Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning
This work addresses the challenge of modeling dissipative physical systems for applications in energy-based control, though it appears incremental as it builds on existing Hamiltonian dynamics encoding methods.
The authors tackled the problem of inferring physical system dynamics with dissipation from observed trajectories, resulting in a deep learning architecture that improves prediction accuracy while reducing network size.
In this work, we introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To improve prediction accuracy while reducing network size, Dissipative SymODEN encodes the port-Hamiltonian dynamics with energy dissipation and external input into the design of its computation graph and learns the dynamics in a structured way. The learned model, by revealing key aspects of the system, such as the inertia, dissipation, and potential energy, paves the way for energy-based controllers.