Shibin Zheng
Papers
2
Total Citations
79
H-Index
2
About
Shibin Zheng is a robotics and computer vision researcher whose work centers on autonomous navigation, visual perception, and intelligent agent policy learning — particularly in the context of indoor robotic systems. His research addresses one of the most challenging problems in mobile robotics: enabling robots to actively search for and approach specific objects using only visual inputs, without relying on pre-built maps or explicit environmental knowledge. His most cited work, "Active Object Perceiver" (2018, 53 citations), introduced a recognition-guided policy learning framework that allows mobile robots to navigate indoor environments by integrating object recognition with decision-making — a significant step toward vision-driven autonomous agents. Building on this, his 2019 paper "GAPLE" (26 citations) advanced the field further by tackling the challenge of generalizability, developing action policies that can transfer across diverse indoor environments and object categories, addressing a critical limitation of prior navigation systems. Zheng's contributions sit at the intersection of deep reinforcement learning, visual recognition, and robotics, reflecting a sustained effort to make robotic agents more capable and adaptable in real-world settings. His work has garnered meaningful attention from the robotics and AI communities, establishing him as a contributor to the growing field of embodied intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2