Zhengtuo Wang
Papers
6
Total Citations
89
H-Index
5
About
Zhengtuo Wang is a robotics researcher whose work focuses on integrating deep learning and point cloud processing to enhance robotic perception and manipulation. His primary research areas include robot grasping, point cloud instance segmentation, and compliance control for industrial automation. Wang’s major contributions lie in developing deep learning methods for estimating grasping poses from point cloud data, as demonstrated in his most-cited paper, "Grasping pose estimation for SCARA robot based on deep learning of point cloud" (42 citations). He has also advanced the use of RGB-D sensors for robotic scene understanding, notably in "Instance segmentation of point cloud captured by RGB-D sensor based on deep learning" (21 citations), which emphasizes the critical role of segmentation quality in downstream tasks. His work on simulation-based training data generation for deep learning, such as in "Simulation and deep learning on point clouds for robot grasping" (11 citations), provides practical tools for robotic systems. Additionally, Wang has explored dual-robot path planning using artificial bee colony algorithms and compliance control for deburring robots through force impedance. With a cumulative citation count exceeding 80, his research bridges theoretical advances and real-world industrial applications, making him a notable contributor to intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Simulation and deep learning on point clouds for robot grasping11 citations · 2021
- 4
- 5Compliance Control of Deburring Robots based on Force Impedance7 citations · 2020
- 6