About

Yupo Zhang is a leading researcher at the intersection of robotics, tactile perception, and neuromorphic computing, with a focus on enabling robots to interact with the physical world through a refined sense of touch. Their work addresses critical challenges in robotic manipulation, particularly for high-precision industrial tasks like snap-fit assembly in electronics manufacturing. Zhang’s major contributions include pioneering the use of event-based optical sensors (Evetac) with sparse probabilistic spiking neural networks to dramatically improve the speed and accuracy of tactile recognition. They have also advanced continual learning in robotics through TactCLNet, a generative replay framework that allows robots to learn new tactile tasks without forgetting previous ones, and developed TempTrans-MIL, a general method for processing complex multimodal tactile time-series data. With over 19 citations across six recent publications (2023-2025), Zhang’s research is gaining rapid traction. Their innovative self-supervised contrastive learning approach for grasp outcome prediction further demonstrates a commitment to reducing the need for labeled data. Zhang is at the forefront of making robotic touch more adaptive, efficient, and intelligent for real-world applications.

Research Focus

Key Achievements

3
H-Index
6
Papers
19
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Multi-Branch Multi-Scale Channel Fusion Graph Convolutional Networks With Transfer Cost for Robotic Tactile Recognition Tasks
4 citations · 2025
📈 Most Prolific Year: 2025 (3 Papers)
🤝 Key Collaborators: 17
🏛 Institutions: Southern University of Science and Technology, Chinese Academy of Sciences, Institute of Art, Shenzhen Institutes of Advanced Technology

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago