Optimal Energy Shaping via Neural Approximators

DOI10.1137/21M1414279MaRDI QIDQ5868542zbMATH OpenOpenAlexFDO

Authors Stefano Massaroli, Michael Poli, F. Califano, Jinkyoo Park, Atsushi Yamashita, Hajime Asama

Publication date 21 September 2022

Published in SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.05537

zbMATH Keywords

neural approximatorspassivity-based controlport-Hamiltonian systemsstability

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Input-output approaches in control theory (93D25)

Recommendations

• Data-driven passivity-based control of underactuated mechanical systems via interconnection and damping assignment
• scientific article; zbMATH DE number 1816773
• Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
• Passivity-based optimal control of discrete-time nonlinear systems
• Optimal control of port-Hamiltonian systems: a continuous-time learning approach

Cites work

• A family of embedded Runge-Kutta formulae
• A Stochastic Approximation Method
• Control by Interconnection and Standard Passivity-Based Control of Port-Hamiltonian Systems
• Control of interactive robotic interfaces. A port-Hamiltonian approach
• Energy-aware robotics
• scientific article; zbMATH DE number 3167340 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 6982909 (Why is no real title available?)
• L\(_2\) gain and passivity techniques in nonlinear control.
• Local convergence of the steepest descent method in Hilbert spaces
• Modeling and Control of Complex Physical Systems
• Modeling and IPC control of interactive mechanical systems. A coordinate-free approach
• Optimal control of port-Hamiltonian systems: a continuous-time learning approach
• Passivity, feedback equivalence, and the global stabilization of minimum phase nonlinear systems
• Port-Hamiltonian Systems in Adaptive and Learning Control: A Survey
• Reinforcement learning. An introduction

Cited in

(5)

• scientific article; zbMATH DE number 2000822 (Why is no real title available?)
• A Neural Network Approach to High-Dimensional Optimal Switching Problems with Jumps in Energy Markets
• Discovering efficient periodic behaviors in mechanical systems via neural approximators
• Structural inference of networked dynamical systems with universal differential equations
• Learning passive policies with virtual energy tanks in robotics

Describes a project that uses

Uses Software

• NeuralCDE
• torchcde
• TensorFlow
• DiffSharp
• PyTorch
• Adam
• JAX
• FFJORD
• TorchDyn
• GitHub
• SymODEN

This page was built for publication: Optimal Energy Shaping via Neural Approximators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5868542)