Traffic signal control (TSC) is a core challenge in urban mobility, where real-time decisions must balance efficiency and safety. Existing methods—ranging from rule-based heuristics to reinforcement learning (RL)—often struggle to generalize to complex, dynamic, and safety-critical scenarios. We introduce \textbf{VLMLight}, a novel TSC framework that integrates vision-language meta-control with dual-branch reasoning. At the core of VLMLight is the first image-based traffic simulator that enables multi-view visual perception at intersections, allowing policies to reason over rich cues such as vehicle type, motion, and spatial density. A large language model (LLM) serves as a safety-prioritized meta-controller, selecting between a fast RL policy for routine traffic and a structured reasoning branch for critical cases. In the latter, multiple LLM agents collaborate to assess traffic phases, prioritize emergency vehicles, and verify rule compliance. Experiments show that VLMLight reduces waiting times for emergency vehicles by up to 65% over RL-only systems, while preserving real-time performance in standard conditions with less than 1% degradation. VLMLight offers a scalable, interpretable, and safety-aware solution for next-generation traffic signal control.

Vehicle-to-everything (V2X) is a popular topic in the field of Autonomous Driving in recent years. Vehicle-infrastructure cooperation (VIC) becomes one of the important research area. Due to the complexity of traffic conditions such as blind spots and occlusion, it greatly limits the perception capabilities of single-view roadside sensing sys-tems. To further enhance the accuracy of roadside perception and provide better information to the vehicle side, in this paper, we constructed holographic intersections with various layouts to build a large-scale multi-sensor holo-graphic vehicle-infrastructure cooperation dataset, called HoloVic. Our dataset includes 3 different types of sen-sors (Camera, Lidar; Fisheye) and employs 4 sensor-layouts based on the different intersections. Each intersection is equipped with 6–18 sensors to capture synchronous data. While autonomous vehicles pass through these intersections for collecting VIC data. HoloViccontains in to-talon 100k+ synchronous frames from different sensors. Additionally, we annotated 3D bounding boxes based on Camera, Fisheye, and Lidar: We also associate the IDs of the same objects across different devices and consecutive frames in sequence. Based on HoloVIC, we formulated four tasks to facilitate the development of related research. We also provide benchmarks for these tasks.

Data-driven autonomous driving motion generation tasks are frequently impacted by the limitations of dataset size and the domain gap between datasets, which precludes their extensive application in real-world scenarios. To address this issue, we introduce SMART, a novel autonomous driving motion generation paradigm that models vectorized map and agent trajectory data into discrete sequence tokens. These tokens are then processed through a decoder-only transformer architecture to train for the next token prediction task across spatial-temporal series. This GPT-style method allows the model to learn the motion distribution in real driving scenarios. SMART achieves state-of-the-art performance across most of the metrics on the generative Sim Agents challenge, ranking 1st on the leaderboards of Waymo Open Motion Dataset (WOMD), demonstrating remarkable inference speed. Moreover, SMART represents the generative model in the autonomous driving motion domain, exhibiting zero-shot generalization capabilities: Using only the NuPlan dataset for training and WOMD for validation, SMART achieved a competitive score of 0.72 on the Sim Agents challenge. Lastly, we have collected over 1 billion motion tokens from multiple datasets, validating the model's scalability. These results suggest that SMART has initially emulated two important properties: scalability and zero-shot generalization, and preliminarily meets the needs of large-scale real-time simulation applications. We have released all the code to promote the exploration of models for motion generation in the autonomous driving field. The source code is available at https://github.com/rainmaker22/SMART.

Traffic congestion in urban areas is a significant problem, leading to prolonged travel times, reduced efficiency, and increased environmental concerns. Effective traffic signal control (TSC) is a key strategy for reducing congestion. Unlike most TSC systems that rely on high-frequency control, this study introduces an innovative joint phase traffic signal cycle control method that operates effectively with varying control intervals. Our method features an adjust all phases action design, enabling simultaneous phase changes within the signal cycle, which fosters both immediate stability and sustained TSC effectiveness, especially at lower frequencies. The approach also integrates decentralized actors to handle the complexity of the action space, with a centralized critic to ensure coordinated phase adjusting. Extensive testing on both synthetic and real-world data across different intersection types and signal setups shows that our method significantly outperforms other popular techniques, particularly at high control intervals. Case studies of policies derived from traffic data further illustrate the robustness and reliability of our proposed method.

Vehicle-to-everything (V2X) is communication between a vehicle and any entity that may affect, or may be affected by the vehicle. It is useful for road safety, traffic efficiency, energy savings and mass surveillance, etc. Intelligent traffic signal control (TSC) is a critical building block for V2X. In contrast to most existing TSC designs that assume real-time traffic flow information is available, this work proposes a reinforcement learning (RL)-based TSC system by explicitly taking into account the delay in the TSC input. To cope with the input delay, the proposed RL-based system extracts features to characterize the traffic flow by exploiting multiple delayed historical observations using either the convolutional neural networks (CNN) or the recurrent neural networks (RNN). As a result, the proposed TSC system can make more appropriate actions on choosing traffic signal plans that better match with the traffic flow. Extensive computer experiments performed on the Simulation of Urban MObility (SUMO) platform confirm that the proposed RL-based TSC system can achieve up to 76.0% reduction in the average vehicle waiting time as compared to the conventional RL-based TSC system for observations with large feedback delays.

A freeway stretch with even one pair of unmeasured on/off-ramps is not fully observable in traffic states. Flow observability is essential for freeway traffic modeling, surveillance, and control. It is a longstanding and tricky issue to estimate flows for unmeasured ramp pairs. This problem seems to be hardly tractable in conventional approaches, and this paper intends to handle it based on machine learning. The work was partially inspired by transfer learning. Consider that no measurements are available for a target ramp pair, and the knowledge about ramp flow estimation may be drawn from other (measured) ramp pairs, provided that measured and unmeasured ramp pairs would share similarities in some key traffic flow patterns. Two simple machine learning algorithms, random forest (RF) and gradient boosting machine (GBM), were employed to this end. RF and GBM were driven by real measurement data to establish models that relate ramp flows to adjacent mainstream traffic conditions. The models were then applied for our task. The estimation performance was evaluated using real measurement data from the Shanghai Urban Expressway and the Intercity Highway in California, with satisfactory results obtained.