Showing eess.SYShow all
2 papers · 1 filter
eess.SY2026
Energy-based Regularization for Learning Residual Dynamics in Neural MPC for Omnidirectional Aerial Robots
Johannes Kübel, Henrik Krauss, Jinjie Li +1
Data-driven Model Predictive Control (MPC) has lately been a core research subject in the field of control theory. The combination of an optimal control framework with deep learnin…
eess.SY2024
Domain-decoupled Physics-informed Neural Networks with Closed-form Gradients for Fast Model Learning of Dynamical Systems
Henrik Krauss, Tim-Lukas Habich, Max Bartholdt +2
Physics-informed neural networks (PINNs) are trained using physical equations and can also incorporate unmodeled effects by learning from data. PINNs for control (PINCs) of dynamic…