Tiffany Yee Kay Yau

Title: Tiffany Yee Kay Yau and Graph Neural Networks for Pedestrian Action Prediction.

Introduction

Tiffany Yee Kay Yau is an inventor associated with Markham, Canada, and Huawei Technologies Co., Ltd. Her patent work addresses a challenge in autonomous driving: predicting whether a pedestrian will cross the road.

Latest Patents

Yau is named on 1 patent: “Method and System for Graph Neural Network Based Pedestrian Action Prediction in Autonomous Driving Systems.” The invention models road users across observed frames of a traffic scene as a spatiotemporal graph, groups them into categories, and provides the graph to a trained graph convolutional neural network. The system predicts whether a pedestrian will cross the road, supporting a more informed understanding of the scene around an autonomous vehicle.

Career Highlights

Yau’s listed patent reflects work at the intersection of artificial intelligence, computer vision, and autonomous driving. It applies graph-based modeling to represent interactions among road users over time and to anticipate pedestrian behavior.

Collaborations

Yau is associated with Huawei Technologies Co., Ltd. Her listed coworkers include Amir Rasouli and Jun Luo.

Conclusion

Tiffany Yee Kay Yau’s patent focuses on using spatiotemporal graphs and neural networks to help autonomous driving systems predict pedestrian actions and interpret traffic scenes.