Zhaojing Yang
Papers
2
Total Citations
15
H-Index
2
About
Zhaojing Yang is an emerging robotics and artificial intelligence researcher whose work sits at the compelling intersection of vision-language models and embodied robot navigation. Based at NVIDIA, Yang has made notable contributions to the rapidly evolving field of legged robot autonomy, most prominently through the development of NaVILA — a Vision-Language-Action (VLA) model designed specifically for legged robot navigation. This pioneering work addresses one of robotics' most challenging problems: enabling legged robots to interpret and act on natural human language instructions while navigating complex, cluttered real-world environments. Unlike wheeled systems, legged robots offer far greater terrain adaptability, and NaVILA leverages this flexibility by bridging high-level language commands with low-level locomotion control. The research has already garnered 15 citations across its 2024 and 2025 publications, a strong early signal of its impact within the community. Yang's contributions are particularly significant because they push the boundaries of how humans interact with autonomous robots, moving toward more intuitive, language-driven control paradigms. Students exploring embodied AI, human-robot interaction, or legged locomotion will find Yang's work an essential reference point in the field.
Research Focus
Key Achievements
Top Papers
- 1NaVILA: Legged Robot Vision-Language-Action Model for Navigation13 citations · 2025
- 2NaVILA: Legged Robot Vision-Language-Action Model for Navigation2 citations · 2024