Cody Phillips

University of Pennsylvania

Papers

6

Total Citations

342

H-Index

6

About

Cody Phillips is a robotics researcher whose work sits at the intersection of computer vision, manipulation, and autonomous systems. His most influential contribution is a pioneering method for single-image 3D object detection and pose estimation for grasping, which has garnered 227 citations and remains a foundational reference in the field. This work demonstrated how deformable parts-based models could infer 3D pose from cluttered scenes without relying on texture cues—a critical capability for real-world robotic manipulation. Phillips also tackled the notoriously difficult problem of perceiving transparent objects, such as glassware, by combining learned detectors with geometric reasoning, a contribution that has earned 50 citations and opened new avenues for handling visually challenging materials. Beyond these core advances, he contributed to multi-robot systems in the MAGIC 2010 competition and developed automated systems for semantic object labeling in retail environments, showcasing his ability to bridge perception and practical deployment. His research consistently addresses the gap between sensing and action, making him a notable figure in robotic perception and grasping.

Research Focus

Key Achievements

6
H-Index
6
Papers
342
Total Citations
57
Avg Citations/Paper
🏆 Most Cited Paper
Single image 3D object detection and pose estimation for grasping
227 citations · 2014
📈 Most Prolific Year: 2016 (2 Papers)
🤝 Key Collaborators: 19
🏛 Institutions: University of Pennsylvania

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago