mlsanityData to 7 Oct 2026

Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems

arXiv 1907.04489 ↗First posted 10 Jul 2019cs.RO cs.LG cs.SYcited by 32

Not on the map. Why?

Abstract (arXiv)

Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such as deep reinforcement learning, require an unrealistic amount of interaction with the real system, do not yield any performance guarantees, and do not make good use of extensive insights from model-based control. In particular, common black-box approaches -- that abandon all insight from control -- are not suitable for complex robot systems. We propose a deep control approach as a bridge between the solid theoretical foundations of energy-based control and the flexibility of deep learning. To accomplish this goal, we extend Deep Lagrangian Networks (DeLaN) to not only adhere to Lagrangian Mechanics but also ensure conservation of energy and passivity of the learned representation. This novel extension is embedded within generic model-based control laws to enable energy control of under-actuated systems. The resulting DeLaN for energy control (DeLaN 4EC) is the first model learning approach using generic function approximation that is capable of learning energy control. DeLaN 4EC exhibits excellent real-time control on the physical Furuta Pendulum and learns to swing-up the pendulum while the control law using system identification does not.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 6; 2022: 6; 2023: 7; 2024: 2; 2025: 7; 2026: 3.

32 papers.

Sort:

By area:

  1. 2021Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Controlcited by 37
  2. 2021Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Modelscited by 33
  3. 2020Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learningcited by 27
  4. 2021Learning Dynamics Models for Model Predictive Agentscited by 21
  5. 2023Deep Learning in Deterministic Computational Mechanicscited by 21
  6. 2021Combining Physics and Deep Learning to learn Continuous-Time Dynamics Modelscited by 20
  7. 2022Physics-Informed Model-Based Reinforcement Learningcited by 17
  8. 2021OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulationcited by 7
  9. 2022Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systemscited by 7
  10. 2021Continuous-Time Fitted Value Iteration for Robust Policiescited by 6
  11. 2023Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learningcited by 5
  12. 2022ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Biascited by 4
20 more
  1. 2023A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identificationcited by 4
  2. 2022Symplectic Momentum Neural Networks -- Using Discrete Variational Mechanics as a prior in Deep Learningcited by 3
  3. 2023Discovering interpretable Lagrangian of dynamical systems from datacited by 3
  4. 2025Generalizable and Fast Surrogates: Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networkscited by 3
  5. 2022End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Controlcited by 2
  6. 2023A Bayesian framework for discovering interpretable Lagrangian of dynamical systems from datacited by 2
  7. 2023MPC-Inspired Reinforcement Learning for Verifiable Model-Free Controlcited by 2
  8. 2025Context-Aware Deep Lagrangian Networks for Model Predictive Controlcited by 2
  9. 2025Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration Interfacecited by 1
  10. 2025Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identificationcited by 1
  11. 2025Learning Physically Consistent Lagrangian Control Models Without Acceleration Measurementscited by 1
  12. 2022KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Imagescited by 0
  13. 2023Graph Neural Networks for Dynamic Modeling of Roller Bearingcited by 0
  14. 2024Joint torques prediction of a robotic arm using neural networkscited by 0
  15. 2024Diminishing Return of Value Expansion Methodscited by 0
  16. 2025ServoLNN: Lagrangian Neural Networks Driven by Servomechanismscited by 0
  17. 2025Geometric Fault-Tolerant Neural Network Tracking Control of Unknown Systems on Matrix Lie Groupscited by 0
  18. 2026Feasibility-aware Imitation Learning from Observation with Multimodal Feedbackcited by 0
  19. 2026Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupedscited by 0
  20. 2026A Bayesian Filtering Approach for Learning Lagrangian Dynamics from Noisy Measurementscited by 0