Vehicle Lane Research Articles

Vehicle Lane Changing Game Model Based on Improved SVM Algorithm

In order to improve the autonomous lane-changing performance of unmanned vehicles, this paper aims to solve the problem of inaccurate decision classification in traditional support vector machine (SVM) algorithms applied to the lane-changing decision-making stage of intelligent driving vehicles. By using game theory-related theories and combining the improved support vector machine (SSA-SVM) method, a vehicle autonomous lane-changing strategy based on game theory is established. The optimized SVM method has certain advantages for vehicle lane-changing decision-making with a small sample size in actual production processes. The lane-changing decision judgment accuracy rate of the SSA-SVM algorithm model can reach 93.6% compared with the SVM algorithm model without algorithm optimization; the SSA-SVM algorithm model has obvious advantages in decision performance and running speed. Therefore, the proposed new algorithm can effectively solve the problem of the objective consideration of the payoff function in conventional decision game theory.

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.

An Improved RRT Path-Planning Algorithm Based on Vehicle Lane-Change Trajectory Data

The Rapidly-exploring Random Tree (RRT) algorithm faces issues in path planning, including low search efficiency, high randomness, and suboptimal path quality. To overcome these issues, this paper proposes an improved RRT planning algorithm based on vehicle lane change trajectory data. This algorithm dynamically adjusts the sampling area based on road environment and trajectory change laws, allowing the random tree to sample within an effective area, thereby improving the algorithm’s sampling efficiency. After determining the sampling area, a sampling point optimization strategy is used to enhance sampling quality, resulting in a smoother and more executable path. Finally, the vehicle is processed in a standardized manner to further improve path safety. Simulation results indicate that, compared to the original RRT algorithm, the improved version reduces nodes, planning time, and path length by 12.77%, 64.79%, and 12.87%, respectively. It also improves path smoothness and more closely aligns with actual lane-change trajectories, demonstrating the effectiveness and executability of the improved algorithm.

Study on the Deviation Characteristics of Driving Trajectories for Autonomous Vehicles and the Design of Dedicated Lane Widths

The vehicular trajectory offset represents a critical controlling element in the design of lane width. In light of the paucity of extant research on the lane widths for dedicated autonomous vehicle lanes, this study deployed the PreScan-Simulink co-simulation platform. Based on the established typical lateral and longitudinal control methods for autonomous vehicles, we initially identified the primary factors influencing trajectory offset through multifactorial coupled analysis. Subsequently, we conducted quantitative research on vehicle trajectory offset using S-shaped curves to elucidate the patterns in geometric elements’ impact on trajectory offset. Following this, we established a model of the relationship between design speed and trajectory offset under different vehicle types. Ultimately, we calculated the lane width values for scenarios involving varying positions and numbers of dedicated lanes. The results demonstrate that vehicle speed significantly impacts the trajectory offsets of autonomous vehicles. For passenger cars, the mean offset at speeds between 60 and 130 km/h is approximately 10 cm. At higher speeds of 140–150 km/h, the offset is more variable. The range of offset exhibited by trucks at speeds between 60 and 100 km/h is [8 cm, 16 cm]. In the case of a single dedicated lane, the width of the inner lanes intended for passenger cars is [2.60 m, 3.00 m], while the outer lanes designed to accommodate trucks have a width of [3.00 m, 3.20 m]. In scenarios with two dedicated lanes, the width of lanes for passenger cars can be reduced further, whereas the required lane width for trucks remains largely unchanged compared to that for single-lane setups. The conclusions show that the width of lanes adapted to autonomous vehicles could be reduced, which could help to optimize the use of road space, thus potentially reducing the occupation of land resources, reducing the environmental impact of road construction, and contributing to sustainable development. This study also provides valuable insights for the design of lanes dedicated to autonomous vehicles.

Mechanism and modeling of car-following behavior under local multi-vehicle influence

Aiming at the limitations of single-dimensional car-following model to describe vehicle car-following behavior in local multi-vehicle environment, the mechanism of vehicles in adjacent lane influencing the subject vehicle car-following behavior is explored, and a vehicle car-following model more suitable for local multi-vehicle environment is attempted to be established. The driving behavior variable reflecting the influence of vehicles in adjacent lane was determined by correlation analysis. Vortisch indicator of similarity(VIS) was used to characterize the influence of vehicles in adjacent lane on car-following behavior. Chi-square independent test and kernel density curve were used to determine the VIS demarcation threshold reflecting whether the influence is significant. Recursive feature elimination was used to screen the variables related to car-following samples significantly affected by vehicles in adjacent lane. The influence mechanism of variables was determined according to the statistical analysis results. Based on the mechanism proposed, the car-following model suitable for local multi-vehicle environment was constructed and its prediction effect was evaluated. Results show that VIS between the speed of subject vehicle and following vehicle in adjacent lane can characterize the influence and the VIS threshold is 0.668. It is concluded that the attention mechanism and memory effect can explain the influence mechanism of car-following behavior in multi-vehicle environment. Considering the attention mechanism and memory effect, RMSE decrease by 65%in Full Velocity Difference Model (FVD) model and 62%in Intelligent Driver Model (IDM) model, MAE decrease by 65%and 59%and R2 increased by 180%and 288%respectively, which proved the rationality of the attention mechanism and memory effect in explaining the car following behavior of subject vehicle in local multi-vehicle environment.

Road section traffic risk propagation model based on macro traffic flow energy consumption

Traffic risk is an important source of road traffic accidents. Effectively predicting the propagation of accident risks on the road after an accident is of great significance for preventing secondary accidents. Therefore, this paper establishes a road section accident risk propagation model based on macro traffic flow energy consumption. Firstly, the influence of lane occupation and vehicle lane changing after the accident on traffic flow is analyzed, and a macro traffic flow model under the risk after the accident is constructed. Secondly, combined with the definition of traffic flow energy dissipation, the movement of the whole vehicle is abstracted as a fluid movement process, and a traffic flow energy consumption model under the risk after the accident is proposed to quantify the accident risk. Finally, according to the spatiotemporal correlation of risk propagation, a risk impact range and duration calculation model is proposed to describe the risk propagation process. In order to verify the effectiveness of the risk propagation model proposed in this paper, MATLAB and VISSIM are used to carry out numerical simulation and simulation verification of traffic flow operation under different initial traffic flow densities. The experimental results show that the greater the initial density of the road section when the accident occurs, the wider the risk impact range and the longer the duration. The absolute value of the prediction deviation rate of the proposed model is below 8%, which has a good prediction effect.

Cooperative Adaptive Cruise Control Platoon Fleet Formation Model Considering Efficiency and Stability

In the existing formation model, vehicles in the same lane or adjacent lane are regarded as the structure, and the driving behavior of vehicles is studied from the perspectives of safety, speed consistency, and stability, and the speed control model is proposed from the perspective of vehicles themselves, to obtain a stable fleet with the same distance and speed. However, in this process, the initial condition of the vehicle, the traffic flow environment, and the efficiency of the fleet formation are less considered. Therefore, based on summarizing the existing fleet building model, this paper puts forward the rapid construction model and algorithm of a cooperative adaptive cruise control platoon fleet. One of the important goals of forming a team is to enter the team with the smoothest trajectory in the shortest time. Therefore, this chapter studies the trajectory optimization of the vehicle formation process from the perspective of vehicle dynamics.

Anticipated buffer time – An evasive surrogate safety indicator for risk assessment of unsignalized intersections under heterogeneous traffic and aggressive driving conditions

Risk assessment of unsignalized intersections is particularly challenging when confronted with a combination of factors such as heavy traffic, diverse vehicle types, lane indiscipline, aggressive driving, and evasive manoeuvres. Understanding how people drive in these situations is crucial for accurately assessing the risks at unsignalized intersections. This study introduces a novel surrogate safety indicator, i.e. Anticipated Buffer Time (ABT), designed to account for these various factors. Additionally, three new indicators derived from ABT are introduced, namely ABT Negation Ratio, ABT Extremity Ratio, and ABT Progression Ratio. A risk assessment measure, denoted as UnSigRisk Score, is formulated using these three indicators for unsignalized intersections. Three intersections in Ahmedabad, India, were selected for the study due to their manifestation of these challenging conditions. Spearman Rank Correlation Coefficient was estimated to find out how well can UnSigRisk Score measure is able to quantify evasive behaviour. The results indicate that this score proficiently measures evasive behaviour, exhibiting coefficients exceeding 0.6 in all cases—significantly outperforming the current evasive indicators, Yaw Rate Ratio and Jerk. The proposed risk assessment score could serve as a practical tool for transportation authorities, enabling them to identify the most vulnerable intersections and allocate resources for targeted safety interventions wisely. The study unequivocally demonstrates that the use of ABT paves the way for a thorough examination of safety at unsignalized intersections, regardless of driving behaviour and traffic conditions.

Highway Main Lane Vehicles Driving Behavior Prediction Based on Residual-Transformer

Highway Main Lane Vehicles Driving Behavior Prediction Based on Residual-Transformer

PERENCANAAN SIRKULASI RUANG PUSAT TERAPI HOLISTIK DI SAMARINDA

Samarinda is one of the most populous cities in East Kalimantan. Living in a densely populated urban area has a greater impact on the risk of mental health disorders. Poor mental health has an impact on physical health. One effort for health care is by conducting holistic health therapy as an alternative to healing overall health, starting from a person's physical, emotional, social, and spiritual health. The purpose of this planning is to produce a holistic therapy center building design in Samarinda with circulation planning that can facilitate building users in their activities in it. Through the analysis method by analyzing the area and building circulation. Analysis of area circulation is carried out by arranging vehicle lanes, parking and building positions. Analysis of building circulation is carried out by determining the pattern of vertical and horizontal space circulation. This planning produces a holistic therapy center in Samarinda that has a circulation space that can increase comfort and facilitate access for building users, so that this therapy center can meet the needs of urban physical and psychological health and become a place for a healthy environmental community

Analysis of Highway Vehicle Lane Change Duration Based on Survival Model

To investigate highway vehicle lane-changing behavior, we utilized the publicly available naturalistic driving dataset, HighD, to extract the movement data of vehicles involved in lane changes and their proximate counterparts. We employed univariate and multivariate Cox proportional hazards models alongside random survival forest models to analyze the influence of various factors on lane change duration, assess their statistical significance, and compare the performance of multiple random survival forest models. Our findings indicate that several variables significantly impact lane change duration, including the standard deviation of lane-changing vehicles, lane-changing vehicle speed, distance to the following vehicle in the target lane, lane-changing vehicle length, and distance to the following vehicle in the current lane. Notably, the standard deviation and vehicle length act as protective factors, with increases in these variables correlating with longer lane change durations. Conversely, higher lane-changing vehicle speeds and shorter distances to following vehicles in both the current and target lanes are associated with shorter lane change durations, indicating their role as risk factors. Feature variable selection did not substantially improve the training performance of the random survival forest model based on our findings. However, validation set evaluation showed that careful feature variable selection can enhance model accuracy, leading to improved AUC values. These insights lay the groundwork for advancing research in predicting lane-changing behaviors, understanding lane-changing intentions, and developing pre-emptive safety measures against hazardous lane changes.

An improved hierarchical deep reinforcement learning algorithm for multi-intelligent vehicle lane change

Lane change is a pivotal technology in autonomous driving, playing a significant role in improving traffic conditions. The control task of lane change becomes exceptionally complex for coordination of multiple intelligent vehicles, especially in unpredictable situations. To address this issue, the paper proposes a novel multi-intelligent vehicle lane change method (MVLC) based on Deep Reinforcement Learning (DRL). The MVLC features a hierarchical framework that includes a lower-layer lane change controller and an upper-layer reinforcement learning decision-making method. In the lower layer, a lane change controller is designed to execute motion control for a single vehicle, consisting of a lateral controller utilizing dueling double deep Q-network to make lane change decision and a longitudinal controller that employs Intelligent Driver Model (IDM) to follow the preceding vehicle. In the upper layer, a model-free DRL method is used for simultaneous control of multiple intelligent vehicles. To learn the optimal policy, a comprehensive reward function is designed. Finally, experiments are conducted in mixed traffic to valid the effectiveness of the proposed method. Results show that MVLC achieves secure and timely lane changes for multiple vehicles. Therefore, the method is expected to have significant potential for improving overall traffic efficiency and mitigating traffic congestion.

A Nonlinear Convolutional Neural Network Algorithm for Autonomous Vehicle Lane Line Detection

A Nonlinear Convolutional Neural Network Algorithm for Autonomous Vehicle Lane Line Detection

Influence of surrounding traffic on lane change dynamics: Insights from a video-based laboratory study

The inherent complexity associated with lane-changing manoeuvres can significantly disrupt traffic flow and increase the risk of collisions. While the lane-changing vehicle influences the surrounding traffic, it is also simultaneously influenced by it. This study aims to examine how the presence and behaviour of surrounding vehicles affect the lane changer's behaviour. A study was conducted in the laboratory using video stimuli of various simulated lane-changing scenarios to achieve the research aim. The study used a two-block design. In the first block, the impact of the lag vehicle was evaluated by varying its gap and behaviour (acceleration, deceleration or maintaining speed) relative to the lane-changing vehicle. In the second block, both the lead and lag gaps were manipulated with respect to the lane-changing vehicle. Data from the participants (n=29) were collected on dependent variables, including lane change decisions (gap acceptance or rejection), perceived cooperation, and reaction time. The analysis was conducted using an Aligned Rank Transform ANOVA. The findings of this laboratory-based study suggest that the lag vehicle, specifically its behaviour, has more influence on lane change decisions than the lead vehicle in the target lane. Additionally, when a lag vehicle decelerates to create a gap in response to a lane changer's request, its actions are perceived as more cooperative, compared to when it accelerates or maintains speed. Furthermore, decisions to change lanes are made faster when the lag vehicle shows a deceleration behaviour. The results of this laboratory-based study provide valuable insights for improving current lane-changing models. We also discuss the implications of findings for improving algorithms governing autonomous vehicle interactions in mixed traffic. Finally, we discuss the benefits and limitations of laboratory-based approaches in studying causal relationships among different factors, as well as the generalizability of our findings.

Bus rapid transit as arterial corridor traffic calming: The relationship between transit infrastructure and motor vehicle operating speeds

Objectives This article presents an analysis of the traffic-calming effects of bus rapid transit (BRT) by studying changes to motor vehicle speeds before and after implementation of Albuquerque Rapid Transit (ART) infrastructure in Albuquerque, New Mexico. Methods While ART construction was completed in spring 2018, the BRT buses did not operate until December 2019; providing a unique opportunity to explore the influence of BRT infrastructure sans BRT buses (i.e., to tease apart the effects of BRT infrastructure and operations). We used validated data from StreetLight InSight to compare before/after changes to average motor vehicle speeds and 85th percentile motor vehicle speeds at 46 ART sites and 36 control sites. Results Findings suggest that infrastructure associated with BRT systems can improve traffic safety by reducing vehicle speeds. Speed decreases at the ART sites were especially strong in terms of 85th percentile decreases, suggesting that the BRT infrastructure is especially effective at limiting excessive speeding. Motor vehicle 85th-percentile speeds along the ART corridor were reduced by 11.5% (compared to a 5.8% decrease at control sites). The 85th-percentile speeds at the ART sites decreased from 32.3 mph to 28.6 mph, which is an especially important range for vulnerable road-user safety outcomes. While ART intersections saw the largest decreases in absolute speeds (a reduction of 4.1 mph in 85th-percentile speeds), ART mid-block sites had larger decreases relative to the control mid-block sites (decreases in 85th-percentile speeds were 73.7% greater at ART mid-block sites than at control mid-block sites). BRT-related lane reductions were linked with particularly strong speed reductions; there were 85th-percentile speed reductions of 4.1 mph (12.6%) when general vehicle lanes were removed versus 2.2 mph (7.8%) when lanes were not removed. Conclusions Speed reductions were experienced across the ART corridor even though 87.0% of BRT locations did not have a change in posted speed limit, suggesting that physical changes to the roadway associated with BRT were impactful in terms of speed reductions and in turn could possibly promote traffic injury prevention by decreasing the number and severity of crashes.

Prototype Network for Few-Shot Hazard Assessment of Vehicle Lane Changes in Risk Field

Prototype Network for Few-Shot Hazard Assessment of Vehicle Lane Changes in Risk Field

Social dilemmas in a mixed traffic flow of buses and personal vehicles in transport mode choice

This paper presents an analysis of social dilemmas that arise when passengers are faced with choosing between personal vehicles and buses in a mixed traffic flow. We conducted the computer simulation using a cellular automata framework to analyze the case. The Revised S-NFS model describes the dynamics of vehicles in a single lane, while Kukida's model defines the rules for lane changing. The presence of social dilemma is determined by the social efficiency deficit. We selected four scenarios that represent different states on the fundamental diagram of personal vehicle flow: free flow, critical point, congested flow, and heavy congested flow. The simulations were performed on an infinite two-lane road. The results show that a social dilemma of the prisoner type exists in congested and heavy congested flow, but not in free flow. Additionally, we have conducted a simulation for the scenario with a dedicated bus lane. This simulation has shown the presence of the chicken-type social dilemma. Simulation results can enhance our comprehension of choosing transportation modes.

Investigation of private and public bikes usage patterns considering GPS trajectory based cycling features

Understanding bike usage patterns is essential for increasing bike demand, evaluating the effectiveness of bike facilities, and improving the quality of the bike system. This study aims to identify factors that influence bike usage for zone-based departure and arrival trips. It also seeks to address knowledge gaps by comparing private and dock-based public bikes, as well as use on weekdays and weekends. This study employed GPS trajectory data from 12,106 private bikes and 29,776 dock-based public bikes over one week in Seoul, South Korea. The dataset comprises zone-based physical characteristics and cycling patterns for 19,153 census zones. To tackle the problem of excessive zero values for bike demand in many zones, zero-inflated negative binomial models were employed for analysis. The findings suggested that realized detours, arising from natural barriers and a lack of infrastructure, are associated with a reduction in arrival trips on weekends but an increase in departure trips on weekdays. Behavioral detours, linked to route preferences, tended to decrease usage of public bikes on weekdays. Departure and arrival trips increased in districts with a higher level of mixed land use and larger commercial areas on weekdays. Moreover, bicyclists tended to prefer districts with longer separated bikeways, while bike usage was likely to decrease in districts with a high floating population and vehicle lanes. These findings provide valuable insights into cycling usage patterns and associated factors, encouraging more extensive use of bikes.

Exploring the willingness to pay for high-occupancy toll lanes under conditions of low familiarity

This study evaluates details of a progressive transportation development model, wherein high occupancy vehicle (HOV) lanes are transformed into high-occupancy toll (HOT) lanes. Although the management strategy of HOT lanes has been implemented for many years, the implementation of HOT lanes is limited in many regions, and thus, many people remain unfamiliar with the concept. This study aims to evaluate travelers' willingness to pay for HOT lanes based on a “low application” scenario in Shenzhen, China, wherein some HOV lanes are present and may potentially be transformed into HOT lanes, but not all area residents are aware of their intended purpose. According to the Diffusion of Innovation Theory, we leverage this situation to conduct a survey of perceptions and attitudes toward the HOT lanes and evaluate how these perspectives may translate to HOT lane utilization. We further proposed a hybrid utility and regret model considering the impacts of loss aversion caused by tolls or coordinated carpooling for single occupancy vehicles to explore relationships between travel behavior and surveyed demographic and socio-economic characteristics in the context of HOT lanes in places where they are unfamiliar. A sensitivity analysis is conducted to characterize any apparent changing influences. The results show that the model considering decision regret performs well, especially in the scenario with low tolls. Nearly 80% of travelers are willing to pay tolls for HOT lanes, even with limited prior exposure to the concept. The increased acceptance of HOT lanes can be expected to hurt total toll revenue, which may be triggered by easier access to carpool partners associated with the free pass. The study informs a deeper understanding of travelers’ willingness to pay for HOT lanes and helps policy-makers develop differentiated tolling strategies.

A macroscopic model of mixed traffic flow considering the characteristics of the vicinity of traffic signals from CPS perspective

To enhance the efficiency and stability of traffic flow in the vicinity of traffic signals under mixed traffic, a macroscopic model considering the characteristics of the vicinity of traffic signals is proposed from the perspective of cyber-physical systems (CPS). In this model, the effects of traffic lights and vehicle lane changing behavior are analyzed. Among them, the remaining time of the signal light, the distance between the vehicle and the signal light, and the urgency of lane change are considered to build a macro model. Finally, the simulation results show that compared with the traditional macroscopic model, the proposed model can improve the stability of traffic flow in the vicinity of traffic signals and effectively alleviate traffic congestion.