mlsanityData to 14 Oct 2026

Investigating Lagrangian Neural Networks for Infinite Horizon Planning in Quadrupedal Locomotion

arXiv 2506.16079 ↗First posted 19 Jun 2025cs.RO cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Lagrangian Neural Networks (LNNs) present a principled and interpretable framework for learning the system dynamics by utilizing inductive biases. While traditional dynamics models struggle with compounding errors over long horizons, LNNs intrinsically preserve the physical laws governing any system, enabling accurate and stable predictions essential for sustainable locomotion. This work evaluates LNNs for infinite horizon planning in quadrupedal robots through four dynamics models: (1) full-order forward dynamics (FD) training and inference, (2) diagonalized representation of Mass Matrix in full order FD, (3) full-order inverse dynamics (ID) training with FD inference, (4) reduced-order modeling via torso centre-of-mass (CoM) dynamics. Experiments demonstrate that LNNs bring improvements in sample efficiency (10x) and superior prediction accuracy (up to 2-10x) compared to baseline methods. Notably, the diagonalization approach of LNNs reduces computational complexity while retaining some interpretability, enabling real-time receding horizon control. These findings highlight the advantages of LNNs in capturing the underlying structure of system dynamics in quadrupeds, leading to improved performance and efficiency in locomotion planning and control. Additionally, our approach achieves a higher control frequency than previous LNN methods, demonstrating its potential for real-world deployment on quadrupeds.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 29 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

24 of 29 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  5. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  6. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  7. 2020Lagrangian Neural Networkscited by 398
  8. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  9. 2017Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equationscited by 373
  10. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  11. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
  12. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 161
12 more
  1. 2015Model Predictive Path Integral Control using Covariance Variable Importance Samplingcited by 124
  2. 2018Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Controlcited by 113
  3. 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 105
  4. 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 66
  5. 2020Learning Off-Policy with Online Planningcited by 53
  6. 2021Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modelingcited by 41
  7. 2023Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Responsecited by 39
  8. 2022Deconstructing the Inductive Biases of Hamiltonian Neural Networkscited by 31
  9. 2021Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learningcited by 28
  10. 2024Barrier Functions Inspired Reward Shaping for Reinforcement Learningcited by 11
  11. 2024PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotioncited by 7
  12. 2021Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matchingcited by 0
  2. 2026Data-Driven Physics Embedded Dynamics with Predictive Control and Reinforcement Learning for Quadrupedscited by 0
  3. 2026LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splattingcited by 0