Papers
2
Total Citations
7
H-Index
2
About
Liwei Deng is a researcher advancing the field of robotic manipulation through innovative grasp detection frameworks. His work centers on computer vision and deep learning for robotics, with a particular focus on developing efficient and accurate grasp detection algorithms that can handle the real-world diversity of object shapes, sizes, and poses. Deng’s major contributions include the introduction of PDCNet, a lightweight and efficient robotic grasp detection framework that leverages Partial Convolution and knowledge distillation to achieve high performance with reduced computational cost. This work has already garnered 5 citations since its 2025 publication, signaling its impact on the field. Additionally, his development of a novel large-kernel residual grasp network addresses the critical limitation of insufficient receptive fields in prior methods, enabling more robust feature extraction for diverse grasping scenarios. By tackling the trade-off between efficiency and accuracy, Deng’s research is paving the way for more practical and deployable robotic grasping systems, making him a notable emerging voice in the robotics and computer vision community.
Research Focus
Key Achievements
Top Papers
- 1
- 2A novel large-kernel residual grasp network for robot grasp detection2 citations · 2024