Hang Ji
Papers
1
Total Citations
3
H-Index
1
About
Hang Ji is a researcher at the forefront of embodied AI and human-robot interaction (HRI), with a focus on bridging the semantic gap between natural language and robotic action. Ji’s most notable contribution is the development of **HuBo-VLM**, a unified vision-language model specifically designed for human-robot interaction tasks. This end-to-end system enables robots to interpret complex human instructions by integrating visual data from onboard sensors with linguistic commands, addressing a core challenge in HRI: translating ambiguous, context-rich human language into precise machine-executable actions. While still early in its citation trajectory (3 citations since 2023), HuBo-VLM represents a significant step toward more intuitive, real-time robot control. Ji’s work sits at the intersection of computer vision, natural language processing, and robotics, aiming to make robots not just functional but truly collaborative partners. By tackling the “huge gap” between human communication and machine code, Ji is helping to shape a future where robots can seamlessly follow spoken instructions in dynamic, unstructured environments—a critical capability for applications in assistive technology, manufacturing, and service robotics.
Research Focus
Key Achievements
Top Papers
- 1