Urban commuters have been suffering from traffic congestion for a long time. In order to avoid or mitigate the congestion effect, it is significant to know how the introduction of autonomous vehicles (AVs) influence the road capacity . The effects that AVs bring to the macroscopic fundamental diagram (MFD) were investigated through microscopic traffic simulations. This is a key issue as the MFD is a basic model to describe road capacity in practical traffic engineering. Accordingly, the paper investigates how the different percentage of AVs affects the urban MFD. A detailed simulation study was carried out by using SUMO both with an artificial grid road network and a real-world network in Budapest. On the one hand, simulations clearly show the capacity improvement along with AVs penetration growth. On the other hand, the paper introduces an efficient modeling for MFDs with different AVs rates by using the generalized additive model (GAM).

As highly automated and autonomous vehicles (AVs) become more and more widespread, inducing the change of traffic dynamics, significant changes occur in traditional traffic control. So far, automotive testing has been done mostly in real-world or pure virtual simulation environment. However, this practice is quite obsolete as testing in real traffic conditions can be quite costly, moreover purely simulation based testing might be inadequate for specific goals. Accordingly, a hybrid concept of the Vehicle-inthe-Loop (ViL) was born recently, in accordance with the Hardware-in-the-Loop concept, i.e. in the ViL concept the vehicle is the 'hardware' within the simulation loop. Furthermore, due to the development of software capabilities, a novel approach, the Scenarioin-the-Loop (SciL) concept evolves based on the ViL approach. The paper defines the main purposes and conditions related to implementing ViL and SciL concepts from the perspective of traffic simulation and traffic control.

The increasing complexity of urban traffic networks has highlighted the potential of Multi-Agent Reinforcement Learning (MARL) for Traffic Signal Control (TSC). However, most existing MARL methods assume homogeneous observation and action spaces among agents, ignoring the inherent heterogeneity of real-world intersections in topology and signal phasing, which limits their practical applicability. To address this gap, we propose HAPS-PPO (Heterogeneity-Aware Policy Sharing Proximal Policy Optimization), a novel MARL framework for coordinated signal control in heterogeneous road networks. HAPS-PPO integrates two key mechanisms: an Observation Padding Wrapper (OPW) that standardizes varying observation dimensions, and a Dynamic Multi-Strategy Grouping Learning (DMSGL) mechanism that trains dedicated policy heads for agent groups with distinct action spaces, enabling adequate knowledge sharing while maintaining structural correctness. Comprehensive experiments in a high-fidelity simulation environment based on a real-world road network demonstrate that HAPS-PPO significantly outperforms Fixed-time control and mainstream MARL baselines (e.g., MADQN, FMA2C), reducing average delay time by up to 44.74% and average waiting time by 59.60%. This work provides a scalable and plug-and-play solution for deploying MARL in realistic, heterogeneous traffic networks.

This study combines text mining and binary logit model to analyze the main influencing factors of consumers’ purchase intention for new energy vehicles (NEVs) in Urumqi. Through the analysis of 34,561 consumer reviews and 400 valid questionnaire data, the study found that battery technology, sales price, and policy support have a significant impact on purchase intention. Based on the differences in consumers’ price sensitivity, technology preference, and policy support, this paper segments consumers into six groups. Based on these findings, we propose policy recommendations to optimize subsidy policies, promote battery technology upgrades, and improve charging infrastructure, in order to drive the development of the NEV market.

Mixed-autonomy urban networks may experience rapid service degradation when local capacity losses interact with demand surges and queue spillback. This study formulates disturbance-period traffic management as a service-maintenance problem and proposes Res-STC (Resilience-oriented Signal-Traffic Cooperative Control), a hybrid multi-agent reinforcement-learning framework that coordinates network-level signal decisions with local speed guidance for eligible connected and autonomous vehicles (CAVs). A cascaded graph-attention/Transformer encoder represents adjacent-intersection coupling and longer-range network dependencies, while an engineering-constrained execution layer enforces minimum and maximum green times, yellow/all-red transitions, and directional anti-starvation rules. Experiments were conducted in SUMO on a 4 × 4 Hangzhou benchmark network adapted from the network used in CoLight, comprising 16 signalized intersections, under 13 demand, disturbance, and CAV-penetration scenarios. Across 10 matched simulation seeds for a selected trained policy, Res-STC achieved the highest or near-highest mean operational performance in most scenarios, particularly in average speed, throughput, and completion rate. Relative to the signal-only ablation, the scenario-level mean change in average speed ranged from − 0.01% to 4.90%, and the corresponding mean change in throughput ranged from − 0.29% to 3.89%. These descriptive results indicate that network-level signal coordination is the primary source of improvement, whereas CAV speed guidance acts as a complementary, scenario-dependent local actuator rather than a substitute for signal control.