Zhenwei Zhu
Papers
2
Total Citations
9
H-Index
2
About
Zhenwei Zhu is a rising researcher in robotic manipulation, with a focus on language-conditioned segmentation and grasping (LCSG) and grasp detection. His work bridges natural language understanding and computer vision to enable robots to identify and grasp specific objects based on human verbal instructions. In his most cited paper, "Infusing Multisource Heterogeneous Knowledge for Language-Conditioned Segmentation and Grasping" (2024, 7 citations), Zhu addresses the challenge of semantic matching between full instructions and raw RGB images, proposing a novel approach that integrates multisource knowledge for more accurate grounding. His second notable work, "A refined robotic grasp detection network based on coarse-to-fine feature and residual attention" (2024, 2 citations), tackles limitations in existing grasp detection methods by introducing a coarse-to-fine feature refinement and residual attention mechanism, improving the precision of grasping rectangles for industrial and household tasks. Zhu’s contributions are particularly relevant for advancing human-robot interaction, where robots must interpret complex commands and execute stable grasps in dynamic environments. His research demonstrates a commitment to enhancing robotic autonomy and dexterity, with potential applications in manufacturing, assistive robotics, and smart homes.
Research Focus
Key Achievements
Top Papers
- 1
- 2