Papers
3
Total Citations
22
H-Index
2
About
Yuanzhe Su is a rising researcher at the intersection of robotics, tactile sensing, and human motion tracking. His work focuses on developing intelligent algorithms that enable robots to perceive and interact with their environment more naturally. Su’s most cited paper, “A Shortcut Enhanced LSTM-GCN Network for Multi-Sensor Based Human Motion Tracking” (2023, 17 citations), addresses a key challenge in robotics: reducing reliance on expensive optical motion capture by fusing data from multiple wearable sensors. He introduced a novel hybrid architecture that overcomes the limitations of traditional convolutions in handling dynamic joint positions, offering a more adaptive and cost-effective solution for motion tracking. In tactile learning, Su has pioneered the use of probabilistic spiking neural networks for continual learning, allowing robots to retain and adapt tactile knowledge as they encounter new tasks—a critical step toward lifelong robotic learning. He has also explored self-supervised contrastive learning for grasp outcome prediction, demonstrating that robots can learn to predict successful grasps without labeled data. Su’s work is notable for its focus on practical, data-efficient methods that push toward more autonomous and perceptive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3