Papers
4
Total Citations
32
H-Index
3
About
Sifeng Liu is a versatile researcher whose work bridges robotics, artificial intelligence, and predictive modeling. His primary research areas include deep learning for tactile sensing, human-centric computer vision, space robotics trajectory optimization, and grey system theory for industrial forecasting. Liu's most notable contribution is the development of a deep learning-assisted tactile sensing platform, which achieved 14 citations for its innovative application in object classification and password recognition—a breakthrough that could enhance human-robot interaction and security systems. He also introduced the Human-centric Relation Segmentation dataset and solution (10 citations), addressing a critical gap in fine-grained vision-language understanding for robotics, enabling more precise commands like “bring me the book in the girl’s left hand.” Earlier in his career, Liu advanced space robotics with a multi-objective particle swarm optimization algorithm for free-floating robots (5 citations), significantly improving load-carrying capacity under multiple constraints. More recently, he applied an optimized reverse Hausdorff fractional discrete grey power model to predict China’s servo industry development (3 citations), demonstrating his ability to merge theoretical modeling with practical economic forecasting. Liu’s work consistently targets real-world challenges, from space exploration to intelligent sensing, showcasing a rare breadth of expertise.
Research Focus
Key Achievements
Top Papers
- 1
- 2Human-centric Relation Segmentation: Dataset and Solution10 citations · 2021
- 3
- 4