Lane Intersection Research Articles

Generating lane-level road networks from high-precision trajectory data with lane-changing behavior analysis

– Recent advances in mobile mapping systems have facilitated the collection of high-precision trajectory data in centimeter positioning accuracy. It provides the potential to infer lane-level road networks, which are essential for autonomous driving navigation. This task is challenging due to the complicated lane merging and diverging structures as well as the lane-changing patterns in trajectory data. This paper presents a lane-level road network generation method from high-precision trajectory data with lane-changing behavior analysis. Trajectories are firstly partitioned by detecting road intersections and changes in lane structure. Subsequently, in regions with consistent lane structure, a principal curve fitting algorithm is developed to extract lane centerlines. Erroneous lanes generated by lane-changing behavior are pruned based on a constructed lane intersection graph. In regions with merging and diverging lanes, a lane-group fitting algorithm is designed. This algorithm estimates lane locations by incorporating a Gaussian mixture model with lane width prior knowledge and then infers lane-level topological structures using trajectory flow information. The proposed method is evaluated on a real-world high-precision trajectory dataset. Comprehensive experiments demonstrate that it outperforms state-of-the-art methods in four metrics. Under complex scenarios, the method is capable of generating lane-level road networks with higher completeness and fewer fragments.

The Integrated optimization of intermittent lane intersection design and dynamic signal control: efficiency, safety, and fuel consumption

ABSTRACT Existing unconventional intersection designs can enhance the capacity of intersections to deal with repaid pressure on urban commuting, whereas they force vehicles to multi-stop and reorganize, resulting in safety risks and high fuel consumption. This paper proposes the Intermittent Lane Intersection (ILI) that combines the advantages of variable lane intersection and CTE (Combining the tandem control and exit lanes for left-turn control). An integrated optimization model is established to obtain the optimal geometric and signal control parameters, and a homothermic genetic algorithm is used to solve the model. Then, the application of ILI in different traffic demands of the Tianfu Third Street intersection is analyzed. Compared with the benchmark design (TI, CTE, and CTE with signal coordinated control), ILI can effectively reduce intersection delay, fuel consumption, and parking times. Additionally, ILI has great application superiority when the traffic arrival rate is [1500,1700] and the left-turn ratio is [0.40,0.60].

Signal timing and geometric design at contraflow left-turn lane intersections

As a type of innovative intersection, Contraflow left-turn lane (CLL) intersection, has been increasingly implemented at the signalized intersections for increasing the leftturn capacity. This study developed a systematic method for determining the length of CLL and the signal timing plan for implementing CLL at signalized intersections. At first, the signal timing and geometric design requirements in the implementation of CLL were analyzed. Then, these requirements were thoroughly considered in the development of the proposed method. A case study was conducted for evaluating the operational benefits of redesigning a real-world CLL intersection using the recommended signal timing plan and CLL lengths. The results of the case study show that the redesigned CLL intersection outperforms the existing CLL intersection in terms of the average traffic delay, average vehicle travel time, and average queue length, and the CLL intersection can achieve its best performance at the recommended CLL lengths. These results indicate that the proposed method can provide useful guidelines to traffic engineers in the implementation of this innovative intersection design.

Rolling‐horizon–based strategy of fully cooperative traffic under signalized intersections

AbstractDedicated left‐turn lanes are traditionally used at intersections. This practice may not be optimal where heavy traffic exists from multiple directions. As is well known, the capacity can be increased if vehicles are grouped in the same direction in advance, but the additional infrastructure is usually needed, such as presignal systems. Fortunately, under the development of connected and automated vehicle (CAV) technology, the presignal system can be achieved by coordinating vehicles directly. To this end, we establish a modeling framework and management strategies for pure CAV traffic to achieve direction‐based grouping. A rolling time‐horizon–based sorting strategy is developed to achieve real‐time coordination under uncertain vehicle arrivals. A series of numerical experiments have shown that the improvement of the proposed sorting strategy is significant and robust compared with traditional dedicated left‐turn lane intersections without coordination, especially when the traffic is busy.

Optimal control of automated left-turn platoon at contraflow left-turn lane intersections

Purpose This study aims to propose a centralized optimal control model for automated left-turn platoon at contraflow left-turn lane (CLL) intersections. Design/methodology/approach The lateral lane change control and the longitudinal acceleration in the control horizon are optimized simultaneously with the objective of maximizing traffic efficiency and smoothness. The proposed model is cast into a mixed-integer linear programming problem and then solved by the branch-and-bound technique. Findings The proposed model has a promising control effect under different geometric controlled conditions. Moreover, the proposed model performs robustly under various safety time headways, lengths of the CLL and green times of the main signal. Originality/value This study proposed a centralized optimal control model for automated left-turn platoon at CLL intersections. The lateral lane change control and the longitudinal acceleration in the control horizon are optimized simultaneously with the objective of maximizing traffic efficiency and smoothness

Geographically weighted poisson regression under linear model of coregionalization assistance: Application to a bicycle crash study

While cycling benefits individuals and society, cyclists are vulnerable road users, and their safety concerns arouse more macro-level spatial crash studies. Our study intends to investigate the spatial effects of population, land use, and bicycle lane infrastructures on bicycle crashes. This was done by developing a semi-parametric Geographically Weighted Poisson Regression (sGWPR) model which deals with the issue of spatial correlation and spatial non-stationarity simultaneously. It is a model that combines both constant and geographically varying parameters. To determine which parameter is fixed or non-stationary, previous studies suggest monitoring the Akaike Information Criterion (AICc). Yet, relying only on AICc might bury some spatial associations. So, in this study, we propose a Linear Model of Coregionalization (LMC) to assist the decision. Here, we use bicycle crash data across the metropolitan area of Greater Melbourne to establish sGWPR models suggested by AICc and LMC, respectively. Comparing the two sGWPR models, we found the sGWPR model under LMC results performs as well as sGWPR models suggested by AICc from the AICc perspective, and a 22.5% improvement in the mean squared error (MSE). It also uncovers more details about the spatial relationship between bicycle crashes and bicycle lane intersection density (BLID), an effect not suggested under AICc results. The parameters of BLID, a new measurement of bicycle lane facilities proposed by us, vary over space across analysis zones in Greater Melbourne.

Signal timing optimization of shifted left-turn intersections

A signal timing optimization method based on shifted left turn lane intersections is proposed to increase the efficiency of shifted left turn lane junctions. In previous studies, vehicle delays were often the only concern but vehicle exhaust emissions were ignored, which could easily aggravate environmental pollution. A multi-objective optimization model was developed in this paper for intersection signal timing from a vehicle and environmental perspective, using vehicle delay, capacity and exhaust emissions as indicators. A modified particle swarm algorithm was used to resolve the impact of a shifted left turn lane on vehicles at a selected junction in Shanghai. The proposed scheme can reduce vehicle delay by 24.58%, increase traffic capacity by 17.09% and reduce tail gas emission by 34.68% in peak period compared with before improvement. In low peak period, the delay, exhaust emission and traffic capacity are reduced by 49.04%, 41.68% and 17.09% compared with those before improvement. Using this optimization scheme can improve vehicle delay to a certain extent, improve vehicle traffic capacity and reduce pollution caused by exhaust emission to the environment. It also verifies the validity of the model and provides some theoretical basis for setting the signal timing for shifted left-turn lane intersections.

Driving Assistance System with Lane Change Detection

In this study, a simple technology for a self-driving system called “driver assistance system” is developed based on embedded image identification. The system consists of a camera, a Raspberry Pi board, and OpenCV. The camera is used to capture lane images, and the image noise is overcome through color space conversion, grayscale, Otsu thresholding, binarization, erosion, and dilation. Subsequently, two horizontal lines parallel to the X-axis with a fixed range and interval are used to detect left and right lane lines. The intersection points between the left and right lane lines and the two horizontal lines can be obtained, and can be used to calculate the slopes of the left and right lanes. Finally, the slope change of the left and right lanes and the offset of the lane intersection are determined to detect the deviation. When the angle of lanes changes drastically, the driver receives a deviation warning. The results of this study suggest that the proposed algorithm is 1.96 times faster than the conventional algorithm.

Multi-Intersection Control with Deep Reinforcement Learning and Ring-and-Barrier Controllers

This paper discusses a machine-learning traffic signal control method. A full-scale corridor is analyzed and the transferability of using a model pre-trained on a single intersection is examined. Two controller designs are explored, a simple two-phase design and a full ring-and-barrier style controller. The full ring-and-barrier controller adapts many of the key features present in traditional controllers, such as protected-permissive left turns, so that they can be used in the reinforcement learning (RL) paradigm. This study is the first to propose a method that uses deep reinforcement learning (DRL) to implement a full ring-and-barrier style controller. The study also examines the feasibility of using transfer learning to pre-train a model on a single intersection and then fine-tune it for application in a complete environment. Training is done on a simple four lane intersection and the pre-trained model is then transferred for fine-tuning to six controllers operating on a corridor modeled with field data obtained for University Avenue in Waterloo, Ontario, Canada. The performance of the fully trained model is then compared with the existing signal plans in relation to the average delay and average queue length. Application of the ring-and-barrier design to this corridor was found to reduce delays by at least 5% and average queue lengths at intersections by 27%.

User-Rated Comfort and Preference of Separated Bike Lane Intersection Designs

Improved bicycle infrastructure has become increasingly common in the United States as cities seek to attract new riders, including the demographic who do not feel comfortable riding with motor vehicle traffic. A key tool in designing low-stress networks is the use of separated or protected bicycle lanes, and intersections are the critical links. This paper presents an analysis of the perceived level of comfort of current and potential bicyclists from 277 survey respondents who rated 26 first-person video clips of a bicyclist riding through mixing zones, lateral shifts, bend-in, bend-out, and protected intersection designs. A total of 7,166 ratings were obtained from surveys conducted at four locations in Oregon, Minnesota, and Maryland, including urban and suburban locations. Survey respondents were categorized into four groups based on their response to attitudes and bicycling behavior by cluster analysis. Descriptive analysis and regression modeling results find that designs that minimize interactions with motor vehicles, such as fully separated signal phases and protected intersections, are rated as most comfortable (72% of respondents rated them as very comfortable or somewhat comfortable). Mean comfort drops off significantly for other designs and interactions with turning vehicles result in lower comfort ratings though there are differences for each design. Importantly, as the exposure distance, measured as the distance a person on a bicycle is exposed to traffic, increases the comfort decreases.

Optimal Access Management for Cooperative Intersection Control

This paper presents an intersection access management methodology that optimizes the crossing sequence of an automated intersection, where the low-level vehicle control is performed by a cooperative intersection control (CIC) strategy. While the CIC regulates the safe and efficient relative motion of vehicles in the intersection, a high-level hybrid queuing model is proposed to describe the dynamics of the vehicle queues associated to each intersection lane. This model, including constraints, is used to design an optimal access management approach based on the model predictive control that minimizes the time that the vehicles spend within the intersection, thereby optimizing the traffic throughput of the intersection. The performance of this methodology is studied by means of two representative examples. The impact of the design parameters of the optimal access management approach is shown for a T-intersection case study. Moreover, using a real-life five lane intersection case study, the proposed approach is compared to a vehicle-actuated traffic light approach, and a first come first served approach. The comparison shows the benefits of the automated optimal serving of vehicles from different lanes.

Perception of Safety and Liking Associated to the Colour Intervention of Bike Lanes: Contribution from the Behavioural Sciences to Urban Design and Wellbeing.

The perception of colour and its subjective effects are key issues to designing safe and enjoyable bike lanes. This paper addresses the relationship between the colours of bike lane interventions—in particular pavement painting and intersection design—and the subjective evaluation of liking, visual saliency, and perceived safety related to such an intervention. Utilising images of three real bike lane intersections modified by software to change their colour (five in total), this study recruited 538 participants to assess their perception of all fifteen colour-design combinations. A multivariate analysis of covariance (MANCOVA) with the Bonferroni post hoc test was performed to assess the effect of the main conditions (colour and design) on the dependent variables (liking towards the intervention, level of visual saliency of the intersection, and perceived safety of the bike lane). The results showed that the colour red was more positively associated to the outcome variables, followed by yellow and blue. Additionally, it was observed that the effect of colour widely outweighs the effect of design, suggesting that the right choice and use of colour would increase the effectiveness on bike-lanes pavement interventions. Limitations and future directions are discussed.

Safety Analysis of Continuous Green Through Lane Intersections

This paper examines safety characteristics of continuous green through lane (CGTL) intersections using paired-t test and ordered probit (OP) statistical models. The results suggest that there is a significant difference between the proportions of sideswipe crashes in the CGTL direction compared with the opposite direction. However, the results did not suggest a significant difference between the proportions of rear-end and right-angle crashes for the CGTL and normal directions. The results further suggest that angle crashes and crashes involving lane changing maneuvers are significantly more severe compared with rear-end crashes.

Single-point Control Strategy for Real-time Online Transit Priority

AbstractBased on optimal control of real-time online transit priority, the system analyzes the synergy of control strategy, the synergy of vehicle operation, and the synergy of all kinds of detection information of the transit lane intersection. The detection basis of transit priority and phase optimization method are designed, and the single point control mode of real-time online transit is established based on the status of bus operation and the time allocation algorithms of refined control strategy. Finally, a system simulation and an evaluation using VISSIM simulation software are conducted, and the results show that the optimization strategy achieved transit priority and a smooth and orderly traffic at intersection.

Utilisation d’un modèle de régression de Poisson pour l’analyse multivariée des données issues de l’enquête nationale de prévalence des infections nosocomiales de 2006 en cancérologie

While cycling benefits individuals and society, cyclists are vulnerable road users, and their safety concerns arouse more macro-level spatial crash studies. Our study intends to investigate the spatial effects of population, land use, and bicycle lane infrastructures on bicycle crashes. This was done by developing a semi-parametric Geographically Weighted Poisson Regression (sGWPR) model which deals with the issue of spatial correlation and spatial non-stationarity simultaneously. It is a model that combines both constant and geographically varying parameters. To determine which parameter is fixed or non-stationary, previous studies suggest monitoring the Akaike Information Criterion (AICc). Yet, relying only on AICc might bury some spatial associations. So, in this study, we propose a Linear Model of Coregionalization (LMC) to assist the decision. Here, we use bicycle crash data across the metropolitan area of Greater Melbourne to establish sGWPR models suggested by AICc and LMC, respectively. Comparing the two sGWPR models, we found the sGWPR model under LMC results performs as well as sGWPR models suggested by AICc from the AICc perspective, and a 22.5% improvement in the mean squared error (MSE). It also uncovers more details about the spatial relationship between bicycle crashes and bicycle lane intersection density (BLID), an effect not suggested under AICc results. The parameters of BLID, a new measurement of bicycle lane facilities proposed by us, vary over space across analysis zones in Greater Melbourne.

Conflict Analysis for Double Left-Turn Lanes with Protected-Plus-Permitted Signal Phases

A conflict study evaluated double left-turn lanes with protected-plus-permitted signal phasing. The data collection team observed traffic behavior at four intersections in the metro Atlanta region. Included in the data set are three intersections operating under protected-plus-permitted signal phasing and a fourth intersection with a before and after examination of a protected-plus-permitted signal phase changed to protected-only phasing. The authors calculated the traffic rates for five conflict types and one traffic event unique to double left-turn movements. A statistically significant decrease in traffic conflicts was identified for the before and after comparison site. The study also identifies unique intersection geometry and traffic volumes at each site and compares traffic conflicts associated with the features. The results generally show that the enhanced capacity of double left-turn lane intersections operating under protected-plus-permitted signal phasing may occur at the expense of the safety of the traveling public.