Autonomous driving requires real-time interaction between vehicles and infrastructure to ensure safety and efficiency. However, current V2X system focused on simulation environments or constrained testbeds, overlooking critical aspects, including the scalability of the autonomous driving environment, as well as infrastructures, vehicles, and control data exchange. To address these issues, this study proposes mOS, a modular edge-intelligent framework validated through real-world intersection deployments and metaverse-based mixed-reality simulations. Built on a containerized and extensible architecture, mOS enables dynamic coordination among vehicles, infrastructure, and virtual entities. Experimental results demonstrate enhanced safety, responsiveness, and scalability while overcoming the limitations of conventional J2735-based V2X systems. Operating over commercial 5G with acceptable latency, the framework provides a cost-effective and practical platform for next-generation intelligent transportation systems.

A research paper by scientists from Chinese Academy of Sciences proposed a hybrid frequency–phase–space encoding method, integrated with high-density electroencephalogram (EEG) recordings, to develop high-speed BCI systems.

The new research paper, published on Mar. 26 in the journal Cyborg and Bionic Systems, developed a groundbreaking visual brain-computer interface (BCI) that sets a new benchmark for noninvasive BCI communication speed.

Understanding traffic scenes under adverse conditions such as rain, fog, night-time illumination, and motion blur remains a major challenge for intelligent transportation systems. Researchers at Tsinghua University propose TrafficPerceiver, a multimodal large language model framework that unifies traffic scene understanding and target-oriented segmentation under natural language instructions. By incorporating reinforcement learning based on group-relative policy optimization, the framework improves robustness and interpretability in complex real-world traffic environments.

6G’s space-ground integrated networks need reliable simulation tools for LEO satellite mega-constellations. A new study in Engineering unveils UltraStar, a high-fidelity simulator that models dynamic satellite topologies, real communication conditions and boosts efficiency via parallel computing. It’s validated across network layers and paves the way for 6G space-ground network development.

Modern technology demands compact, efficient optical devices for cameras, sensors, and quantum systems. Metasurfaces offer nanoscale control of light, yet strong confinement remains difficult. While traditional cavities rely on mirrors, bound states in the continuum (BICs) trap light through destructive interference. A recent review in Opto-Electronic Advances highlights BIC materials across wavelengths, machine-learning-driven designs, emerging topological forms like super-BICs, and scalable applications in lasing, sensing, and nonlinear optics.