Vehicle Behavior Research Articles

Median U-Turn Intersection Critical Parameter Research and Operational Performance Evaluation

As one of the unconventional intersection designs, the median U-turn (MUT) intersection design has been confirmed to have the potential to improve intersection efficiency and produce lower vehicle delays, and it has been widely applied to many urban networks. Most existing studies have successfully evaluated the operational performance of MUT intersections by analyzing the overall traffic flow, particularly for intersection delay and capacity. However, the impact of the critical parameters and behavior of individual vehicles in MUT intersection operations has not been adequately studied. These limitations cannot provide a complete and objective evaluation of MUT intersections. Therefore, a comprehensive cellular automata model is proposed to simulate vehicle dynamic variations, considering road channelization information and vehicle random movements. This model will be compared to the VISSIM model to validate rationality by using field data, and it shows a good agreement between the simulation results of both models. In addition, sensitive experiments reveal that properly adjusting the elements, including the separation distance, the proportion of left-turn vehicles, and green phase percentage, can improve the operation of MUT intersections to varying degrees. By appropriately improving intersection features and conducting reasonable evaluations, the overall performance and sustainability of the MUT intersections in Xi’an city can be enhanced. Finally, this paper offers a valuable guideline for the evaluation and modeling strategies of MUT intersections.

Requirements for automated micro-vehicles from the German public: a survey study

This study investigates public requirements for and acceptance of semi-sized automated micro-vehicles (AMVs) in urban traffic in Germany, addressing safety and functional expectations from both incidentally co-present persons and potential delivery customers. A two-step approach, combining qualitative pre-studies and a quantitative survey was employed. Qualitative research consists of interviews, focus groups, and expert workshops to identify requirements, which are quantified in a survey involving 1000 urban-dwelling Germans. The results show that safety-related requirements are paramount. The top priority is basic vehicle safety, such as “safe braking behaviour,” “visibility,” and “safety in all weather conditions”. Autonomous behaviours for safety and delivery-specific attributes are also significant, though some autonomous functions received mixed responses. Social and sustainability requirements are also important—size and speed restrictions only moderately. The novelty of the research approach lies in focusing not only on the identification of acceptance factors, i.e. showing that size is important to public acceptance, but to study tangible requirements and accepted limits regarding vehicle design, behaviour and integration into public spaces, such as speed and size limits, evaluation of specific autonomous behaviours and technical details. The study emphasises the need for infrastructure, regulations, and trust-building efforts in AMV adoption.

Energy-based approach to the assessment of traffic flow

This article focuses on modeling vehicle acceleration noise in different road conditions, emphasizing urban, highway, and rural roads in Ukraine. Acceleration noise, which refers to the fluctuations in a vehicle's acceleration, is a critical factor in vehicle safety, fuel efficiency, and driving comfort. The research aims to improve current vehicle dynamics models by integrating multi-body dynamics and machine learning algorithms, allowing for more precise predictions of acceleration variability in real-time. The study is based on the existing literature, showing that road surface quality significantly affects acceleration noise. With frequent stop-and-go traffic, urban roads produce moderate but irregular noise patterns. Highways show stable acceleration noise at moderate speeds, but noise increases sharply as vehicles approach higher speeds due to aerodynamic forces. Rural roads, especially those in poor condition, exhibit the highest variability in acceleration noise, even at low speeds. The proposed model has been validated using real-world data. It demonstrates a strong correlation between the predictions and actual vehicle behavior on various road types. One of the key innovations in this research is the use of machine learning to adjust model parameters in real-time dynamically. This adaptive approach enhances the model’s accuracy and applicability, especially in intelligent transport systems. The model can inform traffic management strategies, allowing for real-time adjustments to speed limits, traffic signals, and routing decisions based on road conditions. This contributes to safer, more efficient, and sustainable transport systems, particularly in regions with inconsistent road infrastructure. The research concludes that integrating acceleration noise modeling into intelligent transport systems can significantly improve traffic flow and vehicle safety. Future research will expand the dataset to include a broader range of vehicle types and road conditions, further refining the model's predictive capabilities.

Tucker Decomposition Enhanced Dynamic Graph Convolutional Networks for Crowd Flows Prediction

Crowd flows prediction is an important problem for traffic management and public safety. Graph Convolutional Network (GCN), known for its ability to effectively capture and utilize topological information, has demonstrated significant advancements in addressing this problem. However, GCN-based models were often based on predefined crowd-flow graphs via historical movement behaviors of human beings and traffic vehicles, which ignored the abnormal changes in crowd flows. In this study, we propose a multi-scale fusion GCN-based framework with Tucker decomposition named mTDNet to enhance dynamic GCN for Crowd flows prediction. Following the paradigm of extant methods, we also employ the predefined crowd-flow graphs as a part of mTDNet to effectively capture the historical movement behaviors of crowd flows. To capture the abnormal changes, we propose a Tucker decomposition-based network with the product of the adjacency matrix of historical movement pattern graphs and an adaptive learning tensor ( \(ALT\) ) by reconstructing the crowd flows. Particularly, we utilize the Tucker decomposition scheme to decompose \(ALT\) , which enhances the dynamic learning of graph structures, allowing for effective capturing of the dynamic changes in crowd flow, including abnormal changes. Furthermore, a multi-scale three-dimensional GCN is utilized to mine and fuse the multiscale spatio-temporal information from crowd flows, to further boost the mTDNet prediction performance. Experiments conducted on two real-world datasets showed that the proposed mTDNet surpasses other crowd flow prediction methods.

Sequential Multi-Scale Modeling Using an Artificial Neural Network-Based Surrogate Material Model for Predicting the Mechanical Behavior of a Li-Ion Pouch Cell Under Abuse Conditions

To analyze the safety behavior of electric vehicles, mechanical simulation models of their battery cells are essential. To ensure computational efficiency, the heterogeneous cell structure is represented by homogenized material models. The required parameters are calibrated against several characteristic cell experiments. As a result, it is hardly possible to describe the behavior of the individual battery components, which reduces the level of detail. In this work, a new data-driven material model is presented, which not only provides the homogenized behavior but also information about the components. For this purpose, a representative volume element (RVE) of the cell structure is created. To determine the constitutive material models of the individual components, different characterization tests are performed. A novel method for carrying out single-layer compression tests is presented for the characterization in the thickness direction. The parameterized RVE is subjected to a large number of load cases using first-order homogenization theory. This data basis is used to train an artificial neural network (ANN), which is then implemented in commercial FEA software LS-DYNA R9.3.1 and is thus available as a material model. This novel data-driven material model not only provides the stress–strain relationship, but also outputs information about the condition of the components, such as the thinning of the separator. The material model is validated against two characteristic cell experiments. A three-point-bending test and an indentation test of the cell is used for this purpose. Finally, the influence of the architecture of the neural network on the computational effort is discussed.

Numerical Investigation of Underwater Vehicle Maneuvering Under Static Drift Conditions

The hydrodynamic behavior of underwater vehicles is crucial for achieving optimal maneuverability and energy efficiency in various underwater environments, thereby ensuring effective underwater operations. This research addresses the drift characteristics of an underwater vehicle by conducting Computational Fluid Dynamics (CFD) simulations. DARPA Suboff model was used to analyze its maneuvering characteristics under static drift conditions at a velocity of 3.34 m/s and drift angles ranging from 0 to 18 degrees with 2-degree intervals. The simulations replicate actual sea conditions using the Reynolds-Averaged Navier-Stokes (RANS) equations combined with the k-ω Shear Stress Transport (SST) turbulence model. The computational domain and boundary conditions are carefully defined to optimize the computational cost. The results revealed a significant decrease in longitudinal force when the drift angle increased, while the lateral force and yaw moment showed substantial increases, indicating the complex interactions between drift angles and hydrodynamic performance. This research provides valuable insights into the hydrodynamic forces and moments acting on underwater vehicles, contributing to their design optimization for improved stability and efficiency.

Investigating a Toolchain from Trajectory Recording to Resimulation

The growing variety of transportation options and increasing traffic congestion pose new challenges for road safety. As a result, there is an intensified focus on developing automated driving features and assistance systems aimed at minimizing accidents caused by human errors. The creation of these systems requires a substantial amount of testing kilometers, with estimates suggesting that around 2.1 billion kilometers would be necessary to ensure that each situation pertinent to the driving function is encountered at least once with a probability of 50%. This paper advances the microscopic simulation of traffic scenarios beyond linear patterns, utilizing the open-source environment openPASS. It addresses the research question of whether existing microscopic simulations are able to realistically represent non-linear traffic scenarios. A comprehensive toolchain integrates simulation with video recordings and laser scans. The study compares recorded traffic flow data with simulations at a T-junction, assessing the realism of vehicle models and trajectory representation. Three scenarios are analyzed, considering vehicles and pedestrians. The 3D geometry of the scene was captured with a laser scanner, enabling the mapping of recorded video data onto a geo-referenced environment. Object trajectories were extracted using an ’Regions with Convolutional Neural Networks features’ object detector. While openPASS simulated vehicle and pedestrian behaviors effectively, limitations in trajectory variability and reaction times were observed. These findings highlight the need for more realistic behavior models. This research emphasizes the necessity for improvements to accommodate complex driving behaviors and pedestrian dynamics.

Vehicle Motion Control for Overactuated Vehicles to Enhance Controllability and Path Tracking

The motion control of vehicles poses distinct challenges for both vehicle stability and path tracking, especially under critical environmental and driving conditions. Overactuated vehicles can effectively utilize the available tyre–road friction potential by leveraging additional actuators, thus enhancing their stability and controllability even in challenging scenarios. This paper introduces a novel modular upstream control architecture for overactuated vehicles, integrating a fast and robust linear time-varying model predictive path and speed tracking controller with a model following approach and nonlinear control allocation to form a holistic vehicle motion controller. The architecture decouples the path and speed tracking task from the actuator allocation, where torque vectoring and rear-wheel steering are applied to achieve linear understeer reference vehicle behavior. It allows for the use of a simpler path tracking controller, enabling long preview horizons and enhanced computational efficiency. Nonlinearities, such as the mutual influence of lateral and longitudinal tyre forces, are accounted for within the control allocation. The simulation results demonstrate that the proposed control architecture and overactuation improve vehicle stability in critical driving conditions and reduce path tracking errors compared to a dual-motor vehicle.

A clustering-based approach to scenario-driven planning for EV charging with autonomous mobile chargers

The main goal of this paper is long-term planning for electric vehicle (EV) charging infrastructure using autonomous mobile chargers (AMCs). The proposed method employs a clustering-based strategy to group EVs based on similar charging patterns, thereby reducing the number of scenarios and simplifying the planning problem. This reduces the number of possible scenarios and simplifies the planning problem. Each cluster then undergoes a short-term scheduling process to determine the optimal allocation of AMCs among its EVs. The program evaluates the probability of each scenario as well as the corresponding time results. Eventually, it formulates an ideal long-term strategy for the deployment and operation of AMC. This plan incorporates the concept of confidence level to address uncertainty in forecasting vehicle behavior and charging requirements. It ensures that the number and capacity of chargers are sufficient to meet system requirements at various confidence levels. The concept of confidence level strikes a balance between the cost of deploying mobile chargers and the risk of failing to satisfy the charging demand. This approach leads to optimal and reliable planning for EV charging infrastructure.

Multimodal Trajectory Prediction for Diverse Vehicle Types in Autonomous Driving with Heterogeneous Data and Physical Constraints.

The accurate prediction of vehicle behavior is crucial for autonomous driving systems, impacting their safety and efficiency in complex urban environments. To address the challenge of multi-agent trajectory prediction, we propose a novel model integrating multiple input modalities, including historical trajectories, map data, vehicle features, and interaction information. Our approach employs a Conditional Variational Autoencoder (CVAE) framework with a decoder that predicts control actions using the Gaussian Mixture Model (GMM) and then converts these actions into dynamically feasible trajectories through a bicycle model. Evaluated on the nuScenes dataset, the model achieves great performance across key metrics, including minADE5 of 1.26 and minFDE5 of 2.85, demonstrating robust performance across various vehicle types and prediction horizons. These results indicate that integrating multiple data sources, physical models, and probabilistic methods significantly improves trajectory prediction accuracy and reliability for autonomous driving. Our approach generates diverse yet realistic predictions, capturing the multimodal nature of future outcomes while adhering to Physical Constraints and vehicle dynamics.

Nonverbal Communication of In-Vehicle Humanoid Robot to Communicate Autonomous Vehicle Behavior

Nonverbal Communication of In-Vehicle Humanoid Robot to Communicate Autonomous Vehicle Behavior

The effect of a malfunctioning braking system on the behaviour of a special vehicle during an emergency braking in a curvilinear movement

Vehicle mobility is an increasingly important issue today, even in the military field. Mobility depends on the condition of the vehicle, the route and, of course, the experience of the driver. Vehicle failures and damage are very common in military operations. It is therefore important to find out how these failures and damage can affect mobility. One of the essential parts of a vehicle is the braking system. The authors therefore decided to investigate what is the effect of a malfunctioning brake system on emergency braking behaviour of a special vehicle in a curvilinear movement. Simulation tests were performed based on an experimentally validated model. The tests were performed with a wheeled vehicle on three different surfaces: concrete, wet asphalt, and ice. The experimental conditions were given as follows – the braking process was considered for a braking system with ABS on and off and for two states of braking system sufficiency (8 braked wheels or 4 rear braked wheels). These tests allowed us to analyse the effect of the extent of the damage on safety, in this case the stopping of the vehicle on a specified curved route. The results of braking and stability on different surfaces and under given conditions are evaluated and described in this paper. On the basis of the results, it is possible to prepare training programmes (scenarios) for drivers of special vehicles for the purpose of driving techniques in critical situations.

CRUMPLE ZONE MODELLING OF PASSENGER VEHICLE USING MULTIPLE KELVIN MODEL AND OPTIMIZED WITH PARTICLE SWARM OPTIMIZATION

This paper presents the mathematical modelling of a vehicle crash system using a mass-spring-damper approach to simulate the behavior of a real vehicle during a frontal impact. A Multiple Kelvin model is developed to represent a real vehicle crash situation where the impact is introduced on the frontal vehicle body. The modelling process of Multiple Kelvin model is based on a single Kelvin model that developed into a set of seven mass-spring-damper systems representing the front crumple zone of a real vehicle. The model is then optimized for the parameters k and c using an optimization method namely Particle Swarm Optimization (PSO) algorithm in MATLAB-Simulink. The simulation results demonstrate deformation and acceleration responses closely follow the previous experimental results where the parameters namely Ni, Np, and iw are varied to enhance the model's precision through the calculation of error of 12.15 using parameters Ni = 80, Np = 40 and iw = 0.9.

Robust Static Output Feedback Control of a Semi-Active Vehicle Suspension Based on Magnetorheological Dampers

This paper proposes a novel design method for a magnetorheological (MR) damper-based semi-active suspension system. An improved MR damper model that accurately describes the hysteretic nature and effect of the applied current is presented. Given the unfeasibility of installing sensors for all vehicle states, an MR damper current controller that only considers the suspension deflection and deflection rate is proposed. A linear matrix inequality problem is formulated to design the current controller, with the objective of enhancing ride safety and comfort while guaranteeing vehicle stability and robustness against any road disturbance. A series of experiments demonstrates the enhanced performance of the proposed MR damper model, which exhibits greater accuracy than other state-of-the-art damper models, such as Bingham or bi-viscous. An evaluation of the vehicle behavior under two simulated road scenarios has been conducted to demonstrate the performance of the proposed output feedback MR damper-based semi-active suspension system.

Design Principles to Reduce Vehicle Pocketing at Guardrail-to-Concrete Barrier Transitions

Road restraint systems (RRSs) on European roads are provided by several manufacturers and, hence, lead to differences in geometry, material, and mode of operation. Focusing on the combination of soft steel RRSs with relatively stiffer concrete RRSs, it is vital to consider the potentially critical deformation kinematics during vehicle impacts, such as vehicle pocketing. Since a statutory test procedure was not introduced until mid-2024, much of the transition construction (TC) on Austrian roads has remained untested. Knowledge of the design features to be implemented during the refurbishment of such TCs is of great interest. The main focus of this study was to derive constructive measures (CMs) that increase traffic safety and are applicable to various TCs already installed on roads. The first step involved deriving design principles whose implementations in TCs reduce the risk of critical vehicle or RRS behavior. Based on finite element simulations, the functionality of a TC featuring all derived design principles was examined. The effect of each individual CM was analyzed in a parameter study. The results from a TB61 impact simulation on the derived TC showed the effectiveness of CMs, achieving smooth vehicle redirection. Vehicle pocketing was limited to a minimum, and neither penetration of the TC nor rollover of the vehicle was observed. The analysis of the influence of each CM indicated positive, and in some cases, negative effects. The working width was mainly positively influenced by the compaction of the posts, an additional steel bar, and the chamfering of the first concrete element. A rather diverse picture is drawn regarding the influence on the tensile forces in the guardrails. Some CMs had both positive and negative effects on the distribution of forces in the upper and lower guardrails. Nevertheless, all CMs had positive effects on the tensile forces in the coupling. The chamfering of the first concrete element was the most effective measure to prevent vehicle pocketing. However, through the combination of all CMs, the positive effects predominated, ensuring the functionality of the TC as a whole. This study provides basic insights into the effectiveness of constructive measures, which can serve as a reference for the renovation of in-service TCs or in the development phase of new TCs to be certified.

Reconstructing Road Roughness Profiles Using ANNs and Dynamic Vehicle Accelerations

Road networks are crucial infrastructures that play a significant role in the progress and advancement of societies. However, roads deteriorate over time due to regular use and external environmental factors. This deterioration leads to discomfort for road users as well as the generation of noise and vibrations, which negatively impact nearby structures. Therefore, it is essential to regularly maintain and monitor road networks. The International Roughness Index (IRI) is commonly used to quantify road roughness and serves as a key indicator for assessing road condition. Traditionally, obtaining the IRI involves manual or automated methods that can be time-consuming and expensive. This study explores the potential of using artificial neural networks (ANNs) and dynamic vehicle accelerations from two simulated car models to reconstruct road roughness profiles. These models include a simplified quarter-car (QC) model with two degrees of freedom, valued for its computational efficiency, and a more intricate full-car (FC) model with seven degrees of freedom, which replicates real-life vehicle behavior. This study also examines the ability of ANNs to predict the mechanical properties of the FC model from dynamic vehicle responses to obstacles. We compare the accuracy and computational efficiency of the two models and find that the QC model is almost 10 times faster than the FC model in reconstructing the road roughness profile whilst achieving higher accuracy.

Demand management of plug-in electric vehicle charging station considering bidirectional power flow using deep reinforcement learning

The recent development in plug-in electric vehicle technology has increased its popularity. Plug-in electric vehicles are widely used for their environment-friendly nature and they contribute to the reduction in global warming. With the increasing number of plug-in electric vehicles, charging coordination becomes essential for managing the charging station demand. The random charging behaviour of plug-in electric vehicles makes it a difficult task. This paper proposes a novel demand management strategy of charging stations. The proposed strategy supports the grid and reduces its burden during peak load. Deep-Q network based deep reinforcement learning is used in the proposed strategy. It is a value based deep reinforcement learning algorithm that approximates the Q value function using deep neural network. The deep reinforcement schedules the charging and discharging of plug-in electric vehicles to optimize the cost and manage the charging station load. Deep reinforcement learning enhances charging coordination by dynamically optimizing charging schedules according to real-time conditions and user preferences, thereby increasing efficiency and better integration with the grid. The reward function in deep reinforcement learning is designed based on the power price and demand of the charging station. A discount factor is introduced based on the service time to make the charging coordination efficient. A case study using dynamic pricing is carried out to validate the proposed strategy. The results prove that the proposed strategy optimizes charging and discharging costs and manages charging station demand efficiently. It is also observed that the proposed strategy is fast and incurs less computational cost.

Associations of Battery Cell Voltage Consistency with Driving Behavior of Real-world Electric Vehicles

For proposing an adaptive-threshold-based method for detecting battery voltage inconsistency fault, this study explored the associations between driving behavior and voltage consistency between cells (VCC) at a microscopic level, by performing a naturalistic driving experiment on real-world electric vehicles (EVs). The running process of EVs is divided into four kinds of micro-segments A, B, C, D through the driver’s pedal actions. Focusing on these segments, Pearson correlation coefficients (PCCs) between driving behavior parameters (DBPs) and voltage variation coefficient between cells (VVCC) are calculated, the impact patterns of DBPs to VVCC are analyzed by accumulated local effects (ALE) plots obtained from random forest (RF) modeling. The results show that the maximum PCC is reached by average accelerator pedal stroke with 0.724 for segments A, and by average speed with 0.789, 0.554, and 0.553 for the other three segments. The four RF models show a high accuracy of VVCC prediction with goodness of fit over 0.919, and the ALE plots demonstrate the impact patterns are positive-nonlinear overall. The maximum VVCC growing rates are reached by average accelerator pedal stroke for segments A (48.09%), and average speed for other segments (55.70%, 29.01%, and 23.68% for segments B, C, and D, respectively). These results imply a strong connection between driving behavior and battery voltage consistency, which could be effectively captured to provide crucial inputs and interpretation methods for modeling voltage consistency prediction during EVs running. Hence, this work lays the foundation for the development of battery voltage fault detection algorithms considering different driving states.

Human-like Decision Making for autonomous lane change driving: a hybrid inverse reinforcement learning with game-theoretical vehicle interaction model

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still embraces limitations on human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decisionmaking abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decisionmaking algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyse the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, comfort to build the comprehensive decision cost function. Use the combined decision cost function to conduct a non-cooperative game of vehicle lane changing decision to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario has been established. Firstly, we analyse the human-like decision-making model derived by the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decisionmaking algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of expressway.

DEEP NEURAL NETWORK AND CNN MODEL OF DRIVING BEHAVIOR PREDICTION FOR AUTONOMOUS VEHICLES IN SMART CITY

This research applies deep neural networks (DNN) and convolutional neural networks (CNN) to the modeling and prediction of driving behavior in autonomous vehicles within the Smart City context. Developed, trained, validated, and tested within the Keras framework, the model is optimized to predict the steering angle for self-driving vehicles in a controlled simulated environment. Utilizing a training dataset comprised of image data paired with steering angles, the model achieves autonomous navigation along a designated track. Key innovations in the model’s architecture, including parameter fine-tuning and structural optimization, contribute to its computational efficiency and high responsiveness. The integration of convolutional layers facilitates advanced spatial feature extraction, while the inclusion of repeated layers mitigates information loss, with implications for potential future enhancements. Clustering algorithms, including K-Means, DBSCAN, Gaussian Mixture Model, Mean-Shift, and Hierarchical Clustering, further augment the model by providing insights into driving environment segmentation, obstacle detection, and driving pattern analysis, thereby enhancing complex decision-making capabilities amid real- world noise and uncertainty. Empirical results demonstrate the efficacy of Gaussian Mixture and DBSCAN algorithms in addressing environmental uncertainties, with DBSCAN displaying robust noise tolerance and anomaly detection capabilities. Additionally, the CNN model exhibits superior performance, with lower loss values on both training and validation datasets compared to an RNN model, underscoring CNN’s suitability for visually driven tasks within autonomous systems. The study advances the field of autonomous vehicle behavior prediction through a novel integration of neural networks and clustering algorithms to support sophisticated decision-making in autonomous driving. The findings contribute to the development of intelligent systems within the Smart City framework, emphasizing model precision and computational efficiency.