Hongrui Sang
Papers
7
Total Citations
35
H-Index
4
About
Hongrui Sang is a robotics researcher whose work spans the frontiers of deformable object manipulation, human–robot interaction safety, and autonomous skill acquisition. His most-cited paper, "Learning Graph Dynamics With Interaction Effects Propagation for Deformable Linear Objects Shape Control" (2025, 9 citations), introduces a novel graph-based dynamics model for precise shape control of deformable linear objects—a critical capability for applications in manufacturing and medical surgery. Sang also addresses the pressing challenge of safe human–robot collaboration through "An Active Strategy for Safe Human–Robot Interaction Based on Visual–Tactile Perception" (2023, 7 citations), which fuses visual and tactile sensing for proactive safety. His systematic review "Robot skill learning and the data dilemma it faces" (2024, 5 citations) provides a comprehensive analysis of data-driven learning methods, while "NeuTRL: Neural Trust-Guided Reinforcement Learning for Human-Robot Collaboration" (2025, 4 citations) advances RLHF for complex, long-horizon tasks. Notably, his early work on "A Novel Intelligent Robot for Epidemic Identification and Prevention" (2020, 4 citations) demonstrates real-world impact during the COVID-19 pandemic. With over 35 total citations and contributions to hierarchical learning and scene augmentation, Sang is shaping the future of intelligent, safe, and adaptive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Robot skill learning and the data dilemma it faces: a systematic review5 citations · 2024
- 4
- 5A Novel Intelligent Robot for Epidemic Identification and Prevention4 citations · 2020
- 6
- 7Scene Augmentation Methods for Interactive Embodied AI Tasks3 citations · 2023