The advent of autonomous vehicles (AVs) is expected to transform the current transportation system into a safe and reliable one. The existing infrastructures, operational criteria, and design method were developed to meet the requirements of human drivers. However, previous studies have shown that in the traditional horizontal and vertical combined design methods, where the two-dimensional alignment elements change, there are varying changes in curvature and torsion, which cause the continuous degradation of the spatial curve and torsion. This continuous degradation will inevitably cause changes in the trajectory of Autonomous Vehicles (AVs), thereby affecting driving safety. Therefore, studying the characteristics of autonomous vehicles trajectory deviation has theoretical significance for optimizing highway alignment safety design. Driving simulation tests were performed by using PreScan and Simulink to calibrate the lateral deviation. A machine learning approach called the Gradient Boosting Decision Tree (GBDT) algorithm was implemented to build a model and express the relationship between space alignment parameters and lane deviation. The results showed that the AV’s driving trajectory is significantly affected by the space alignment factors when the vehicle is driving in the inner lane, the downhill section, and the left-turn section. These findings will provide a novel perspective for road safety research based on autonomous vehicle driving trajectories.
Existing signal control systems for urban traffic are usually based on traffic flow data from fixed location detectors. Because of rapid advances in emerging vehicular communication, connected vehicle (CV)-based signal control demonstrates significant improvements over existing conventional signal control systems. Though various CV-based signal control systems have been investigated in the past decades, these approaches still have many issues and drawbacks to overcome. We summarize typical components and structures of these existing CV-based urban traffic signal control systems and digest several important issues from the summarized vital concepts. Last, future research directions are discussed with some suggestions. We hope this survey can facilitate the connected and automated vehicle and transportation research community to efficiently approach next-generation urban traffic signal control methods and systems.
Lane change prediction is critical for crash avoidance but challenging as it requires the understanding of the instantaneous driving environment. With cutting-edge artificial intelligence and sensing technologies, autonomous vehicles (AVs) are expected to have exceptional perception systems to capture instantaneously their driving environments for predicting lane changes. By exploring the Waymo open motion dataset, this study proposes a framework to explore autonomous driving data and investigate lane change behaviors. In the framework, this study develops a Long Short-Term Memory (LSTM) model to predict lane changing behaviors. The concept of Vehicle Operating Space (VOS) is introduced to quantify a vehicle's instantaneous driving environment as an important indicator used to predict vehicle lane changes. To examine the robustness of the model, a series of sensitivity analysis are conducted by varying the feature selection, prediction horizon, and training data balancing ratios. The test results show that including VOS into modeling can speed up the loss decay in the training process and lead to higher accuracy and recall for predicting lane-change behaviors. This study offers an example along with a methodological framework for transportation researchers to use emerging autonomous driving data to investigate driving behaviors and traffic environments.
In the future connected vehicle environment, the information of multiple vehicles ahead can be readily collected in real-time, such as the velocity or headway, which provides more opportunities for information exchange and cooperative control. Meanwhile, gyroidal roads are one of the fundamental road patterns prevalent in mountainous areas. To effectively control the system, it is therefore significant to explore the evolution mechanism of traffic flow on gyroidal roads under a connected vehicle environment. In this paper, we present a new continuum model with the average velocity of multiple vehicles ahead on gyroidal roads. The stability criterion and KdV-Burger equation are deduced via linear and nonlinear stability analysis, respectively. Solving the above KdV-Burger equation yields the density wave solution, which explores the formation and propagation property of traffic jams near the neutral stability curve. Simulation examples verify that the model can reproduce complex phenomena, such as shock waves and rarefaction waves. The analysis of the local cluster effect shows that the number of vehicles ahead and the radius information, and the slope information of gyroidal roads can exert a great influence on traffic jams. The effect of the first and second terms are positive, while the last term is negative.
During both daily operation and emergency evacuation, the corners of walking facilities in subway stations play an important role in efficient circulation. However, the effectiveness of the corner is difficult to assess. In this paper, a method of passenger gathering and scattering analysis based on queueing models was proposed to investigate the corner performance in subway stations. Firstly, we constructed a set of state spaces of passenger flow according to passenger density and proposed the state transition model of passenger flow. Moreover, the model of passenger flow blocking and unblocking probability were also presented. Then, to illustrate the validity of the method and model, several passenger gathering-scattering scenarios and were simulated to verify the influence of passenger distribution and facility width on passenger walking, and the blocking probability, throughput, and expected time were also analyzed under various widths of the target corridor and arrival rates. Results showed that the proposed model can reproduce the trend of walking parameters changing and the self-organizing phenomenon of 'faster is lower'. With the increase of arrival rates of passengers, walking speeds of passengers decrease and the expected walking time is prolonged, and the blocking probability sharply increased when the arrival rate exceeded 7 peds/s. In addition, with change of width of the target facility, efficiency of capacity of walking circulation facility fluctuated. With the width of the target corridor enlarged by 10%, the steady state of passenger flow was less crowded. Therefore, corridor width is critical to the circulation efficiency of passengers in subway stations. The conclusions will help to develop reasonable passenger flow control plans to ease the jam and keep passengers walking safely.
Traffic signal control (TSC) systems are one essential component in intelligent transport systems. However, relevant studies are usually independent of the urban traffic simulation environment, collaborative TSC algorithms and traffic signal communication. In this paper, we propose (1) an integrated and cooperative Internet-of-Things architecture, namely General City Traffic Computing System (GCTCS), which simultaneously leverages an urban traffic simulation environment, TSC algorithms, and traffic signal communication; and (2) a general multi-agent reinforcement learning algorithm, namely General-MARL, considering cooperation and communication between traffic lights for multi-intersection TSC. In experiments, we demonstrate that the integrated and cooperative architecture of GCTCS is much closer to the real-life traffic environment. The General-MARL increases the average movement speed of vehicles in traffic by 23.2% while decreases the network latency by 11.7%.
