Papers

4

Total Citations

23

H-Index

2

About

Lingfeng Sun is a robotics researcher whose work spans robotic manipulation, assembly automation, and human-robot interaction. His research addresses some of the most demanding challenges in intelligent robotics, combining machine learning with physical dexterity to advance autonomous systems in real-world environments. Among his most significant contributions is a holistic multi-level reasoning framework for robotic assembly, which moves beyond conventional target segmentation and pose regression to enable flexible, blueprint-free part assembly — a breakthrough with broad implications for manufacturing, maintenance, and recycling. His work on data-efficient grasp learning, accumulating 9 citations, introduces a maximum likelihood grasp sampling loss that dramatically reduces the supervision burden typically required to train robust grasping models. Sun has also tackled the persistent sim-to-real transfer problem in contact-rich manipulation, proposing online admittance residual learning to achieve safer, more stable robot-environment interaction. More recently, his "Imagined Potential Games" framework addresses the nuanced challenge of predicting and navigating around human agents in collaborative indoor environments. With publications across 2022–2024 and a growing citation record, Sun represents an emerging voice pushing the boundaries of autonomous manipulation and interactive robotic behavior.

Research Focus

Key Achievements

2
H-Index
4
Papers
23
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection
10 citations · 2024
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 15
🏛 Institutions: University of California, Berkeley, Systems Control (United States)

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago