Daniel Suo
Papers
3
Total Citations
528
H-Index
3
About
Daniel Suo is a researcher working at the intersection of robotics, computer vision, and machine learning, with a particular focus on advancing autonomous systems through deep learning. His most influential contribution, "Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge," has garnered an impressive 487 citations since its 2017 publication, establishing him as a key voice in robotic object recognition and manipulation. This work tackled one of the field's most demanding practical challenges — enabling robots to reliably identify and locate objects in cluttered, real-world warehouse environments — using self-supervised techniques that reduce the need for costly labeled training data. Suo's research demonstrates a consistent drive to bridge theoretical machine learning advances with tangible robotic applications. More recently, his work on DeLuca, a differentiable control library, reflects a broader ambition to democratize gradient-based control methods by providing open-source, auto-differentiable simulation environments for the robotics community. Together, these contributions position Suo as a thoughtful innovator helping to shape the future of intelligent autonomous systems, from warehouse automation to generalizable robot control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3