Qihang Su
Papers
1
Total Citations
2
H-Index
1
About
Qihang Su is a researcher advancing the frontier of physics-informed machine learning, with a primary focus on Hamiltonian neural networks and rigid body dynamics. His most-cited work introduces a groundbreaking deep modeling methodology for six-degree-of-freedom (6-DoF) rigid body systems, leveraging energy variation estimation to overcome long-standing challenges in modeling complexity and accuracy. By embedding Hamiltonian principles into neural network architectures, Su’s approach enables more physically consistent and data-efficient simulations of controlled rigid body motion—a critical capability for applications in robotics, aerospace, and autonomous systems. Though early in his career, his 2023 paper has already garnered attention, accumulating 2 citations as a foundational reference for researchers seeking to bridge classical mechanics and modern deep learning. Su’s contributions stand out for their elegant fusion of theoretical physics with practical computational tools, offering a pathway to more interpretable and robust dynamic models. As the field of scientific machine learning rapidly evolves, his work positions him as an emerging voice in the development of energy-aware, structure-preserving neural networks for complex physical systems.
Research Focus
Key Achievements
Top Papers
- 1