Minghao Gou
Papers
9
Total Citations
552
H-Index
6
About
Minghao Gou is a robotics researcher whose work sits at the intersection of computer vision and robotic manipulation, with a particular focus on grasp perception and pose estimation in complex, real-world environments. His most influential contribution, **AnyGrasp** (2023, 210 citations), established a landmark framework enabling robots to perform robust, human-like grasping across both spatial and temporal domains — addressing a longstanding challenge in prehensile manipulation. Building on this, his earlier work on graspness discovery (2021, 124 citations) introduced a principled approach to identifying where robots should grasp in cluttered scenes, dramatically improving detection speed and accuracy over conventional uniform-sampling methods. His research on 7-DoF grasp pose estimation from monocular RGBD images (2021, 117 citations) further pushed the boundaries by leveraging rich RGB information to overcome the limitations of depth-only approaches. Gou has also contributed to community infrastructure through the GraspNet-1Billion dataset and the OCRTOC cloud-based benchmark, providing standardized evaluation platforms that have helped unify progress across the field. With over 550 cumulative citations, his work has meaningfully advanced the reliability and practicality of robotic grasping systems in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains210 citations · 2023
- 2Graspness Discovery in Clutters for Fast and Accurate Grasp Detection124 citations · 2021
- 3RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images117 citations · 2021
- 4
- 5
- 6Target-referenced Reactive Grasping for Dynamic Objects16 citations · 2023
- 7RGB Matters: Learning 7-DoF Grasp Poses on Monocular RGBD Images6 citations · 2021
- 8
- 9