Justin Kearns

Papers

Total Citations

232

H-Index

About

Justin Kearns is a leading researcher in robotic manipulation and computer vision, with a focus on enabling robots to interact with unfamiliar objects in unstructured environments. His pioneering work addresses the fundamental challenge of robotic grasping without the need for explicit 3D models, a paradigm shift that has influenced the field of autonomous robotics. In his highly cited 2007 paper, "Robotic Grasping of Novel Objects" (159 citations), Kearns introduced a learning algorithm that directly predicts grasp points from visual input, bypassing traditional geometric reconstruction. This approach was further refined in his 2008 work, "Learning to Grasp Novel Objects Using Vision" (73 citations), which demonstrated robust performance on previously unseen objects. Kearns’ contributions have been instrumental in advancing data-driven methods for manipulation, making robots more adaptable in real-world settings like manufacturing and service robotics. His research continues to inspire new generations of roboticists, bridging the gap between perception and action with elegant, practical solutions.