To address the severe safety challenges of AI-driven autonomous driving under the Autonomy 2.0 paradigm, a joint research team from Tongji University, SAMR Defective Product Recall Technical Center, and Tsinghua University, proposed a hierarchical risk-filtering safety assurance framework, establishing a four-category assessment metric system and layered safety strategies, with a dedicated safety monitor for system-level architecture design.

Can vision-language models understand unstructured road scenes under degraded sensing conditions? Researchers developed the Unstructured Scene Benchmark (USB), a test and evaluation framework for autonomous driving models in unstructured road scenes and degraded visual conditions. By testing seven open-source vision-language models across six camera views, 20 corruption types, and 45,969 question-answer samples, the study reveals uneven robustness, weak planning ability, and signs of insufficient visual grounding.

Researchers have developed a method to generate customizable virtual road networks with adjustable complexity, which cuts required test mileage by over 30% while preserving real-world road features. This enables faster, more efficient identification of functional defects and performance boundaries in autonomous vehicles.

To answer this question: How to accurately predict the future trajectories of mixed-flow vehicle platoons in traffic oscillation scenarios? This study introduces CPIDLM, a hybrid AI model that significantly improves vehicle movement predictions during traffic speed changes by combining physical driving laws with individual human behavior patterns. By explicitly accounting for driver uncertainty and how vehicles affect one another, this approach reduced distance prediction errors by 16.7% compared to existing methods, providing a more reliable foundation for autonomous vehicles.

Researchers developed COIN, a collaborative and interaction-aware reinforcement learning framework for multi-agent autonomous driving. COIN enables vehicles to learn both individual navigation and system-level cooperation, improving safety and efficiency in dense scenarios such as intersections, roundabouts, and bottlenecks. The framework was evaluated in simulation and further validated on a hybrid robotic platform.

A PPPL researcher has developed a faster way of finding the best diamond-based materials for quantum computers. The new approach treats qubits, the basic units of information in quantum computers and the key components of quantum sensors, as isolated molecules. It has already identified promising materials for practical quantum devices. The new research also shows that qubits can be understood through chemistry, enabling scientists to design and build qubits the way a chemist designs custom molecules for a new medication.

Researchers at the Paul Scherrer Institute PSI have been examining the cladding tubes of nuclear reactor fuel rods using a new 3D imaging technique. They were able to determine with extremely high precision how the quality of the cladding changes over time as a result of corrosion and radiation exposure. The oxide layer on the tubes proved to retain its density even after years in operation. The new method allows this to be checked in great detail.

A new study led by researchers at the University of Oulu sheds light on a poorly understood part of space weather: where powerful waves form at the edge of Earth’s magnetic shield, and where the solar wind can find a way through.