Kevin Wolfram
Papers
1
Total Citations
10
H-Index
1
About
Kevin Wolfram is a robotics researcher whose work focuses on enabling robots to perceive and interact with objects in unstructured, real-world environments. His primary research areas include 6D pose estimation, object learning, and robotic grasping. Wolfram’s most-cited paper, “Object Learning for 6D Pose Estimation and Grasping from RGB-D Videos of In-hand Manipulation” (2021, 10 citations), introduces a novel pipeline that allows robots to autonomously generate high-quality object models by manipulating objects in-hand and observing them from multiple viewpoints. This contribution is significant because it addresses a critical bottleneck in deploying robots in homes and other domains where pre-existing object models are unavailable. By combining in-hand manipulation with RGB-D perception, Wolfram’s work enables robots to learn object geometries and poses on the fly, directly supporting downstream tasks like detection and grasping. Though early in his career, his research has already been recognized for its practical impact on autonomous manipulation, offering a scalable path toward more capable and adaptable service robots. Wolfram’s work stands out for its integration of perception and action, making object learning a tangible, real-time capability for robots.
Research Focus
Key Achievements
Top Papers
- 1