Justin Driemeyer

Papers

Total Citations

1,180

H-Index

About

Justin Driemeyer has made foundational contributions to the field of robotic manipulation, particularly in enabling robots to grasp objects they have never seen before. His key research areas include computer vision, machine learning, and autonomous grasping. Driemeyer’s most influential work, "Robotic Grasping of Novel Objects using Vision" (2008), has garnered nearly 1,000 citations, establishing a paradigm shift away from requiring pre-built 3D models. Instead, he developed learning algorithms that predict optimal grasp points directly from visual input, allowing robots to interact with unfamiliar objects in real time. This approach, detailed across his highly cited papers (2007, 2008), bypasses traditional model-based methods, significantly improving adaptability in unstructured environments. Driemeyer’s contributions have been instrumental in advancing practical robotic systems for manufacturing, service robotics, and assistive technologies. His work is widely recognized for its elegance and impact, inspiring subsequent research in data-driven grasping and vision-based manipulation. For students and researchers, Driemeyer’s research exemplifies how combining perception with learning can solve long-standing challenges in robotics, making autonomous grasping more robust and accessible.