Papers

2

Total Citations

54

H-Index

2

About

Yidan Feng is a leading researcher in industrial robotics, specializing in sim-to-real transfer learning for object recognition and localization. Their work addresses a critical bottleneck in automated bin picking—the gap between simulated training environments and real-world industrial applications. Feng's most influential contribution is the S2R-Pick framework, a generic deep-learning system that achieves fast, accurate object recognition and localization for industrial robotic bin picking, overcoming challenges posed by textureless and reflective parts common in manufacturing. This work has garnered 52 citations, reflecting its practical significance. Feng also developed SESR, a self-ensembling approach for instance segmentation in auto-store scenarios that eliminates the need for costly manual annotations, demonstrating a commitment to scalable, cost-effective solutions. By pioneering robust sim-to-real pipelines, Feng has advanced the deployment of intelligent robotic systems in logistics and manufacturing, enabling more reliable automation. Their research bridges the gap between computer vision theory and industrial practice, making them a key figure in the field of robotic perception and manipulation.

Research Focus

Key Achievements

2
H-Index
2
Papers
54
Total Citations
27
Avg Citations/Paper
🏆 Most Cited Paper
A Sim-to-Real Object Recognition and Localization Framework for Industrial Robotic Bin Picking
52 citations · 2022
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 11
🏛 Institutions: Chinese University of Hong Kong, Nanjing University of Aeronautics and Astronautics

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago