Qidi Wu

Papers

Total Citations

H-Index

About

Qidi Wu is a researcher at the intersection of robotics, machine learning, and biomechanics, with a primary focus on data-driven modeling and control of robotic systems. Their most notable contribution is the development of energy-constrained Lagrangian neural networks, a novel framework that integrates physical principles—specifically energy conservation—into neural network architectures for modeling complex robotic dynamics. This work, published in 2025 and already garnering early citations, demonstrates particular promise in prosthetic applications, where accurate, physically consistent models are critical for safe and efficient human-robot interaction. By embedding Lagrangian mechanics into the learning process, Wu’s approach enables more robust and interpretable models that respect the fundamental laws of physics, bridging the gap between pure data-driven methods and classical control theory. This innovation has the potential to advance adaptive prosthetics, exoskeletons, and autonomous systems, offering a pathway toward more reliable and energy-efficient robotic behaviors. With a growing citation record and a focus on real-world impact, Qidi Wu is emerging as a key contributor to the next generation of physically informed machine learning for robotics.