Papers

3

Total Citations

54

H-Index

2

About

Haifeng Han is a leading researcher in robotic manipulation, with a focus on deformable object handling, intelligent grasping, and bin-picking automation. His work bridges model-based reinforcement learning and deep learning to solve complex, real-world industrial challenges. Han’s seminal 2017 paper on model-based reinforcement learning for deformable linear object (DLO) manipulation—cited 31 times—pioneered a universal approach to controlling cables, wires, and hoses, overcoming the lack of material-specific models. He further advanced robotic grasping with his 2022 study on learning suction graspability, which leveraged physically simulated images to train deep neural networks for bin-picking, achieving 22 citations by reducing reliance on expensive human-labeled datasets. Most recently, in 2024, Han introduced a Hybrid-AI grasp planning system that integrates rule-based and DNN-based methods, targeting throughput improvements in logistics automation amid labor shortages. His contributions have direct implications for manufacturing, warehousing, and service robotics, demonstrating how AI-driven solutions can enhance robot dexterity and efficiency. Han’s work is widely recognized for its practical impact, earning him a reputation as a key innovator in intelligent robotic manipulation.

Research Focus

Key Achievements

2
H-Index
3
Papers
54
Total Citations
18
Avg Citations/Paper
🏆 Most Cited Paper
Model-based reinforcement learning approach for deformable linear object manipulation
31 citations · 2017
📈 Most Prolific Year: 2017 (1 Papers)
🤝 Key Collaborators: 16
🏛 Institutions: Nara Institute of Science and Technology, Toshiba (Japan)

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago