In recent decades, studies on short-term traffic speed forecasting of the large-scale road are a new challenge for researchers and engineers. Especially based on deep learning neural networks, studies on short-term traffic forecasting have achieved mush-room growth. This study proposes a stacked Bidirectional Gated Recurrent Unit neural network model to predict the traffic speed of the expressway over different estimation time intervals in an effective manner. By building a multiscale-grid model, it can take less time to derive a set of key traffic parameters of different scales to predict traffic speed of the various-scale road. The speed prediction of small-scale sections can cover more detailed road spatial features preparing for Vehicle Navigation System, and the speed prediction of large-scale sections can establish the real-time traffic control strategies. In order to validate the effectiveness of the proposed model, we use the floating car data, with an updating frequency of 1 minute from the urban freeway of Beijing, for model training and testing. The experimental results show that the stacked BiGRU network with the multiscale-grid model enables to capture the spatial-temporal characteristics of traffic speed efficiently. Furthermore, the BiGRU with two layers (BiGRU-2L) outperforms benchmark models in the prediction of the traffic speed, which presents a significant advantage in reducing the overfitting problem, decreasing the excessive time-consuming and improving the effective use of limited computation resources.

Urban road intersections play an important role in deciding the total travel time and the overall travel efficiency. In this paper, an innovative traffic grid model has been proposed, which evaluates and diagnoses the traffic status and the time delay at intersections across whole urban road networks. This method is grounded on a massive amount of floating car data sampled at a rate of 3 s, and it is composed of three major parts. (1) A grid model is built to transform intersections into discrete cells, and the floating car data are matched to the grids through a simple assignment process. (2) Based on the grid model, a set of key traffic parameters (e.g., the total time delay of all the directions of the intersection and the average speed of each direction) is derived. (3) Using these parameters, intersections are evaluated and the ones with the longest traffic delays are identified. The obtained intersections are further examined in terms of the traffic flow ratio and the green time ratio as well as the difference between these two variables. Using the central area of Beijing as the case study, the potential and feasibility of the proposed method are demonstrated and the unreasonable signal timing phases are detected. The developed method can be easily transferred to other cities, making it a useful and practical tool for traffic managers to evaluate and diagnose urban signal intersections as well as to design optimal measures for reducing traffic delay and increase operation efficiency at the intersections.

Adaptive signal control is a method that dynamically adjusts signal phases based on real-time traffic conditions, aiming to improve the efficiency of intersection light control. However, in practical applications, obtaining complete traffic spatiotemporal states at intersections is challenging given the limited data sources. To address this issue, this paper presents a novel deep reinforcement learning model, namely 3DQN-PSTER, which combines Dueling Deep Q Network, Double Deep Q Network, and Priority SumTree Experience Replay technology. This model effectively extracts traffic states from sampled floating car data (FCD) and achieves optimal timing schemes. To evaluate its performance, the proposed model is tested in a simulated intersection environment using actual intersection data. The model interacts with the environment by adjusting signal phases, updating traffic states, and obtaining optimal timing schemes. Simulation results demonstrate that the proposed model exhibits higher convergence efficiency and outperforms benchmark models. When applied, the reinforcement learning single control (RLSC) based on the 3DQN-PSTER model outperforms fixed-time signal control schemes and actuated signal control (ASC) schemes. Even in scenarios with low penetration ratios of FCD, RLSC still significantly outperforms ASC. Therefore, the signal timing optimization method proposed in this paper could greatly enhance intersection operation efficiency in both ideal overall data environments and partial states.

Urban road intersection bottleneck has become an important factor in causing traffic delay and restricting traffic efficiency. It is essential to explore the prediction of the operating performance at intersections in real-time and formulate corresponding strategies to alleviate intersection delay. However, because of the sophisticated intersection traffic condition, it is difficult to capture the intersection traffic Spatio-temporal features by the traditional data and prediction methods. The development of big data technology and the deep learning model provides us a good chance to address this challenge. Therefore, this paper proposes a multi-task fusion deep learning (MFDL) model based on massive floating car data to effectively predict the passing time and speed at intersections over different estimation time granularity. Moreover, the grid model and the fuzzy C-means (FCM) clustering method are developed to identify the intersection area and derive a set of key Spatio-temporal traffic parameters from floating car data. In order to validate the effectiveness of the proposed model, the floating car data from ten intersections of Beijing with a sampling rate of 3s are adopted for the training and test process. The experiment result shows that the MFDL model enables us to capture the Spatio-temporal and topology feature of the traffic state efficiently. Compared with the traditional prediction method, the proposed model has the best prediction performance. The interplay between these two targeted prediction variables can significantly improve prediction accuracy and efficiency. Thereby, this method predicts the intersection operation performance in real-time and can provide valuable insights for traffic managers to improve the intersection’s operation efficiency.

To address the issue of traffic accidents caused by livestock crossing roads on grassland highways, this paper proposes an adaptive cruise control method for unmanned aerial vehicles (UAVs) based on an ensemble Q-network and a Soft Actor-Critic (SAC) with delayed policy updates, namely the ED-SAC algorithm. Building upon the standard SAC framework, this method introduces multiple independent Critic networks to form an ensemble Q-network, and employs a random subset minimization strategy during the calculation of target Q-values to mitigate policy bias resulting from overestimated values; simultaneously, a delayed policy update mechanism decouples the optimization processes of the Actor and Critic networks, thereby enhancing training stability and control robustness. Using the PyBullet simulation platform, this paper constructs a UAV inspection scenario on grassland roads and designs three typical test tasks: infinite loop, grid scan and spiral trajectories, to conduct comparative validation of the PPO, TD3, SAC and ED-SAC algorithms. Experimental results demonstrate that, under disturbance-free conditions, ED-SAC achieves the highest mission success rate and the lowest tracking error across all three trajectory scenarios, with an average tracking error as low as 0.27 m and a mission success rate as high as 98.7%. Under continuous random external disturbances, ED-SAC still maintains high trajectory tracking accuracy and attitude control stability, with a mission success rate reaching up to 96.2%. The results demonstrate that the proposed ED-SAC algorithm can effectively enhance the trajectory tracking accuracy, training stability and anti-disturbance capability of UAVs in complex grassland road inspection scenarios, providing a reliable intelligent control method for active grassland road inspection and traffic safety early warning.