mlsanityData to 14 Oct 2026

Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Network for Robotic Dynamics Learning

arXiv 2412.01297 ↗First posted 2 Dec 2024cs.RO cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We present a morphological-symmetry-equivariant heterogeneous graph neural network, namely MS-HGNN, for robotic dynamics learning, that integrates robotic kinematic structures and morphological symmetries into a single graph network. These structural priors are embedded into the learning architecture as constraints, ensuring high generalizability, sample and model efficiency. The proposed MS-HGNN is a versatile and general architecture that is applicable to various multi-body dynamic systems and a wide range of dynamics learning problems. We formally prove the morphological-symmetry-equivariant property of our MS-HGNN and validate its effectiveness across multiple quadruped robot learning problems using both real-world and simulated data. Our code is made publicly available at https://github.com/lunarlab-gatech/MorphSym-HGNN/.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

28 of 44 references.

References · 28

  1. 2017Deep Setscited by 1,421
  2. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  3. 2016Group Equivariant Convolutional Networkscited by 1,165
  4. 2021E(n) Equivariant Graph Neural Networkscited by 965
  5. 2019Hamiltonian Neural Networkscited by 712
  6. 2020Lagrangian Neural Networkscited by 398
  7. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  8. 2018Graph networks as learnable physics engines for inference and controlcited by 244
  9. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
  10. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 116
  11. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
  12. 2021SE(3) Equivariant Graph Neural Networks with Complete Local Framescited by 76
16 more
  1. 2021Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modelingcited by 41
  2. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  3. 2024Symmetry Considerations for Learning Task Symmetric Robot Policiescited by 28
  4. 2024Leveraging Symmetry in RL-based Legged Locomotion Controlcited by 25
  5. 2020GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learningcited by 21
  6. 2021Combining Physics and Deep Learning to learn Continuous-Time Dynamics Modelscited by 20
  7. 2022Compositional Learning of Dynamical System Models Using Port-Hamiltonian Neural Networkscited by 18
  8. 2021Legged Robot State Estimation using Invariant Kalman Filtering and Learned Contact Eventscited by 13
  9. 2024Morphological Symmetries in Roboticscited by 13
  10. 2024Port-Hamiltonian Neural ODE Networks on Lie Groups For Robot Dynamics Learning and Controlcited by 12
  11. 2023On discrete symmetries of robotics systems: A group-theoretic and data-driven analysiscited by 8
  12. 2023SO(2)-Equivariant Downwash Models for Close Proximity Flightcited by 7
  13. 2024MAGIC-VFM: Meta-learning Adaptation for Ground Interaction Control with Visual Foundation Modelscited by 6
  14. 2024MI-HGNN: Morphology-Informed Heterogeneous Graph Neural Network for Legged Robot Contact Perceptioncited by 5
  15. 2021Learning Robot Structure and Motion Embeddings using Graph Neural Networkscited by 4
  16. 2023Hierarchical Meta-learning-based Adaptive Controllercited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulationcited by 5
  2. 2025Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learningcited by 4
  3. 2026Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotioncited by 4
  4. 2026WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systemscited by 1
  5. 2026Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulationcited by 0