Papers
14
Total Citations
253
H-Index
7
About
Yijiong Lin is a robotics researcher specializing in tactile sensing, sim-to-real deep reinforcement learning, and dexterous robotic manipulation. His work addresses a fundamental challenge in modern robotics: enabling robots to interact intelligently with their physical environment through rich touch perception, often using low-cost, high-resolution vision-based tactile sensors. Lin's most significant contributions include the development of accessible tactile sensing platforms and simulation frameworks. His DigiTac sensor and the Tactile Gym 2.0 environment (50 citations) have lowered barriers to entry for tactile robotics research, democratizing access to high-resolution touch data. His work on bimanual tactile manipulation through sim-to-real reinforcement learning (34 citations) pushes toward human-level robot dexterity in complex, underexplored settings. He has also pioneered 3D shape reconstruction from tactile data with TouchSDF and explored interpretable tactile perception using graph neural networks. With citations spanning sensor design, non-prehensile manipulation, anomaly recovery, and attention mechanisms for robust control, Lin's research portfolio demonstrates both technical breadth and practical impact. His cumulative citation count exceeding 240 reflects growing community recognition of his contributions to making tactile robotics more capable, interpretable, and widely accessible.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7Graph Neural Networks for Interpretable Tactile Sensing9 citations · 2022
- 8Classification of Vision-Based Tactile Sensors: A Review5 citations · 2025
- 9
- 10