Ruohan Yu

Title: Ruohan Yu and Autonomous Emergency-Rescue Vehicle Safety

Introduction

Ruohan Yu is an inventor based in Zhenjiang, China, whose patent work addresses collision-risk prediction for autonomous emergency-rescue vehicles. The supplied information identifies Jiangsu University as her organization and lists one patent.

Latest Patents

Yu’s listed patent is “Crash Risk Prediction Method and System of Emergency Rescue Autonomous Vehicle Based on HM-TRW and HAGENN Structure Search.” It describes representing an emergency-rescue vehicle and nearby moving objects as a dynamic heterogeneous graph. The method uses HM-TRW to assess the importance and changing behavior of surrounding objects and their interactions, then combines those results with the objects’ original features.

The system feeds this information into HAGENN to predict collision risk. It also applies dynamic heterogeneous graph embedding to a hierarchical attention neural network to learn about the objects’ characteristics and changing conditions. The disclosure describes using positioning and parameterized spaces to determine and search attention functions, with multi-stage differential search intended to accelerate that process. Its stated aim is to support more comprehensive and accurate collision-risk prediction during autonomous emergency-vehicle operation.

Career Highlights

The available information associates Yu’s patent activity with Jiangsu University. Her listed invention focuses on applying graph-based modeling and attention mechanisms to vehicle safety.

Collaborations

Long Chen and Hai Wang are identified as Yu’s coworkers. The supplied information does not specify their roles in the patent or the extent of their collaboration.

Conclusion

Ruohan Yu’s listed patent combines dynamic heterogeneous graphs and hierarchical attention methods to predict collision risks for autonomous emergency-rescue vehicles.