Tianyang Zhao

Papers

Total Citations

H-Index

About

Tianyang Zhao is a researcher advancing the field of autonomous systems through innovative work in human trajectory prediction. Their primary research focuses on developing probabilistic models that enable self-driving cars and social robots to anticipate human movement with greater accuracy and diversity. Zhao’s most notable contribution is the **Latent Belief Energy-Based Model (LB-EBM)**, introduced in their 2021 paper, which has garnered 84 citations. This model redefines trajectory forecasting by defining a cost function in latent space, capturing the inherent uncertainty and multimodality of human behavior—a critical improvement over deterministic approaches. By generating diverse, plausible future paths, LB-EBM enhances the safety and social intelligence of autonomous platforms. Zhao’s work bridges probabilistic machine learning and robotics, offering a principled framework for decision-making under uncertainty. Their research has implications for human-robot interaction, autonomous navigation, and smart infrastructure. With growing recognition in the computer vision and robotics communities, Zhao continues to push the boundaries of how machines understand and anticipate human intent, making autonomous systems more reliable and context-aware in dynamic, real-world environments.