Vehicle Behavior Research Articles

Vehicle Activity Dataset: A Multimodal Dataset to Understand Vehicle Emissions with Road Scenes for Eco-Routing

In the field of smart mobility, Artificial Intelligence (AI) approaches are influential and can make a highly beneficial contribution. Our project aims to develop a real-time ecological map of road traffic. This map will allow electric vehicles (EVs) and thermal vehicles (TVs) to display the cost of energy consumption and CO2 emissions on different road sections. In urban environments, road traffic emissions are a significant contributor to environmental pollution, with vehicle emissions being a major component. Addressing these impacts requires a thorough understanding of the operational behavior of vehicles on different road infrastructures within the region. This paper presents a novel, comprehensive dataset, the Vehicle Activity Dataset (VAD), designed to assess the emissions and fuel consumption characteristics of vehicles about their actual operating environment. Constructed from a large number of real-world driving scenarios, VAD incorporates emission data collected by an industrial Portable Emission Measurement System (PEMS), road scenes captured by an RGB camera, and the detection of different object classes within these images. The primary objective of VAD is to provide a comprehensive understanding of the relationship between vehicle emissions and the diverse range of objects present on the road. Experimental results in real road traffic environments through different studies demonstrate the robustness of the developed dataset.

Vehicle Simulation Algorithm for Observations with Variable Dimensions Based on Deep Reinforcement Learning

Vehicle simulation algorithms play a crucial role in enhancing traffic efficiency and safety by predicting and evaluating vehicle behavior in various traffic scenarios. Recently, vehicle simulation algorithms based on reinforcement learning have demonstrated excellent performance in practical tasks due to their ability to exhibit superior performance with zero-shot learning. However, these algorithms face challenges in field adaptation problems when deployed in task sets with variable-dimensional observations, primarily due to the inherent limitations of neural network models. In this paper, we propose a neural network structure accommodating variations in specific dimensions to enhance existing reinforcement learning methods. Building upon this, a scene-compatible vehicle simulation algorithm is designed. We conducted experiments on multiple tasks and scenarios using the Highway-Env traffic environment simulator. The results of our experiments demonstrate that the algorithm can successfully operate on all tasks using a neural network model with fixed shape, even with variable-dimensional observations. Our model exhibits no degradation in simulation performance when compared to the baseline algorithm.

Autonomous overtaking decision and motion planning of intelligent vehicles based on graph convolutional network and conditional imitation learning

To ensure safe overtaking of intelligent vehicles in dynamic interactive environments, this paper proposes an end-to-end learning method for autonomous overtaking based on Graph Convolutional Network (GCN) and Conditional Imitation Learning (CIL). This method completes the autonomous overtaking behavior by directly mapping the environmental perception data to the underlying vehicle control actions (e.g. throttle and steer angle). This method fully considers the influence of other vehicles’ driving behavior on the overtaking behavior of the ego vehicle. Firstly, the dynamic interactive environments information around the ego vehicle is aggregated in the form of graph-structured data, and the aggregated global features are used as the input of the GCN to output the optimal action instructions that the ego vehicle should take. Secondly, combined with CIL, the action instructions output by the GCN are used as high-level commands to guide CIL. Finally, combined with other perception data, the underlying control actions of the vehicle will be output by CIL to complete safe overtaking in dynamic interactive environments. The method proposed in this paper can effectively extract the global information of the driving scene and complete the collision-free autonomous overtaking behavior, which greatly improves the intelligence of the driving system. The feasibility of the method has been verified by experiments on the CARLA simulation platform. The experimental results prove that the performance of this method is better than that of the conventional end-to-end learning framework, and it has better success rate and generalization performance.

Integrating Surrounding Vehicle Information for Vehicle Trajectory Representation and Abnormal Lane-Change Behavior Detection.

The detection of abnormal lane-changing behavior in road vehicles has applications in traffic management and law enforcement. The primary approach to achieving this detection involves utilizing sensor data to characterize vehicle trajectories, extract distinctive parameters, and establish a detection model. Abnormal lane-changing behaviors can lead to unsafe interactions with surrounding vehicles, thereby increasing traffic risks. Therefore, solely focusing on individual vehicle perspectives and neglecting the influence of surrounding vehicles in abnormal lane-changing behavior detection has limitations. To address this, this study proposes a framework for abnormal lane-changing behavior detection. Initially, the study introduces a novel approach for representing vehicle trajectories that integrates information from surrounding vehicles. This facilitates the extraction of feature parameters considering the interactions between vehicles and distinguishing between different phases of lane-changing. The Light Gradient Boosting Machine (LGBM) algorithm is then employed to construct an abnormal lane-changing behavior detection model. The results indicate that this framework exhibits high detection accuracy, with the integration of surrounding vehicle information making a significant contribution to the detection outcomes.

Infrastructure-Assisted cooperative driving and intersection management in mixed traffic conditions

Infrastructure-assisted cooperative driving, which consists of connected and automated vehicle (CAV) trajectory planning and traffic signal control, can greatly improve the efficiency of signalized intersection operations. In existing studies, the CAV trajectory planning problem is simplified to only modeling longitudinal vehicle behaviors or assuming the lane changing can be executed instantaneously. The generated CAV trajectories are not realistic and can’t be implemented at the vehicle level. Instantaneous lane changing process may also lead to safety issues or uncomfortable driving behavior of following vehicles in a mixed traffic environment. To fill this research gap, we propose an optimization framework that integrates a full CAV trajectory planning model with traffic signal control in a cooperative driving environment with both CAVs and human-driven vehicles (HDVs). A two-level optimization model is formulated based on discrete time. The high-level model optimizes traffic signal parameters, CAV arrival time, and lane assignment at the stop bar, to minimize total vehicle delay. Given arrival time and lane assignment, the low-level model generates trajectories with integrated car-following and lane-changing maneuvers to mimic a human driving policy based on imitation learning. Numerical experiments from a real-world intersection show that the proposed model outperforms adaptive and fixed time signal control by as much as 63.06% in terms of reduction of average vehicle delay, due to better utilization of lane capacity and reduced lost time. In addition to mobility benefits, fuel consumption is also significantly reduced under the proposed infrastructure-assisted cooperative driving framework.

Output-only estimation of lateral wheel-rail contact forces and track irregularities

The contact between the wheel and the rail heavily affects the dynamic behaviour of railway vehicles and their running safety. The real-time knowledge of wheel-rail contact forces is tricky due to the several running conditions of the train and the combined tribological and wear characteristics of wheels and rails. Furthermore, their measurement and that of track irregularities, sensitive to the harshness of the wheel-rail contact, require dedicated sensors. Therefore, the development of strategies for estimating wheel-rail contact features is essential to perform the condition monitoring of rails to improve the safety related to the entire railway system. A nonlinear model-based estimation procedure, based on a Central Difference Kalman Filter, is proposed in this work to estimate the lateral wheel-rail contact forces and moments, including the identification of lateral track irregularities in the estimation process related to rails. Furthermore, the developed estimation technique can be used as a tool to monitor continuously the track conditions through in-service railway vehicles, coupled with the possibility to improve the effectiveness of control systems onboard them by estimating wheel-rail contact interactions through a model-based estimator, which is fed by measurements obtained by the typical set of sensors adopted for condition monitoring purposes on railway vehicles.

Vehicle Speed and Position Estimation considering Microscopic Heterogeneous Car-Following Characteristics in Connected Vehicle Environments

This paper proposes a method for estimating the speed and position of unsampled vehicles using sampled data from connected automated vehicles (CAVs). The determination of vehicle speed and position on the road is a challenging and crucial task, as they can effectively reflect traffic flow characteristics and contribute to traffic state estimation and intersection signal timing optimization. Connected automated vehicles have the capability to upload their own trajectory data while also capturing trajectory data of surrounding vehicles through onboard sensors. Therefore, this paper proposes a novel approach to estimate the speed and position of unsampled vehicles. Firstly, using real vehicle trajectory data, the correlation between the velocity of following vehicles and the velocity of leading vehicles under different densities is analyzed, leading to the development of a velocity estimation model incorporating a speed correction factor. Secondly, the correlation between time headway, the rate of change of following vehicle acceleration, and traffic density is examined. To address the issue of heterogeneous behavior in vehicle following described by the Intelligent Driver Model (IDM), a real-time optimization model for estimating vehicle position by optimizing IDM parameters is proposed. The velocity estimation model and the position estimation model are summarized as two nonlinear optimization problems. Finally, the proposed method is validated using actual vehicle trajectory data. Experimental results demonstrate that when the number of connected automated vehicles (CAVs) is 2, the proposed method reduces the average absolute error by 30.73% and the standard deviation of the average absolute error by 42.8% compared to a linear model-based speed estimation method under different density conditions. Compared to a method that estimates vehicle position by calibrating desired gaps, the proposed method reduces the average absolute error by 38.2% and the standard deviation of the average absolute error by 41.7% under different density conditions. Furthermore, the proposed method exhibits good practicality under different CAV penetration rates.

A market-based real-time algorithm for congestion alleviation incorporating EV demand response in active distribution networks

The dynamic charging behavior of electric vehicles (EVs) is causing frequent line-overloading problems and serious power security issues. Controlled and smart charging mechanisms for EVs incorporating demand response (DR) may provide significant operational flexibility to the grid operators and reduce charging costs for EV users. However, controlling EV charging may cause inconvenience to individual EV users. A market-based mechanism is proposed in this research work that allows EV users and households to participate in the network congestion alleviation DR program online while maintaining the power quality. Consumers submit their charging requirements (e.g., charging power and charging deadlines) and load curtailment tolerances to the aggregator. The aggregator is an entity assumed to have a long-term contract with the distribution system operator (DSO) and regularly receives network congestion information on behalf of retail energy users. Lyapunov optimization (LO) framework is used to reschedule the EVs, and household loads using DC optimal power flow (DCOPF) to get the dynamic congestion cost signal (CCS). The developed strategy is tested on a modified IEEE 33-bus radial active distribution network (ADN). Simulation results illustrate that the designed algorithm is promising in mitigating network congestion by ensuring significantly fewer violations of network constraints (i.e., line limits) both in terms of capacity and frequency. It also results in less energy cost as compared to other benchmark algorithms, e.g., greedy algorithm, and provides a guarantee of meeting EV charging, and flexible household loads’ (FHL) delay tolerance constraints. The average curtailment ratio of FHL and the service delay for EV-charging requests are converged to the user-defined limits, i.e., 0.25 for curtailment ratio tolerance and 10 times-lots for EV service delay. Unlike other counterparts, the developed algorithm is especially suitable for real-time applications as the per-slot average computational cost is negligible, i.e., 0.55 s.

Communication Strategies for Effective Interaction With Pedestrians and Automated Service Vehicles in Japanese Parking Areas

One of the challenges in introducing automated service vehicles (ASVs) to parking areas is guiding pedestrians to make quick and appropriate crossing decisions based on an understanding of what the ASV typically does. This study aims to find effective communication strategies for ASVs for pedestrian crossings in Japanese parking areas. Virtual Reality experiments were conducted with 40 participants facilitating vehicle behavior (Normal Deceleration, Early Deceleration, Early Stop) and text-based external human-machine interfaces (eHMIs; No eHMI, “After you,” “I’ll stop,” “In Automated Driving”) as tools of communication with two types of ASVs (bus and golf cart) in parking areas. The results indicated that vehicle behavior significantly influenced pedestrian crossing decisions, and pedestrians began to cross when the ASV decelerated early and stopped not too far from them (Early Deceleration). Self-reported measure analyses revealed that text messages containing the intent of the ASV's actions or instruction (After you, I’ll stop) with Early Deceleration would probably lead to pedestrians’ favorable attitudes toward automated buses. These findings contribute to communication designs based on implicit communication for pedestrian crossing decision-making in parking areas with a clear interpretation of ASV’s intentions.

Modeling the lane-changing behavior of non-motorized vehicles on road segments via social force model

Using traffic marking to separate non-motorized lane from the adjacent motorized lane is a common traffic design method for urban road segments. With the increase in non-motorized vehicle flow, illegal lane-changing occurs frequently, which leads to more serious conflict among road users. The study of the behavior characteristics of non-motorized illegal lane-changing on road segments, and establishing a microscopic simulation model can be used as a theoretical support and analysis tool for the design of non-motorized lane. This paper takes non-motorized vehicles as the research object to study lane-changing behavior characteristics. Then, the K-means clustering algorithm is used to classify riding styles into three types: risker, opportunist, and prudent. The micro-behavioral characteristics of riders with different riding styles are analyzed. Next, a three-layer model framework composed of perceptual, decision-making, and social force model is established. The logit model is used in the decision-making model to predict the probability of non-motorized vehicles crossing the line. Different riding styles are considered in the social force, and a virtual boundary force is introduced to describe lane-changing behavior. Subsequently, parameters are calibrated and the model is validated in various ways. Finally, the proposed model is used to conduct simulation experiments to explore the renovation scheme of the non-motorized lane. The results show that the proposed model can reproduce the traffic operation in the real scenario.

Ultra-Short-Term Load Forecast of Charging Stations Considering the Travelling and Charging Behaviours of Electric Vehicles

The traditional electric vehicle (EV) load forecasting methods are mostly used to predict large areas such as cities, which makes it difficult to serve practical applications. The existing charging station load forecasting methods ignore the traveling and charging behaviors of EVs. To this end, a charging station ultra-short-term load prediction method considering the traveling and charging behaviors of EVs is proposed. Firstly, EV types are classified according to charging behaviors. On this basis, a rolling forecast model of the number of arrivals per unit time of each vehicle type is established, and then the impact of charging randomness on load forecast is reduced by repeated Monte Carlo sampling. The total load of charging stations during the prediction period can be obtained by adding up the load of individual vehicles. The results show that the method enables accurate prediction of ultra-short-term load at charging stations, which has higher accuracy and reference value than the traditional load forecasting methods.

A secure multifactor-based clustering scheme for internet of vehicles

The development of the Internet of Vehicles (IoV) has been made possible through a variety of communication technologies and advanced AI techniques. In this context, ensuring stable and efficient communication for IoV is extremely important. It addresses several challenges related to security issues, high dynamism, constant connection outages, and the expected high traffic density. To overcome these challenges, vehicle clustering is a viable strategy for a reliable communication environment. The majority of current research focuses on solving the problem of cluster stability and efficiency by utilizing one or multiple factors, particularly vehicle location, mobility, and behavior. This article introduces an efficient Multifactor Clustering Scheme for IoV (MFCS-IoV). MFCS-IoV includes two stages: cluster formation and cluster head selection. The cluster formation is based on the improved K-means algorithm, considering both the vehicle mobility and final destination within the driving zone. While, a weighted cluster fitness function that includes mobility, behavior, dynamic location, and security is used to optimally select the Cluster Head (CH). Blockchain technology has been integrated into the model to safeguard the privacy of information like destination and other vehicle parameters. Simulation results demonstrate the success of MFCS-IoV in partitioning the vehicles into stable clusters and selecting the optimal cluster heads based on the proposed parameters. The effectiveness of MFCS-IoV is demonstrated by simulating different scenarios of 50 to 300 vehicles in the driving area. A comparison with related works shows that MFCS-IoV outperforms other schemes regarding average node-to-node delay, packet delivery rate, and throughput. Additionally, the proposed MFCS-IoV increases communication reliability by providing stable clusters while maintaining security measures.

Analysis of discretionary lane-changing behaviours of autonomous vehicles based on real-world data

This study aims to quantify the impact of discretionary lane-changing (DLC) on following vehicles (FVs) in the target lane using real-world dataset. The Waymo Open Dataset is used to identify the differences between autonomous vehicles (AVs) DLC and human-driven vehicles (HDVs) DLC maneuvers and compare their impacts on the driving volatility. Then, a block maxima (BM) model is applied to estimate crash risks. Finally, multivariate adaptive regression splines (MARS) is adopted to model gap acceptance behaviors of AV and HDV. Compared to HDV DLC, AV DLC leads to lower speed and yaw rate volatility and smaller acceleration rates of FVs. Further, the BM model reveals that the crash risk in AV DLC events is half of that in HDV DLC events. Additionally, MARS show that AV and HDV accept different lead gap. These findings highlight the benefits of mixing AVs in traffic and guide the improvement of AV controllers.

Clustering pipeline for vehicle behavior in smart villages

Smart cities and villages present a plethora of opportunities for fusing and managing multi-source data. However, in the analysis of mobility patterns, the use of only one data source (i.e., road sensors) without considering other contextual data sources, limits the understanding of the process. To address this gap, we propose a pipeline that integrates multiple data sources, providing valuable information for pattern extraction, mainly based on vehicle mobility behavior and provenance. Our research also highlights the critical role of selecting the appropriate normalization algorithm to scale input features from heterogeneous data sources, which has not received sufficient attention in the literature. We conducted our analysis using data from four License Plate Recognition (LPR) cameras, spanning nine months, and incorporating several databases that include provenance, gross income, and holiday information, resulting in a dataset of over 50,000 vehicles. Using this data and our clustering pipeline, we identified various traffic patterns among residents and visitors in a rural touristic area. Our findings assist data analysts in choosing algorithms for analyzing heterogeneous datasets. Moreover, policymakers could use our results to adjust the resources, such as new parking zones.

Modeling and simulation of charging characteristics of electric vehicle group under the mode of autonomous driving‐shared travel

AbstractCompared with the traditional travel mode, the increasingly mature autonomous driving and shared travel technologies can lead to a higher driving utilization rate and lower car parc; however, at the same time, they will bring unknown impacts to the trans‐energy system. As a new generation of vehicles, the behavior of electric vehicles will also be affected. This paper describes and models the behavior of electric vehicle group in the autonomous driving‐shared travel mode in detail, and uses the multi‐agent technology to establish a large‐scale electric vehicle group simulation model. This model fully considers the constraints of traffic network and charging station and the influence of fuel vehicles, which can simulate the actual scene well and be used to study the charging behavior of electric vehicle group. Finally, the simulation model is used to obtain the charging load curve of the electric vehicle group under the new travel mode and analyze the influence of travel upgrade and network topology on charging load.

Simulation of Signalized Intersection with Non-Lane-Based Heterogeneous Traffic Conditions Using Cellular Automata

Intersections affect the maneuvering and driving behavior of vehicles. The present study attempts to simulate an isolated signalized intersection with the dimensions obtained through the influence zone of intersections. This model includes several unexplored traffic characteristics observed at the intersection, such as non-lane-based heterogeneity and seepage behavior. The model was calibrated and validated with the field data collected in New Delhi, India. Several measures of performance, such as GEH statistics, Theil’s coefficient, root mean square error, and so forth, were used to validate and benchmark the simulation model. After calibration and validation, the model was used to find delays. The delays obtained from the model, several manuals, and the field were compared and found to be close to the field delays. Further, delays obtained from Indonesian and Canadian manuals were comparatively closer to the delays obtained from the field, whereas delays obtained from the Indian Highway Capacity Manual (2017) and U.S. Highway Capacity Manual (2010) are overestimated. The model presented can be used to benchmark the performance of signalized intersections under a variety of traffic and environmental conditions.

FUBA: A fuzzy‐based unmanned aerial vehicle behaviour analytics for trust management in flying ad‐hoc networks

AbstractFlying Ad‐Hoc Network (FANET) is a promising ad hoc networking paradigm that can offer new added value services in military and civilian applications. Typically, it incorporates a group of Unmanned Aerial Vehicles (UAVs), known as drones that collaborate and cooperate to accomplish several missions without human intervention. However, UAV communications are prone to various attacks and detecting malicious nodes is essential for efficient FANET operation. Trust management is an effective method that plays a significant role in the prediction and recognition of intrusions in FANETs. Specifically, evaluating node behaviour remains an important issue in this domain. For this purpose, the authors suggest using fuzzy logic, one of the most commonly used methods for trust computation, which classifies nodes based on multiple criteria to handle complex environments. In addition, the Received Signal Strength Indication (RSSI) is an important parameter that can be used in fuzzy logic to evaluate a drone's behaviour. However, in outdoor flying networks, the RSSI can be seriously influenced by the humidity of the air, which can dramatically impact the accuracy of the trust results. FUBA, a fuzzy‐based UAV behaviour analytics is presented for trust management in FANETs. By considering humidity as a new parameter, FUBA can identify insider threats and increase the overall network's trustworthiness under bad weather conditions. It is capable of performing well in outdoor flying networks. The simulation results indicate that the proposed model significantly outperforms FNDN and UNION in terms of the average end‐to‐end delay and the false positive ratio.

Review on the Development of Left Turn Crossing Theory of Non-Motor Vehicles

Non-motor vehicles are an important part of urban road traffic system, which plays an important role in the daily travel of urban residents. In recent years, the congestion of urban road traffic system has become more and more serious. In order to alleviate the congestion situation, on the one hand, the traffic management department reduces the road congestion by limiting the number of motor vehicles; on the other hand, the government vigorously advocates public transportation and green and low-carbon travel to adjust the travel mode structure. This paper systematically combs, summarizes and summarizes the views of domestic and foreign scholars from two aspects of the mode and theoretical development of non-motor vehicles turning left across the street. It is found that the left-turn crossing behavior of non-motor vehicles is from simple to comprehensive, from immature to gradually mature. Finally, the research on the development of non-motor vehicle holiday behavior is summarized and prospected.

Dynamic characteristics of rack vehicle-track coupled system on large slope line: theoretical modelling and experimental validation

Rack railway is a rail transportation that utilizes the gear-rack engagement to supply the traction forces on large-slope lines, primarily employed in mountainous regions where the conventional trains cannot operate due to the wheel-rail adhesion limitations. However, there is limited research on this system dynamics and further analysis is required to understand the interaction mechanism between the rack vehicle and track. Based on the typical vehicle-track coupled dynamics theory, the rack vehicle-track spatially coupled dynamics model is developed in this paper to evaluate the dynamic behaviours of the rack vehicle and the track system running on large-slope line with a detailed modeling of the longitudinal motion for the rack and sleeper, where the time-varying gear-rack mesh stiffness and the rail geometrical irregularity are incorporated. The excellent agreement observed between simulated and field-test results serves as strong validation for developed dynamics model. The results demonstrate that the vibration responses of the wheelset and the rack are dominated by the gear-rack mesh excitations. It should be noticed that the wheel loads are reduced by the presence of the gear-rack engagement. Furthermore, the vibration of the sleeper can explicitly reflect the gear-rack mesh characteristics through the transfer of the rack fastener.

Decentralized collaborative optimal scheduling for EV charging stations based on multi‐agent reinforcement learning

AbstractCharging behaviours of electric vehicles (EVs) exhibit substantial randomness, making accurate prediction or modelling challenging. Furthermore, as the number of EVs continues to increase, charging stations are diversifying their offerings to accommodate distinct charging characteristics, addressing a wide spectrum of EV charging needs. Previous research mostly focused on the randomness of EVs while neglecting the heterogeneity in charging infrastructure. Therefore, this paper introduces a decentralized collaborative optimal method for EV charging stations, taking into account the varying facility types and the power limitations. First, a decentralized collaborative framework is proposed. The energy boundary model and the average laxity of EVs contribute to transforming the optimization problem into a Markov Decision Process (MDP) with uncertain transitions. Then, multi‐agent deep deterministic policy gradient multi‐individuals (MADDPG‐MI) algorithm is developed to train several heterogeneous agents presenting different types of charging facilities. Each agent makes decisions for multiple homogenous charging piles. Numerous simulation studies validate that the proposed method can effectively reduce charging costs and manages in scenarios involving either homogeneous or multiple heterogeneous charging facilities. Moreover, the MADDPG‐MI algorithm demonstrates performance consistency among multiple decision‐making units while consuming lower training resources offering enhanced scalability.