mlsanityData to 7 Oct 2026

Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network

arXiv 2209.11588 ↗First posted 23 Sep 2022cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Lagrangian and Hamiltonian neural networks (LNNs and HNNs, respectively) encode strong inductive biases that allow them to outperform other models of physical systems significantly. However, these models have, thus far, mostly been limited to simple systems such as pendulums and springs or a single rigid body such as a gyroscope or a rigid rotor. Here, we present a Lagrangian graph neural network (LGNN) that can learn the dynamics of articulated rigid bodies by exploiting their topology. We demonstrate the performance of LGNN by learning the dynamics of ropes, chains, and trusses with the bars modeled as rigid bodies. LGNN also exhibits generalizability -- LGNN trained on chains with a few segments exhibits generalizability to simulate a chain with large number of links and arbitrary link length. We also show that the LGNN can simulate unseen hybrid systems including bars and chains, on which they have not been trained on. Specifically, we show that the LGNN can be used to model the dynamics of complex real-world structures such as the stability of tensegrity structures. Finally, we discuss the non-diagonal nature of the mass matrix and its ability to generalize in complex systems.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

17 of 27 references.

References · 17

  1. 2017Graph Attention Networkscited by 8,854
  2. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  3. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  4. 2019Hamiltonian Neural Networkscited by 702
  5. 2020Lagrangian Neural Networkscited by 388
  6. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  7. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 205
  8. 2019Hamiltonian Graph Networks with ODE Integratorscited by 107
  9. 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 102
  10. 2020Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Datacited by 40
  11. 2021Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Controlcited by 37
  12. 2020Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanicscited by 32
5 more
  1. 2022Deconstructing the Inductive Biases of Hamiltonian Neural Networkscited by 31
  2. 2021Constraint-based graph network simulatorcited by 27
  3. 2022Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systemscited by 20
  4. 2020Learning Physical Constraints with Neural Projectionscited by 19
  5. 2022Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networkscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 1; 2025: 7; 2026: 5.

22 papers.

Sort:

  1. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  2. 2023Mirage: Model-Agnostic Graph Distillation for Graph Classificationcited by 13
  3. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  4. 2023GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Setscited by 7
  5. 2023StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapescited by 4
  6. 2023Discovering interpretable Lagrangian of dynamical systems from datacited by 3
  7. 2025Dynami-CAL GraphNet: A Physics-Informed Graph Neural Network Conserving Linear and Angular Momentum for Dynamical Systemscited by 3
  8. 2023Graph Neural Stochastic Differential Equations for Learning Brownian Dynamicscited by 2
  9. 2023A Bayesian framework for discovering interpretable Lagrangian of dynamical systems from datacited by 2
  10. 2025Rapid training of Hamiltonian graph networks using random featurescited by 2
  11. 2025Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Frameworkcited by 2
  12. 2026Super-resolution of turbulent reacting flows on complex meshes using graph neural networkscited by 2
10 more
  1. 2026NeuROK: Generative 4D Neural Object Kinematicscited by 2
  2. 2023Discovering Symbolic Laws Directly from Trajectories with Hamiltonian Graph Neural Networkscited by 1
  3. 2024Bonsai: Gradient-free Graph Condensation for Node Classificationcited by 1
  4. 2025Do Two AI Scientists Agree?cited by 1
  5. 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recoursecited by 1
  6. 2025Rigid Body Adversarial Attackscited by 0
  7. 2025TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flowscited by 0
  8. 2026HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimationcited by 0
  9. 2026GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyondcited by 0
  10. 2026LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splattingcited by 0