Lane Selection Research Articles

Road marking defect detection based on CFG_SI_YOLO network

Existing road marking detection primarily focuses on the direction, position, and color of road markings. However, clear and accurate road markings directly impact issues such as directional guidance, lane selection, speed limits, and parking positions. Therefore, we introduce the CFG_SI_YOLO model for road marking defect detection. This model introduces a multi-channel CoordConv module, which enhances the network's focus on fine details based on the distribution characteristics of road markings defect. This helps prevent the loss of road marking information caused by model compression and pooling operations; Moreover, the model introduces the Focal-EIoU loss function to address the issue of imbalanced samples between easy and difficult cases. Additionally, the GELU activation function is incorporated to prevent gradient explosions, enhance the network's non-linear expressiveness, and improve the detection accuracy of the model. Finally, we add a similarity attention module to enhance the network's focus on the target, reduce interference from other objects, and mitigate false detection defects caused by inter-class similarity. Experiments conducted on a self-made dataset containing various types of road markings have shown that our approach achieved Precision, Recall, F1, IoU, and mAP of 85.7%, 85.8%, 85.7%, 75.1% and 82.8%, respectively. These results are significantly better than other methods, confirming the effectiveness and feasibility of our approach. Our code and results can be found on https://github.com/ly6660/Road_marking_line_code_data.

Probabilistic modeling and simulation of drivers’ lane selection and its impact on highway traffic using fuzzy-based decision-making

Traffic on highways has increased significantly in the past few years. Consequently, this has caused delays for the drivers in reaching their final destination and increased the highway’s congestion level. Many options have been proposed to ease these issues. In this paper, a model of the highway drivers’ population was built based on several factors, including the behavioral patterns of the drivers, like drivers’ time flexibility to reach the destination, their carpool eligibility, and their tolerance to pay the toll price, in addition to the traffic information from the system. A fuzzy logic decision-making model is presented to emulate how drivers would choose the lane to use based on the aforementioned factors and the current congestion levels of all the lanes on the highway. The presented model, along with the simulation results from applying the model to different simulation scenarios, show the usefulness of such a model in predicting an optimal toll value. Such optimal value would reduce congestion on the highway at one end while maximizing the revenue for the toll company.

STABILITY ANALYSIS FOR HETEROGENEOUS TRAFFIC FLOW WITH LANE-CHANGE DISTURBANCE

Stability analysis and benefit estimation have substantial implications for lane-change decision-making to reduce delay and variation. Connected platoons drive with minor headway to increase capacity, whereas dividing or reforming platoons significantly impacts traveling efficiency. Therefore, this article focuses on the instability of the platoon caused by an en-route lane-change. Construction of platoon forming, combination rules, and car-following models for various vehicle types are presented to describe driving behaviours. Then, a velocity adjustment and a model for lane-change preparation and recovery are proposed. In addition, a group of stability recognition indexes and related stability evaluation factors are presented. Experiments involving numerical comparisons of the proposed factors are conducted to demonstrate the propagation properties of the instability and reveal the fluctuation degree. The variation duration, velocity variation range, and total delay are the primary indicators for evaluating lane-change feasibility. The models and findings can be applied effectively in practice to determine the optimal time and location for en-route lane-change and to assist with traffic management and lane selection at the entrance.

Discretionary Lane-Change Decision and Control via Parameterized Soft Actor–Critic for Hybrid Action Space

This study focuses on a crucial task in the field of autonomous driving, autonomous lane change. Autonomous lane change plays a pivotal role in improving traffic flow, alleviating driver burden, and reducing the risk of traffic accidents. However, due to the complexity and uncertainty of lane-change scenarios, the functionality of autonomous lane change still faces challenges. In this research, we conducted autonomous lane-change simulations using both deep reinforcement learning (DRL) and model predictive control (MPC). Specifically, we used the parameterized soft actor–critic (PASAC) algorithm to train a DRL-based lane-change strategy to output both discrete lane-change decisions and continuous longitudinal vehicle acceleration. We also used MPC for lane selection based on the smallest predictive car-following costs for the different lanes. For the first time, we compared the performance of DRL and MPC in the context of lane-change decisions. The simulation results indicated that, under the same reward/cost function and traffic flow, both MPC and PASAC achieved a collision rate of 0%. PASAC demonstrated a comparable performance to MPC in terms of average rewards/costs and vehicle speeds.

Modeling of Vehicle Left-Turn Trajectories and Exit Lane Selection at Signalized Intersections

Modeling of Vehicle Left-Turn Trajectories and Exit Lane Selection at Signalized Intersections

Simple analysis of gel images with IOCBIO Gel

BackgroundCurrent solutions for the analysis of Western Blot images lack either transparency and reproducibility or can be tedious to use if one has to ensure the reproducibility of the analysis.ResultsHere, we present an open-source gel image analysis program, IOCBIO Gel. It is designed to simplify image analysis and link the analysis results with the metadata describing the measurements. The software runs on all major desktop operating systems. It allows one to use it in either a single-researcher environment with local storage of the data or in a multiple-researcher environment using a central database to facilitate data sharing within the research team and beyond. By recording the original image and all operations performed on it, such as image cropping, subtraction of background, sample lane selection, and integration boundaries, the software ensures the reproducibility of the analysis and simplifies making corrections at any stage of the research. The analysis results are available either through direct access to the database used to store it or through the export of the relevant data.ConclusionsThe software is not only limited to Western Blot image analysis and can be used to analyze images obtained as a part of many other widely used biochemical techniques such as isoelectric focusing. By recording the original data and all the analysis steps, the program improves reproducibility in the analysis and contributes to the implementation of FAIR principles in the related fields.

Investigating the dynamics of speed and acceleration at merging and diverging sections using UAV based trajectory data

The present study evaluates the speed and acceleration characteristics at the merging and diverging sections near two toll plazas located on National Highway under mixed traffic conditions using trajectory data obtained from video recorded using unmanned aerial vehicles (UAVs). The whole study section of 280 m is divided into zones of 20 m each, and the speed-distance and acceleration-distance relations are studied. The study analyzes the speed variations among vehicle classes in merging and diverging sections. The study shows that due to heterogeneous traffic and weak lane discipline, the speed distribution deviates from the normal distribution and follows the generalized extreme value (GEV) distribution in merging and diverging sections. The average maximum lateral speed is 3.0 km/h in the diverging section and 8.0 km/h in the diverging section (2.6 times higher than in the diverging section). The overall lane selection and lane changes are only prominent in the range from 40 m to 160 m in the merging section and the range from 100 m to 200 m in the diverging section. The results of acceleration modeling indicate that most vehicle classes follow a parabolic profile, except two-wheelers (2Ws) and light commercial vehicles (LCVs), whereas cars follow a dual-regime model in the diverging section, which is consistent with previous literature. The study also identified critical speeds for each vehicle class in both the merging and diverging sections, which can be useful in designing toll plaza facilities and informing safety measures.

SimToll: A Highway Toll, Lane Selection, and Traffic Modeling Dataset

SimToll: A Highway Toll, Lane Selection, and Traffic Modeling Dataset

Driving Behavior Modeling and Characteristic Learning for Human-like Decision-Making in Highway

To make autonomous vehicles consider driver's personalized characteristics, this paper proposes an integrated model and learning combined (IMLC) algorithm to realize human-like driving. It includes the integrated driving behavior modeling to ensure basic safety and the characteristic learning to further imitate human driver's style. Firstly, an integrated behavior model is built according to driver's operation logics, including lane advantage assessment, target lane selection and acceleration determination. The lane advantage is assessed by five lane features, like safety, efficiency, cooperativity, etc. Then, parameters of the built model are learned from human's demonstrations. For the lane selection parameter, a novel lane feature extraction method is presented and the maximum entropy inverse reinforcement learning (IRL) is adopted to solve. For the acceleration parameter, since it's hard to extract human's acceleration features accurately, the particle filtering is used to estimate. Finally, the IMLC algorithm is validated in highD dataset compared to existing algorithms. The results show that the RMSE of position and velocity in 9s are within 4.2m and 0.9m/s, which has great advantage. Moreover, we test the human-like performance in driver simulator. The safety and efficiency in this process are fairly approximate.

A two‐stage method for the shipper lane selection problem with time windows in transportation service procurement

AbstractThe shipper lane selection problem (SLSP) is determining which lanes are to be served by the shipper's vehicle fleet or outsourced to the carriers through auction. While the SLSP in previous studies assumes that each lane is associated with a set of discrete times at which it can be served, this study considers a generalized version assuming a lane service time window for each lane, which is named the SLSP with time windows (SLSPTW). The SLSPTW is formulated as a mixed integer linear programming model that minimizes the sum of the transportation and the service/setup costs incurred by the shipper to auction off the lanes served by the carriers. In the proposed two‐stage solution approach, the first stage is designed to generate quickly a set of possible solutions, the best of which is then verified by a decomposed model of the SLSPTW at the second stage. Besides, an iterative‐improvement mechanism for the proposed algorithm is adopted to achieve the efficiency of the solution quality improvement. The effectiveness and efficiency of the developed solution method is demonstrated by the conducted numerical experiments.

Modeling adaptive platoon and reservation‐based intersection control for connected and autonomous vehicles employing deep reinforcement learning

AbstractAs a cutting‐edge strategy to reduce travel delay and fuel consumption, platooning of connected and autonomous vehicles (CAVs) at signal‐free intersections has become increasingly popular in academia. However, when determining optimal platoon size, few studies have attempted to comprehensively consider the relations between the size of a CAV platoon and traffic conditions around an intersection. To this end, this study develops an adaptive platoon‐based autonomous intersection control model, named INTEL‐PLT, which adopts deep reinforcement learning technique to realize the optimization of multiple dynamic objectives (e.g., efficiency, fairness, and energy saving). The framework of INTEL‐PLT has a two‐level structure: The first level employs a reservation‐based policy integrated with a nonconflicting lane selection mechanism to determine the lanes’ releasing priorities; and the second level uses a deep Q‐network algorithm to identify the optimal platoon size based on real‐time traffic conditions (e.g., traffic density, vehicle movement, etc.) of an intersection. The model is validated and examined on the simulator Simulation of Urban Mobility. It is found that the proposed model exhibits superior performances on both travel efficiency and fuel conservation as compared with state‐of‐the‐art methods in three typical traffic conditions. Moreover, several in‐depth insights learned from the simulations are provided in this paper, which could better explain the relation between platoon size and traffic condition.

Lane Selection Model Based on Phase-Field Coupling and Set Pair Logic

Intelligent and connected driving (ICD) is an effective method of the vehicle’s active safety and traffic efficiency. Lane-changing is the critical part of ICD behavior and the basic content of traffic flow theory. Lane selection is the most important during lane-changing, which has a critical influence on traffic safety and efficiency. Focusing on the development of ICD technology, a lane selection model based on phase-field coupling and set pair logic is proposed. In this model, the method of phased-field coupling is used to comprehensively analyze the full information of lanes with the interaction between cluster vehicles considering driving propensity. The certain and uncertain human-vehicle-environment information is fully explored using the method of set pair logic. In the lane selection model, the lane utility and utility gains of lane-changing are calculated to select the candidate target lane. And the overall satisfaction is analyzed to determine the target lane as the final strategy. The proposed lane selection model constructed in this research fully considers the development of ICD technology and adapts to the requirement of an Intelligent and Connected Vehicle. This research could provide a theoretical basis for vehicle autonomous behavior decision-making and ICD.

A two-stage stochastic programming model for seaport berth and channel planning with uncertainties in ship arrival and handling times

The limited availability of berths and channels is generally the bottleneck restricting the capacity of a seaport and thus resulting in traffic congestion. Optimizing the operations of the berths and channels has been recognized as a more economic avenue for mitigating seaport traffic congestion compared with channel dredging and berth expanding that needs significant capital and time costs. This paper presents a two-stage stochastic mixed integer linear programming model for the seaport berth and channel planning, aiming to minimize the expected total weighted completion times of ships under uncertain ship arrival times and ship handling durations. The first stage decides the berth allocation of ships under uncertainty. In the second stage, the channel planning, including the selection of lanes, assignment of tugboats, and sequencing of ships, is determined after the uncertainty has been realized. To effectively solve the model, we propose two tailored decomposition methods, that is, the stage decomposition method and the decomposition-based heuristic algorithm (DHA). Then, a lower bound of the problem is derived to evaluate the quality of the solution. Numerical experiments on Tianjin Port of China show the satisfactory performance of these two proposed methods. Especially, the DHA is able to obtain near-optimal solutions with the average optimality gap less than 3% within four-hour computational time for the instances up to 500 scenarios and 190 ship movements. Some managerial insights are obtained to guide the operations of the port.

Behavior Decision Model With Situation Assessment for Intelligent Vehicles Based on Vehicle-to-Everything Information

Under the application of cooperative vehicle infrastructure technology, vehicles can drive more safely and efficiently in urban traffic environments. This paper presents a behavior decision model composed of a situation assessment module and decision process module to make a decision on lane selection and velocity control. Different common traffic elements are considered, such as surrounding obstacles, traffic lights, lane lines, and road velocity limits, to ensure the model outputs safe and legal behaviors. A green-wave passage strategy is also proposed to allow vehicles to pass through traffic intersections at a smoother velocity and to improve driving efficiency. To verify the correctness and rationality of the model, a Prescan/Simulink co-simulation platform including multiple common urban driving scenarios is established. The results show that the model can output correct behaviors with safety and legitimacy in different scenarios and realize vehicles meeting at intersections, vehicle-following, queuing at intersections with traffic lights, lane-changing for obstacle avoidance, and so forth. Compared with the general decision model without the green-wave passage strategy, the driving time is reduced by an average of 8.53%, and the standard deviation of the driving velocity is reduced by an average of 65.42%, which means that the model can reduce the variation of velocity and improve driving efficiency. The model has a certain practical application value.

Impact of Penetrations of Connected and Automated Vehicles on Lane Utilization Ratio

Lane Utilization Ratio (LUR), affected by lane selection behavior directly, represents the traffic distribution on different lanes of road section for a single direction. The research on LUR, especially under Penetration Conditions of Connected and Automated Vehicles (PCCAV), is not comprehensive enough. Considering the difficulty in the conduction of real vehicle experiment and data collection under PPCAV, the lane selection model based on phase-field coupling and set pair logic, which considers the full-information of lanes, was used to carry out microscopic traffic simulation. From the analysis of microsimulation results, the basic relationships between Penetration of Connected and Automated Vehicles (PCAV), traffic volume, and Lane-Changing Times, also that between PCAV, traffic volume, and LUR in the basic section of the urban expressway were studied. Moreover, the influence of driving propensity on the effect of PCAVs was also studied. The research results could enrich the traffic flow theory and provide the theoretical basis for traffic management and control.

Humanlike Decision and Motion Planning for Expressway Lane Changing Based on Artificial Potential Field

The autonomous vehicles (AVs) need to share the driving environment with the human driving vehicles (HDVs) on expressway in the future. The non-humanlike lane changing (LC) behavior of AVs can mislead human drivers, which brings potential risks. Stronger humanlike ability requires a more complex algorithm. However, the requirement of the on-board vehicle computation resources limits the humanlike ability of LC algorithms. In this context, considering environmental risks, driver speed requirements and driver focus shifting process, this paper proposes a new type of LC algorithm based on artificial potential field (APF) aiming to improve the humanlike ability. The coupling relationship between the longitudinal and the lateral potential field forces is analyzed theoretically based on environmental risk APF. Based on the relationship, we proposed a conversion mechanism of the driver between the lateral and longitudinal potential field forces to mimic the driver’s speed requirement. Then a target lane selection strategy is designed to trade-off the driver’s speed requirement and safety between multiple lanes. Finally, to mimic the driver’s focus transfer process, the lateral forces of the ego vehicle are analyzed theoretically to further propose a moving virtual lane lines algorithm to build the lateral space varying potential field. The algorithm proposed in this paper is validated by comparing with other LC algorithms in the real traffic scenarios. The results indicate that the proposed algorithm has a better ability to mimic human driver’s LC decision-making and provides a smoother and safer humanlike trajectory.

Optimal Trajectory Control for Left-Turn Vehicles at Exit Lane for Left-Turn Intersections

The exit lane for left-turn (EFL) intersection is a newly proposed unconventional intersection that can alleviate left-turn traffic congestion at intersections. The EFL design characteristic lies in that a part of exit lanes can be provisionally used as left-turn lanes to provide additional capacity for left-turn traffic. The inappropriate lane selection of human drivers decreases the effectiveness of such design. This paper establishes an optimal trajectory planning model for left-turn vehicles at EFL intersections under the automated driving environment. The longitudinal acceleration and lane changing variables are optimized simultaneously. The optimization model is formulated as a mixed-integer linear model, which ensures the computational efficiency. The effectiveness of the proposed model is explored under various traffic, geometric, and signal control conditions. The results show that the model can provide a suitable control strategy for left-turn vehicles. On average, traffic delay can be reduced by 47.3%. The proposed model has a promising control effect under high volume conditions. Moreover, the proposed model performs stably under the various length of the mixed-usage area.

Intersection Vehicle Turning Control for Fully Autonomous Driving Scenarios.

Currently the research and development of autonomous driving vehicles (ADVs) mainly consider the situation whereby manual driving vehicles and ADVs run simultaneously on lanes. In order to acquire the information of the vehicle itself and the environment necessary for decision-making and controlling, the ADVs that are under development now are normally equipped with a lot of sensing units, for example, high precision global positioning systems, various types of radar, and video processing systems. Obviously, the current advanced driver assistance systems (ADAS) or ADVs still have some problems concerning high reliability of driving safety, as well as the vehicle’s cost and price. It is certain, however, that in the future there will be some roads, areas or cities where all the vehicles are ADVs, i.e., without any human driving vehicles in traffic. For such scenarios, the methods of environment sensing, traffic instruction indicating, and vehicle controlling should be different from that of the situation mentioned above if the reliability of driving safety and the production cost expectation is to be improved significantly. With the anticipation that a more sophisticated vehicle ad hoc network (VANET) should be an essential transportation infrastructure for future ADV scenarios, the problem of vehicle turning control based on vehicle to everything (V2X) communication at road intersections is studied. The turning control at intersections mainly deals with three basic issues, i.e., target lane selection, trajectory planning and calculation, and vehicle controlling and tracking. In this paper, control strategy, model and algorithms are proposed for the three basic problems. A model predictive control (MPC) paradigm is used as the vehicle upper layer controller. Simulation is conducted on the CarSim-Simulink platform with typical intersection scenes.

Energy saving performance improvement of intelligent connected PHEVs via NN-based lane change decision

Plug-in hybrid electric vehicles (PHEVs) unite the advantages of the engine and electric motor which could provide great potential in saving energy. However, the fuel economy performance of the PHEVs is highly associated with the driving condition, especially for parallel PHEVs because they could not decouple the engine work status from the driving condition. Meanwhile, fuel economy performance is not only a longitudinal issue but also related to lane selection. Lane selection is an important driving behavior and the algorithm of lane selection is necessary for the development progress of intelligent connected vehicles. Energy consumption cost is an important part of the vehicle’s using consumption cost. Therefore, lane selection strategies must consider this point. With the development of intelligent connected vehicle technology, such as V2X (Vehicle to Everything), the potential of energy consumption performance of intelligent connected PHEVs could be improved by taking environment information from V2X and smart sensors into lane selection. In this paper, a neural network (NN) based method is proposed to predict the future status of the local vehicle using the information from V2X, and then another network is used to estimate the future energy consumption of each lane. The lane selection is decided on energy consumption estimation. Lastly, the effectiveness of the method is validated by simulation using Matlab combined with SUMO (Simulation of Urban MObility).

CLACD: A complete LAne-Changing decision modeling framework for the connected and traditional environments

This study develops a Complete LAne-Changing Decision (CLACD) modeling framework that explains both the mandatory and discretionary lane-changing behaviors, incorporates both the successful and failed lane-changing attempts, and describes lane-changing behaviors in both the traditional and connected environments. The connected environment provides real-time and valuable information about surrounding vehicles and downstream situations (e.g., congestion ahead) that drivers cannot foresee. Such information can be particularly useful for complex driving maneuvers like discretionary lane-changing (DLC), which requires information about surrounding traffic speeds and subsequent gaps available on the adjacent lanes. DLC modeling efforts in the connected environment appear to be nascent, primarily because of: (a) the novelty of the connected environment (and the consequent scarcity of the relevant data), and (b) the lack of a behaviorally sound DLC model even for the traditional environment (that is, without driver-aid messages). Moreover, the existing models omit failed DLC attempts by motorists that are likely to create traffic disruptions and have a significant impact on traffic safety. To overcome these challenges, this study develops a DLC model (i.e., CLACD model) for the traditional environment, which is extended for the connected environment. An integrated approach is employed to model DLC behavior by combining the target lane selection using the utility theory approach and the gap acceptance behavior using a game theory approach. To collect high-quality vehicle trajectory data in the connected environment, the CARRS-Q advanced driving simulator was used. The CLACD models (for both the traditional and connected environments) are calibrated using NGSIM and the driving simulator data, and the CLACD models’ performances were rigorously assessed using various performance indicators. Results reveal that the CLACD models can effectively capture the observed DLC decisions with high accuracy. The performance of CLACD models is compared with the performance of two alternative models described in the literature, revealing that the CLACD models outperform the alternatives. A sensitivity analysis suggests a consistent trend of the CLACD models, which agrees with past research. Furthermore, the CLACD model shows a realistic prediction of traffic flow patterns compared with the utility theory model. By incorporating failed DLC attempts into the CLACD models, the performance and realism of CLACD models have been significantly improved.