Corbin Cogswell
Papers
2
Total Citations
23
H-Index
2
About
Corbin Cogswell’s research lies at the intersection of robotics, computer vision, and machine learning, with a core focus on enabling robots to generalize manipulation skills to unfamiliar objects. His most cited work, “Transferring Grasping Skills to Novel Instances by Latent Space Non-Rigid Registration” (2018), introduces a novel framework that leverages the structural similarities within object categories—such as tools or household items—to transfer learned grasping strategies from known examples to new, unseen instances. By employing latent space non-rigid registration, Cogswell’s approach allows robots to adapt their grasps based on shape and functional cues, significantly reducing the need for exhaustive retraining. This contribution has garnered 21 citations, reflecting its impact on advancing robotic autonomy in open, unstructured environments. Cogswell’s work is particularly notable for bridging the gap between simulation and real-world application, addressing a critical challenge in robotic manipulation. His research continues to inspire developments in transfer learning and dexterous robotics, making him a promising voice in the field of intelligent, adaptive automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2