Recent scholars have developed a number of stochastic car-following models that have successfully captured driver behavior uncertainties and reproduced stochastic traffic oscillation propagation. Whereas elegant frequency domain analytical methods are available for stability analysis of classic deterministic linear car-following models, there lacks an analytical method for quantifying the stability performance of their peer stochastic models and theoretically proving oscillation features observed in the real world. To fill this methodological gap, this study proposes a novel analytical method that measures traffic oscillation magnitudes and reveals oscillation characteristics of stochastic linear car-following models. We investigate a general class of stochastic linear car-following models that contain a linear car-following model and a stochastic noise term. Based on frequency domain analysis tools (e.g., Z-transform) and stochastic process theories, we propose analytical formulations for quantifying the expected speed variances of a stream of vehicles following one another according to one such stochastic car-following model, where the lead vehicle is subject to certain random perturbations. Our analysis on the homogeneous case (where all vehicles are identical) reveals two significant phenomena consistent with recent observations of traffic oscillation growth patterns from field experimental data: A linear stochastic car-following model with common parameter settings yields (i) concave growth of the speed oscillation magnitudes and (ii) reduction of oscillation frequency as oscillation propagates upstream. Numerical studies verify the universal soundness of the proposed analytical approach for both homogeneous and heterogeneous traffic scenarios, and both asymptotically stable and unstable underlying systems, as well as draw insights into traffic oscillation properties of a number of commonly used car-following models. Overall, the proposed method, as a stochastic peer, complements the traditional frequency-domain analysis method for deterministic car-following models and can be potentially used to investigate stability responses and mitigate traffic oscillation for various car-following behaviors with stochastic components.

Self-driving technology companies and the research community are accelerating the pace of use of machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews the current state of the art in mMP, with an exclusive focus on its impact on traffic congestion. The paper identifies the availability of congestion scenarios in current datasets, and summarizes the required features for training mMP. For learning methods, the major methods in both imitation learning and non-imitation learning are surveyed. The emerging technologies adopted by some leading AV companies, such as Tesla, Waymo, and Comma.ai, are also highlighted. It is found that: (i) the AV industry has been mostly focusing on the long tail problem related to safety and has overlooked the impact on traffic congestion, (ii) the current public self-driving datasets have not included enough congestion scenarios, and mostly lack the necessary input features/output labels to train mMP, and (iii) although the reinforcement learning approach can integrate congestion mitigation into the learning goal, the major mMP method adopted by industry is still behavior cloning, whose capability to learn a congestion-mitigating mMP remains to be seen. Based on the review, the study identifies the research gaps in current mMP development. Some suggestions for congestion mitigation for future mMP studies are proposed: (i) enrich data collection to facilitate the congestion learning, (ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and (iii) integrate domain knowledge from the traditional car-following theory to improve the string stability of mMP.

Numerous fast heuristic algorithms, including shooting heuristics (SH), have been developed for real-time trajectory optimization, although their optimality has not yet been quantified. This paper compares the performance between fast heuristics and exact optimization models. We investigate a core trajectory optimization problem as a building block for numerous trajectory optimization problems, i.e., guiding movements of connected automated vehicles on a one-lane highway when the arrival and departure times and velocity are given. To apply the SH algorithm to this problem, we adapt it to a fast-simplified shooting heuristic (FSSH) model to solve the trajectory smoothing problems with different arrival and departure velocities. An exact trajectory optimization (ETO) model is formulated that takes the vehicle position and velocity as the decision variables, and the fuel consumption and driving comfort as the objective function. The constraints of the model are based on the limits and safety of the vehicle dynamics between consecutive vehicles. We demonstrate the convexity of the ETO objective function, ensuring the solvability of the ETO model at the true optimum using gradient descent algorithms supplied by the MATLAB optimization toolbox. Six groups of numerical experiments using different input parameters and one experiment using real Next Generation Simulation (NGSIM) data are conducted. ETO can improve the objective values by a few to tens of percentage points. However, FSSH achieves a greater solution efficiency with an average solution time of less than 0.1 s compared to ~450 s for ETO.

Intersections in the urban network are potential sources of traffic flow inefficiency. Existing intersection control mostly adopts the “cross” flow pattern model, while the use of the roundabout circular flow pattern is rather sparse. Connected and autonomous vehicle (CAV) technologies can enable roundabouts to better compete with traditional intersection designs in terms of performance. This study proposes a roundabout control strategy for CAVs to enhance intersection performance while ensuring vehicle safety. A hierarchical framework is developed to decouple the flow-level performance objective and vehicle-level safety constraints to achieve computational tractability for real-time applications. It entails developing a roundabout flow control model to optimize merge-in flows, a merge-in decision model to generate vehicle passing sequence from the optimal flows, and a virtual platoon control model to achieve safe and stable vehicle operations in a circular roundabout platoon. The performance of the proposed roundabout control strategy is illustrated through numerical studies and compared to existing intersection control methods. Its stability and safety characteristics are also demonstrated.

Accurate vehicle trajectory prediction enables safe, comfortable, and optimal proactive motion planning for connected and autonomous vehicles (CAVs). Because of rapid advances in learning techniques and increasing access to massive amounts of data, deep learning techniques have been applied to predict vehicle trajectories, especially the long short-term memory (LSTM) model. However, the accurate prediction of vehicle trajectories for congested urban traffic remains problematic, as existing LSTM models do not perform well. To address this gap, this paper proposes to leverage an emerging deep learning technique—transformer—and utilizes a recently released dataset (pNEUMA) for predicting vehicle trajectories in congested urban traffic. The proposed transformer model uses the self-attention mechanism, which helps to identify dependencies within the model inputs, to systematically determine the impacts of vehicular interactions on the target vehicle’s future trajectory. The pNEUMA dataset, which provides drone-based large-scale data of congested urban traffic, is processed to fit a typical trajectory prediction scenario, and used to train the transformer model. Numerical studies are conducted to analyze the effectiveness of the proposed modeling approach. A comparison of the proposed model with representative LSTM models highlights the advantages of leveraging the transformer model characteristics for the vehicle trajectory prediction of congested urban traffic. By contrast, existing LSTM models may suffice for the trajectory prediction of freeway traffic. The results also indicate that, unlike for vehicle trajectory prediction for freeway traffic, a longer time window of inputs does not guarantee better prediction performance for congested urban traffic.