Papers

11

Total Citations

365

H-Index

9

About

Hao Dang’s research lies at the intersection of robotic grasping, tactile perception, and task-driven manipulation. His core contributions center on enabling robots to plan and execute grasps that are not only stable but also functionally suitable for specific object manipulation tasks—a concept he terms “semantic grasping.” Dang pioneered the use of tactile feedback and hand kinematic data as proxies for semantic constraints, allowing robots to grasp objects without relying on visual or geometric information, a method known as “blind grasping.” His work on learning grasp stability from tactile data has been highly influential, with his most-cited paper, “Semantic grasping: Planning robotic grasps functionally suitable for an object manipulation task” (2012), accumulating 89 citations. He has also advanced robot learning from human demonstration, developing task descriptors and program synthesis techniques for everyday object manipulations. Dang’s research has practical implications for disaster response, where he has explored complex physical task planning for humanoid robots. With over 360 total citations across his top publications, Hao Dang’s work has significantly shaped the fields of robotic manipulation and tactile-based grasping, providing foundational methods for creating more dexterous and autonomous robotic systems.

Research Focus

Key Achievements

9
H-Index
11
Papers
365
Total Citations
33
Avg Citations/Paper
🏆 Most Cited Paper
Semantic grasping: Planning robotic grasps functionally suitable for an object manipulation task
89 citations · 2012
📈 Most Prolific Year: 2012 (3 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: Columbia University, Microsoft (United States), Beihang University

Top Papers

  1. 1
  2. 2
  3. 3
    Learning grasp stability
    61 citations · 2012
  4. 4
  5. 5
  6. 6
  7. 7
  8. 8
  9. 9
  10. 10

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago