Zhiyao Bao
Papers
2
Total Citations
35
H-Index
2
About
Zhiyao Bao is an emerging robotics researcher whose work centers on the critical challenge of deploying learning-based robotic systems in real-world environments. Their most significant contribution lies in developing frameworks for human-in-the-loop autonomy, addressing a fundamental gap between laboratory demonstrations and practical robot deployment. Bao's research tackles the well-documented brittleness of deep learning systems in robotics — namely, their tendency to fail when encountering scenarios outside their training distribution and their hunger for excessive labeled data. Their landmark work, "Robot Learning on the Job," proposes innovative mechanisms by which robots can continue learning during active deployment, guided by human oversight rather than requiring exhaustive pre-deployment training. This approach represents a pragmatic shift in how the robotics community thinks about the human-robot collaboration cycle. The paper has accumulated 35 citations across its published versions, reflecting meaningful traction within the robotics and machine learning communities for a recently published contribution. Bao's research speaks directly to one of the field's most pressing open problems: making intelligent robots genuinely useful outside controlled settings, bridging the persistent gap between promising research prototypes and reliable, adaptable real-world systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2