In recent years, reinforcement learning (RL) methods have shown powerful learning capabilities in single-vehicle autonomous driving. However, few studies have focused on multi-vehicle cooperative driving based on RL, particularly in the dynamically changing traffic environments of highway ramp merge zones. In this paper, a multi-agent deep reinforcement learning (MARL) framework for multi-vehicle cooperative decision-making is proposed based on actor–critic, which categorizes vehicles into two groups according to their origins in the merging area. At the same time, the complexity of the network is reduced and the training process of the model is accelerated by utilizing mechanisms such as partial parameter sharing and experience playback. Additionally, a combination of global and individual rewards is adopted to promote cooperation in connected autonomous vehicles (CAVs) and balance individual and group interests. The training performance of the model is compared under three traffic densities, and our method is also compared with state-of-the-art benchmark methods. The simulation results show that the proposed MARL framework can have stronger policy learning capability and stability under various traffic flow conditions. Moreover, it can also effectively improve the speed of vehicles in the merging zone and reduce traffic conflicts.

The booming growth of the internet of things has brought about widespread deployment of devices and massive amounts of sensing data to be processed. Federated learning (FL)-empowered mobile edge computing, known for pushing artificial intelligence to the network edge while preserving data privacy in learning cooperation, is a promising way to unleash the potential information of the data. However, FL’s multi-server collaborative operating architecture inevitably results in communication energy consumption between edge servers, which poses great challenges to servers with constrained energy budgets, especially wireless communication servers that rely on battery power. The device-to-device (D2D) communication mode developed for FL turns high-cost and long-distance server interactions into energy-efficient proximity delivery and multi-level aggregations, effectively alleviating the server energy constraints. A few studies have been devoted to D2D-enabled FL management, but most of them have neglected to investigate server computing power for FL operation, and they have all ignored the impact of dataset characteristics on model training, thus failing to fully exploit the data processing capabilities of energy-constrained edge servers. To fill this gap, in this paper we propose a D2D-assisted FL mechanism for energy-constrained edge computing, which jointly incorporates computing power allocation and dataset correlation into FL scheduling. In view of the variable impacts of computational power on model accuracy at different training stages, we design a partite graph-based FL scheme with adaptive D2D pairing and aperiodic variable local iterations of heterogeneous edge servers. Moreover, we leverage graph learning to exploit the performance gain of the dataset correlation between the edge servers in the model aggregation process, and we propose a graph-and-deep reinforcement learning-based D2D server pairing algorithm, which effectively reduces FL model error. The numerical results demonstrate that our designed FL schemes have great advantages in improving FL training accuracy under edge servers’ energy constraints.

Traffic breakdown refers to the first-order transition from free flow to synchronized flow. It is characterized by a rapid decrease in speed, suddenly increasing density, and abruptly plummeting capacity in most of the relevant observations. To understand its cause and model its empirical observations, a multi-regime car-following model is proposed, which classifies the car-following state into four regimes, i.e., Free driving, High-speed following, Low-speed following, and Emergency. Simulation results demonstrate that traffic breakdown and spontaneous jam formation can be reproduced simultaneously by the new model. Experimental verification has shown that the new model can successfully simulate the observed concave growth pattern of traffic oscillations.

With the increasing complexity of transportation systems, traditional qualitative descriptions fail to objectively reflect the level of autonomy in traffic signal control systems—especially the lack of a systematic evaluation framework that links technology synergy, task autonomy, and system-level autonomy. To address this critical systematic gap, this study integrates the Analytic Hierarchy Process (AHP) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to develop a systematic quantitative classification model for assessing system autonomy. The model constructs a three-level indicator framework—“technology–task–system”—based on the systematic closed-loop architecture of traffic signal control systems (upper interaction layer + lower technology chain layer), thereby enabling a holistic and quantitative evaluation of traffic signal control system autonomy. Results indicate that human involvement in the system decreases from 86% at the non-autonomous L0 level to 13% at the fully autonomous L3 level. This systematic quantitative method first reveals the inherent evolution logic of system autonomy (technology → task → system). Additionally, it provides a theoretical foundation for two key applications: the performance comparison across different traffic signal control systems and the planning of their intelligent development pathways—filling the gap of scattered, non-systematic evaluations in existing research. It also serves as a practical tool for these applications.