Papers
1
Total Citations
19
H-Index
1
About
Weikun Deng is a researcher at the forefront of integrating machine learning with classical physics to advance robotic manipulation. His work centers on developing physics-informed machine learning (PIML) models that bridge the gap between data-driven approaches and physical laws, particularly for solving inverse dynamics problems in robotic manipulators. In his most-cited paper (2024, 19 citations), Deng introduces a novel framework that embeds physical constraints directly into neural network architectures, enabling more accurate and sample-efficient predictions of joint torques and forces. This contribution is pivotal for improving the control and safety of robots in complex, real-world environments. By reducing reliance on large labeled datasets, his approach accelerates the deployment of intelligent robotic systems in manufacturing, healthcare, and autonomous operations. Deng’s research not only demonstrates the power of hybrid modeling but also sets a foundation for future work in interpretable AI for robotics, earning recognition for its practical impact and methodological innovation.
Research Focus
Key Achievements
Top Papers
- 1