mlsanityData to 14 Oct 2026

Optimal Energy Shaping via Neural Approximators

arXiv 2101.05537 ↗First posted 14 Jan 2021eess.SY cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce optimal energy shaping as an enhancement of classical passivity-based control methods. A promising feature of passivity theory, alongside stability, has traditionally been claimed to be intuitive performance tuning along the execution of a given task. However, a systematic approach to adjust performance within a passive control framework has yet to be developed, as each method relies on few and problem-specific practical insights. Here, we cast the classic energy-shaping control design process in an optimal control framework; once a task-dependent performance metric is defined, an optimal solution is systematically obtained through an iterative procedure relying on neural networks and gradient-based optimization. The proposed method is validated on state-regulation tasks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 14 Jan 2021.

Builds on

23 of 49 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2015Automatic differentiation in machine learning: a surveycited by 855
  5. 2019Hamiltonian Neural Networkscited by 712
  6. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  7. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  8. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  9. 2020Lagrangian Neural Networkscited by 398
  10. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  11. 2019Challenges of Real-World Reinforcement Learningcited by 291
  12. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
11 more
  1. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
  2. 2020Dissecting Neural ODEscited by 153
  3. 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 79
  4. 2020Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEcited by 76
  5. 2018Fashionable Modelling with Fluxcited by 53
  6. 2020Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Datacited by 40
  7. 2020Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Controlcited by 38
  8. 2020Stable Neural Flowscited by 25
  9. 2020TorchDyn: A Neural Differential Equations Librarycited by 17
  10. 2019Port-Hamiltonian Approach to Neural Network Trainingcited by 4
  11. 2020Optimal Control of Port-Hamiltonian Systems: A Time-Continuous Learning Approachcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2021Total Energy Shaping with Neural Interconnection and Damping Assignment -- Passivity Based Controlcited by 5
  2. 2024Optimal Potential Shaping on SE(3) via Neural ODEs on Lie Groupscited by 0
  3. 2024Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systemscited by 0
  4. 2026Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Controlcited by 0