Wenyuan Zeng

Papers

Total Citations

H-Index

About

Wenyuan Zeng is a leading researcher in autonomous driving, with a focus on motion forecasting and graph-based representation learning. Their most notable contribution is the development of **LaneRCNN**, a novel framework that introduces distributed graph-centric representations for predicting the future behaviors of dynamic actors. This work, published in 2021 and garnering 11 citations, addresses a core challenge in self-driving technology: modeling the complex, latent interactions between vehicles, pedestrians, and road infrastructure. By encoding map elements and agent trajectories into a unified graph structure, LaneRCNN enables more accurate and interpretable long-term motion predictions. Zeng’s research bridges the gap between spatial reasoning and temporal dynamics, offering a scalable solution for real-world autonomous systems. Their work is widely recognized for advancing the state of the art in behavior forecasting, with implications for safer and more efficient autonomous navigation. As a rising voice in robotics and computer vision, Zeng continues to push the boundaries of how machines understand and anticipate human-like driving behavior.