Tianhao Fu
Papers
1
Total Citations
2
H-Index
1
About
Tianhao Fu is a rising researcher in embodied intelligence and vision-language models, with a focus on bridging the gap between generalized AI and domain-specific robotic applications. His key research areas include multimodal learning, robotics perception, and human-robot interaction for home environments. Fu’s most notable contribution is the development of **SweepMM**, a high-quality multimodal dataset designed specifically for sweeping robots in home scenarios. This work addresses a critical bottleneck in embodied AI: existing vision-language models lack the domain-specific knowledge required for household robots to understand and navigate complex, cluttered environments. By providing a rich, annotated dataset, SweepMM enables vision-language models to learn contextual cues—such as furniture layouts, obstacles, and cleaning priorities—that are essential for autonomous navigation and task execution. Although recently published in 2024, the paper has already garnered 2 citations, signaling early impact in the field. Fu’s work is foundational for advancing generalist robots that can adapt to real-world homes, and his dataset is poised to become a benchmark for future research in embodied vision-language learning.
Research Focus
Key Achievements
Top Papers
- 1