Chenyi Weng
Papers
1
Total Citations
2
H-Index
1
About
Chenyi Weng is a researcher advancing the frontiers of human-robot collaboration through innovative machine learning and sensor-based activity recognition. Their key research areas include human activity recognition (HAR), graph convolutional networks (GCNs), and adaptive skeleton-based modeling for interactive robotics. Weng’s most notable contribution is the development of ATD-GCN, a novel framework that leverages adaptive skeleton tree-decomposition to accurately interpret human movements in collaborative settings. This work, published in 2025, has already garnered 2 citations, signaling early impact in a rapidly evolving field. By enabling robots to understand complex human actions in real time, Weng’s research directly enhances safety and efficiency in shared workspaces, from manufacturing floors to assistive technologies. Their approach stands out for its adaptability, allowing the model to generalize across diverse human poses and interaction scenarios. As the demand for intuitive human-robot interfaces grows, Weng’s contributions are poised to influence next-generation autonomous systems, bridging the gap between raw sensor data and meaningful robotic response.
Research Focus
Key Achievements
Top Papers
- 1