model can be more suitable for actual driving and improve the effect of driver mental load identification.

Cloud-Based Reinforcement Learning in Automotive Control Function Development

Automotive control functions are becoming increasingly complex and their development is becoming more and more elaborate, leading to a strong need for automated solutions within the development process. Here, reinforcement learning offers a significant potential for function development to generate optimized control functions in an automated manner. Despite its successful deployment in a variety of control tasks, there is still a lack of standard tooling solutions for function development based on reinforcement learning in the automotive industry. To address this gap, we present a flexible framework that couples the conventional development process with an open-source reinforcement learning library. It features modular, physical models for relevant vehicle components, a co-simulation with a microscopic traffic simulation to generate realistic scenarios, and enables distributed and parallelized training. We demonstrate the effectiveness of our proposed method in a feasibility study to learn a control function for automated longitudinal control of an electric vehicle in an urban traffic scenario. The evolved control strategy produces a smooth trajectory with energy savings of up to 14%. The results highlight the great potential of reinforcement learning for automated control function development and prove the effectiveness of the proposed framework.

Overcoming driving challenges in complex urban traffic: A multi-objective eco-driving strategy via safety model based reinforcement learning

This study proposes a novel eco-driving control strategy for connected and automated hybrid electric vehicles, which utilizes deep reinforcement learning (DRL) to optimize various aspects of driving performance, including fuel economy, ride comfort, and travel efficiency, in complex urban traffic scenarios. The proposed strategy incorporates a driving safety model that predicts potential risk associated with the DRL agent's planned speed, thus ensuring the safety of the DRL based eco-driving strategy. Additionally, we propose a multi-objective composite reward function design scheme that considers various constraints caused by traffic elements, such as traffic lights, preceding vehicles, road curvature, and speed limit. This design scheme enables the proposed strategy to effectively adapt to diverse driving challenges in complex urban traffic scenarios. To evaluate the proposed strategy, we develop an urban traffic simulation model based on real-world road and traffic data from Shanghai, China. This model is used as the test scenario and can reflect real urban traffic conditions. The simulation results demonstrate the capability of the proposed strategy to safely and efficiently control vehicles to complete driving tasks in complex urban scenarios. Moreover, the proposed strategy excels in simultaneously optimizing the driving comfort and fuel consumption of the controlled vehicle.

Toward urban traffic scenarios and more: a spatio-temporal analysis empowered low-rank tensor completion method for data imputation

Existing traffic monitoring approaches cannot completely cover all road segments in real-time, leading to massive amounts of missing traffic data, which limits the implementation of intelligent transportation systems. Most existing methods lack deep mining of the unique spatiotemporal characteristics of traffic flows, resulting in difficulty in application to urban traffic with complex topologies and variable states. In this paper, we propose a novel Spatio-Temporal constrained Low-Rank Tensor Completion (ST-LRTC) method, which adopts a manifold embedding approach to depict the local geometric structure of spatiotemporal domains. Specifically, under the low-rank assumption, the method introduces temporal constraints based on the continuity and periodicity of traffic flow and a spatial constraint matrix reflecting the traffic flow transmission mechanism. We embed low-dimensional spatiotemporal constraint matrices into the low-rank tensor completion solving process to fully utilize the global features and local spatiotemporal characteristics of the traffic tensor. Experiments were performed using traffic data from Xi’an, China, and the results indicated that ST-LRTC outperformed state-of-the-art methods under various missing rates and patterns. Thorough experiments have demonstrated that the incorporation of spatiotemporal analysis can enhance the adaptability of the tensor completion model to complex urban scenarios, which guarantees better monitoring, diagnosis, and optimization of urban traffic states.

A Novel UAV-Assisted Multi-Mobility Channel Model for Urban Transportation Emergency Communications

With the increasing requirements for unmanned aerial vehicle (UAV) communication in various application scenarios, the UAV-assisted emergency communication in urban transportation scenario has received great attention. In this paper, a novel UAV-assisted UAV-to-vehicle (U2V) geometry-based stochastic model (GBSM) for the urban traffic communication scenario is proposed. The three-dimensional (3D) multi-mobilities of the transmitter (Tx), receiver (Rx), and clusters are considered by introducing the time-variant acceleration and velocity correspondingly. The velocity variation of the clusters is used to simulate the motion of vehicles around the Rx. Moreover, to describe the vehicles’ moving states, Markov chain is adopted to analyze the changes in cluster motion states, including survival, death, dynamic, and static states. By adjusting the scenario-specific parameters, such as the vehicle density (ρ) and dynamic–static ratio (Ω), the model can support various urban traffic scenarios. Based on the proposed model, several key statistical properties, namely the root mean square (RMS) delay spread, temporal autocorrelation function (ACF), level-crossing rate (LCR), power delay profile (PDP), and stationary interval, under different clusters and antenna accelerations are obtained and analyzed. The accuracy of the proposed model is verified by the measured data. The results demonstrate the usability of our model, which can be provided as a reference for the design, evaluation, and optimization of future communication networks between UAV and vehicles in urban transportation emergency communications.

Dynamic Selfish Node Detection With Link Quality Consideration in Vehicular Networks

With the emergence of various applications in intelligent transportation systems (ITS), the cooperative communication among the nodes on roads is becoming more and more important in vehicular networks. However, selfish nodes, which are not willing to relay data packets for others, drastically decrease the communication performance of the network in various aspects including packet delivery ratio, end-to-end delay, communication bandwidth, etc. It is critical to detect the selfish nodes in the network for avoiding the decrement of network performance. Nevertheless, it is extremely challenging to correctly and fairly detect selfish nodes in vehicular networks where the network topology is highly dynamic and link quality between nodes is lossy. In order to address this issue, a novel detection scheme is proposed in this paper. The proposed scheme jointly considers the link quality, mobility, and vehicle behaviors at the network layer and MAC layer with fuzzy logic in a fully decentralized manner. Furthermore, an innovative perception module is deployed based on probabilistic calculations to refine the detection decisions of the scheme. The scheme is validated by simulation platforms which integrate Veins, SUMO, and INET Framework under IEEE 802.11p and AODV protocols. The computer simulations are conducted with both highway and urban traffic scenarios of Xi'an city in China. As the results shown, the proposed scheme demonstrates better detection capabilities than the conventional schemes in terms of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Precision</i> , <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Recall</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F1-score</i> with an acceptable communication overhead.

Tri-HGNN: Learning triple policies fused hierarchical graph neural networks for pedestrian trajectory prediction

In complex and dynamic urban traffic scenarios, the accurate trajectory prediction of surrounding pedestrians with interactive behaviors plays a vital role in the self-driving system. Intrinsic factors and extrinsic factors will inevitably influence the pedestrians trajectory. Intrinsic factors such as pedestrians diversified intentions bring rich and diverse multi-modal future possibilities. Besides, extrinsic factors affecting the future trajectory are accompanied by context semantics such as interactions among pedestrians. However, most of the existing methods discuss two problems (interaction and intention) separately. Considering both two factors impact the trajectory of pedestrians, a Triple Policies Fused Hierarchical Graph Neural Networks (Tri-HGNN) is proposed to model spatial and temporal interactions and intentions among the whole scene of pedestrians at each time step and predict the multiple future trajectories. Tri-HGNN contains three different policies: (i) Extrinsic-level policy is used to extract spatial nodes embedding from the interaction graph of pedestrian trajectories by using the Graph Attention Network. (ii) Intrinsic-level policy adopts the Graph Convolutional Network to infer the human intention for more accurate prediction. Moreover, human intention is influenced by the intrinsic interaction generated among pedestrians, so we fuse the interaction features to grasp the influence of the extrinsic interaction. (iii) Basic-level policy then integrates the heuristic information obtained from other two policies and concatenates it with historical trajectories to make multiple predictions through Temporal Convolution Network. Experimental results show that our model improves performance compared with state-of-the-art methods on the ETH/UCY and SDD benchmarks.