Journal of Advanced Transportation最新文献

Travel Time Reliability (TTR) plays a pivotal role in commuting. Nevertheless, existing measurement methods are not specifically designed for commuting scenarios, and their direct application to assess TTR for commuting may yield results incongruent with actual commuting conditions, as they overly rely on measures like mean and percentiles. Drawing on the cyclical characteristics of commuting, the study has established a TTR measurement model based on information entropy and standard deviation, tailored to individual commuters. By selecting commuting data from extensive travel datasets and applying both this model and conventional measurement methods, the focus is on quantitatively analyzing TTR for metro commuters and car commuters under various feature conditions, with a particular emphasis on commuting to work. The objective is to verify the feasibility and advantages of the proposed model. The research indicates that, compared to typical measurement methods, this model more accurately reflects TTR for commuting purposes. The results underscore a significantly superior TTR for metro commuters over car commuters. Distance and departure time exert a substantial impact on the TTR of car commuters, while distance and transfer times moderately influence the TTR of metro commuters. These findings serve as a crucial foundation for enhancing the quality of commuting experiences.

Vehicle interactions with different driving behaviors in mixed traffic conditions, in which autonomous vehicles (AVs) and manual vehicles (MVs) coexist, would result in unstable traffic flow leading to a potential crash risk. A proactive traffic management strategy is required to enhance both safety and mobility by preventing hazardous events in connected environments. The purpose of this study is to develop a Proactive Lane-changE Assistant Strategy for Automated iNnovative Transportation (PLEASANT) to enhance traffic safety. PLEASANT is a strategy for providing lane change assistance information to vehicles approaching risky situations such as crashes, broken vehicles, and upcoming hazardous obstacles. In addition, this study proposed a comprehensive simulation framework that incorporates driving simulation and traffic simulation to evaluate the performance of PLEASANT when dealing with mixed traffic. To characterize vehicle interactions between AVs and MVs, this study analyzes driving behavior in mixed car-following situations based on multiagent driving simulation (MADS), which is able to synchronize the space and time domains on the road by connecting two driving simulators. The characteristics of vehicle interactions between AVs and MVs were incorporated into microscopic traffic simulations. The effectiveness of PLEASANT was evaluated based on the crash potential index from the perspective of safety. The results showed that PLEASANT was capable of enhancing traffic safety by approximately 21%. PLEASANT is expected to be useful as a novel management strategy for enhancing traffic safety in mixed-traffic environments.

Accurate and timely forecasting of critical components is pivotal in intelligent transportation systems and traffic management, crucially mitigating congestion and enhancing safety. This paper aims to comprehensively review deep learning algorithms and classical models employed in traffic forecasting. Spanning diverse traffic datasets, the study encompasses various scenarios, offering a nuanced understanding of traffic forecasting methods. Reviewing 111 seminal research works since the 1980s, encompassing both deep learning and classical models, the paper begins by detailing the data sources utilized in transportation systems. Subsequently, it delves into the theoretical underpinnings of prevalent deep learning algorithms and classical models prevalent in traffic forecasting. Furthermore, it investigates the application of these algorithms and models in forecasting key traffic characteristics, informed by their utility in transport and traffic analyses. Finally, the study elucidates the merits and drawbacks of proposed models through applied research in traffic forecasting. Findings indicate that while deep learning algorithms and classic models serve as valuable tools, their suitability varies across contexts, necessitating careful consideration in future studies. The study underscores research opportunities in road traffic forecasting, providing a comprehensive guide for future endeavors in this domain.

The ability to change lanes safely, efficiently, and comfortably is an important prerequisite for the application of Connected-Automated Vehicles (CAVs). Based on the five-order polynomial trajectory planning for CAVs, the 2D-Action Asynchronous Lane Change (AALC) trajectory planning model is constructed by further considering the longitudinal and lateral driving action execution time parameters. This is done to improve the applicability of the lane change model and increase the CAV lane change success rate. The continuous collision space algorithm is constructed by determining the continuity condition of collision trajectory parameter solution space through the monotonicity of trajectory curve parameters and collision form classification. AALC trajectory safety judgment is realized through this algorithm. A cooperative lane change trajectory evaluation objective function is constructed, considering multivehicle comfort and efficiency. Finally, the AALC model is solved in the continuous collision space according to the optimal objective function, and the lane change is divided into free, cooperative, and refused according to the optimization. The results indicate that the AALC model achieves the transfer of collision space between lanes through asynchronous process of behavior execution time window, thereby reducing the possibility of vehicle collision. The AALC model reduces the degree of change of cooperative lane change parameters by asynchronous process of behavior, increasing the number of free lane change trajectories by about 17%, effectively reducing the occurrence of lane change refusal, improving the successful rate of lane change, and enhancing the overall evaluation of the lane change. The AALC model realizes the reallocation of collision space between different lanes through asynchronous process, making it more suitable for environments with large differences in vehicle gaps such as ramp merging. The collision-based trajectory optimization algorithm can quickly obtain the corresponding safety space and optimal trajectory. The maximum calculation time for a single cooperative lane change is 0.073 s, thus enabling real-time trajectory planning.

Safety and efficiency of autonomous driving behavior are a tradeoff. Behaviors that are too focused on safety can reduce road operation efficiency, while those that are too efficient can compromise passengers’ safety beyond their tolerance. Therefore, it is important to understand people’s characteristics and maintain a balance between safety and efficiency. Overtaking, which involves passing the preceding vehicle and improving road capacity, requires complex interaction as collisions with opposing vehicles must be avoided on a two-lane, two-way road. Overtaking to increase road capacity can induce unnecessary deceleration in oncoming vehicles, harming oncoming traffic flow. To address these concerns, a diverse dataset of natural overtaking behavior is a priority. We conduct experiments using a network connection between two multiagent driving simulators to collect a human behavior-based overtaking dataset and develop driving behavior models engaged in overtaking situations using the Extra Trees model. The behavior models are embedded in microsimulation to generate human behavior-based datasets under different conditions using a dynamic link library and component object model interfaces. To understand the interaction in an overtaking scenario by the generated datasets, we used a K-means clustering technique to analyze the different reaction behaviors between the oncoming and overtaking vehicles. The threshold for achieving a balanced combination of safety and efficiency is established using XGboost. Finally, safe overtaking behavior is analyzed using a combination of the classified driving styles and thresholds. The results show that the overtaking vehicle can safely start overtaking without endangering oncoming vehicles when both speed and distance conditions are met simultaneously; the speed is lower than 44.29 km/h and it is 407 m away from oncoming vehicles.

This paper proposes an optimization model for the train operation scheme of the Airport Express Line (AEL) based on the expected arrival time of passengers by the introduction of the train departure time to cope with the time-dependent passenger flow and provide better prompt train service according to passengers’ demand. Considering factors such as train sections, station arrangement, passenger capacity, departure time windows, passenger flow conservation, and boarding and disembarkation processes, this paper also aims to find the optimal combination of the passengers’ total travel time and the train operation cost. A set of alternative train options is introduced to simplify the model and convert integer variables related to train pairs into 0-1 variables. The elaborately designed simulated annealing algorithm mainly focuses on the key elements of strategies like initial solution generation, neighborhood solution construction, and the allocation of passenger flows, tailored to the model’s unique features and the time-dependent passenger flow. Neighborhood solution strategies include the increase or haut of train operations and the adjustment of the number of stops, which refines the solution space and boosts the process efficiency of the heuristic algorithm. Additionally, the model and algorithm proposed in this paper are practiced during the peak hour of Nanjing Metro Line S1 for empirical validation. The research findings demonstrate that the optimized train operation scheme is better synchronized with the fluctuating number of time-dependent passenger flows and exhibits notable improvement in computational efficiency and convergence.

The advent of automated vehicles (AVs) and connected automated vehicles (CAVs) creates significant uncertainties in infrastructure planning due to many unknowns, such as performance variability and user adaptation. As technologies are still emerging with low market penetration, limited observational data hinder validation and escalate prediction uncertainty. This study addresses these gaps by employing diverse vehicle models and wide performance ranges in Aimsun microsimulations. It involved three AV/CAV car-following models with the default Gipps human-driven vehicle (HDV) model. We evaluated the performance of a mixed fleet in three well-calibrated real-world corridor models, including two highways and one freeway. Vehicle parameters in Aimsun are commonly drawn from a corresponding truncated normal distribution with fixed mean, min, and max values. However, to account for future uncertainty and heterogeneity, our AV/CAV models were given truncated normal distributions with variable means for important parameters to incorporate broader performance ranges. The variable means are drawn from intervals with uniform probability, and some of the interval extended below HDV values to account for scenarios where riders opt for smoother rides at the cost of traffic flow. Recognizing that precise future prediction is unattainable, we aimed to establish traffic performance boundaries that define best- and worst-case scenarios in a mixed-fleet environment. Enumerating all possible combinations is impractical, so a refined optimization algorithm was employed to expedite solution discovery. Our findings suggest that AVs/CAVs, even with conservative performance parameters, can improve traffic operations by reducing peak delays and enhancing travel time reliability. Freeways benefited more than arterial roads, especially with full CAV penetration, although the authors speculate this could create bottlenecks at off-ramps. The added capacity may induce traffic demand that is difficult to estimate. Instead, we conducted a demand sensitivity analysis to gauge additional traffic accommodation without worsening delays. Compared to point predictions, establishing the range of possibilities can help us future-proof infrastructure by considering uncertainties in the planning process. Our framework can be adopted to test alternative models or scenarios as more data becomes available.

More highway built in the mountains in recent years, the driving risk in the tunnel group is becoming a new issue. This paper analyzed the driving risk in the mountain highway tunnel group from the perspective of visual load. Based on vehicle test in the Pengshui-Xiantang tunnel group in China, the evolution characteristics of MTPA were quantitatively analyzed, and the random forest model was constructed to discuss the effect factors of the maximum transient velocity value of the pupil area (MTPA) in different sections. The results are as follows: (1) The MTPA frequently presents a tendency of steep rise and fall in the tunnel group. MTPA in the second tunnel is significantly higher than the first tunnel. (2) The mountain tunnel group can be divided into nine sections; the velocity, design luminance, measured luminance, and location have different effects on MTPA in each section. Due to the complex terrain conditions, the location has a more significant impact on MTPA in the second tunnel. (3) The first tunnel entrance, the first tunnel exit to the second tunnel entrance, and the second tunnel exit are the areas with more significant pressure on drivers in the tunnel group. The visual load of drivers in the exit section of the last tunnel is the greatest. The driving risk reduction recommendations include improving the transition lighting design of the second tunnel, clarifying the tunnel group identification, and adding safety features at the tunnel connection section, in order to clarify the driver’s expectations and reduce the fear of the unknown mountain environment.

The Dedicated Bus Lane (DBL) is often adopted to ensure transit priority. This is because transit priority can effectively mitigate congestion at the signalized intersection. However, the DBL would cause heavy sacrifices from general vehicles when the frequency of buses is low. To address this issue, many studies were proposed to reduce general vehicles’ sacrifice by converting DBLs into Bus-Priority Lanes (BPLs). Such BPLs can be intermittently open to general vehicles. However, these studies cannot ensure absolute transit priority when general vehicles access BPLs. With the advance of Connected Automated Vehicle (CAV) technology, this paper proposes a Trajectory-Based Control (TBC) method for connected automated traffic to approach signalized intersections considering absolute transit priority. A TBC controller is designed to control general vehicles’ trajectories to access BPLs without interference with buses. The TBC controller can balance the multiple cost factors and ensure absolute bus priority. The proposed TBC controller is evaluated against the noncontrol baseline and the state-of-the-art TBC. Sensitivity analysis is conducted under four different congestion levels. The results demonstrate that the proposed TBC method outperforms and has benefits in improving throughputs and fuel efficiency and reducing delays.

Traffic accident data-based portrait plays a vital role in accident cause investigation, relationship reasoning, prevention, and control. The traffic accident data tend to be multisourced with increasingly hidden and complicated accident relationships. The existing reported research focus more on traffic drivers’ measurement of penalty, the relationship among drivers, cars, and dates, etc. How to use multisource data based on deep learning, especially based on the Chinese recent unstructured data and structured data to establish accident portrait for individual and groups of accident drivers, still lacks. Moreover, how to perform multisource accident data label extraction, identity, and relationship extraction are still challenging problems. This paper proposes a multisource accident datasets-driven deep learning-based traffic accident portrait method. Our multisource accident datasets-driven deep learning model is composed of the following three submodels: (1) the structured data accident model using our accident feature-driven bidirectional long short-term memory (Bi-LSTM) and accident feature-driven bidirectional conditional random field (Bi-CRF) model to extract labels, (2) the unstructured traffic accident data model using our accident feature-driven piecewise convolutional neural network (PCNN) model to identify the extracted labels, and (3) the semistructured traffic accident data processing model. Moreover, to solve the problem of how to construct hidden relationship among the multisource accident data, a multisource accident data visualization method based on traffic accident knowledge graph where the accident relational inference algorithm is to complete the hidden relationship between traffic accident data labels is used and then data are visualized using the traffic accident knowledge graph. This paper uses the NER dataset of the People’s Daily and a manually labeled dataset to test the Bi-LSTM + Bi-CRF model, and it acquires the highest scores of 0.9562 and 0.9779 compared with several other models. This paper uses the DuIE dataset and a manually labeled dataset to test the PCNN model, and it acquires the highest scores of 0.9674 and 0.9108 compared with several other models. Experiments verified our model’s merits than other models in regards to accident label extraction, accident identity identification, and accident relationship extraction.