Yiye Chen
Papers
1
Total Citations
13
H-Index
1
About
Yiye Chen is an emerging robotics researcher specializing in robot perception and manipulation, with a particular focus on grasp detection and generation for robotic systems. Her most notable work, *Keypoint-GraspNet* (2023), addresses a critical challenge in robotic grasping: generating accurate 6-DoF grasp poses from monocular RGB-D input. By leveraging keypoint-based representations, Chen's approach circumvents the computational bottlenecks traditionally associated with point cloud processing, including the difficulties that arise when handling small objects with sparse point cloud data. This contribution represents a meaningful step forward in making 6-DoF grasp learning more efficient and practically deployable in real-world robotic settings. With 13 citations accrued relatively quickly after publication, her work is gaining traction within the robotics and computer vision communities, reflecting its relevance to ongoing challenges in robotic manipulation. Chen's research sits at the intersection of deep learning, 3D scene understanding, and physical robot interaction — areas of growing importance as autonomous systems are increasingly expected to operate in unstructured environments. Her contributions suggest a promising trajectory in advancing robust, computationally efficient perception pipelines for next-generation robotic manipulation systems.
Research Focus
Key Achievements
Top Papers
- 1