# Structured Mechanical Models for Robot Learning and Control

arXiv: https://arxiv.org/abs/2004.10301 · HTML: https://mlsanity.com/paper/2004.10301/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 21 of 21)

- [Investigating Compounding Prediction Errors in Learned Dynamics Models](https://mlsanity.com/paper/2203.09637/) (2022)
- [Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling](https://mlsanity.com/paper/2109.06407/) (2021)
- [Deconstructing the Inductive Biases of Hamiltonian Neural Networks](https://mlsanity.com/paper/2202.04836/) (2022)
- [Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models](https://mlsanity.com/paper/2110.01894/) (2021)
- [Compositional Learning of Dynamical System Models Using Port-Hamiltonian Neural Networks](https://mlsanity.com/paper/2212.00893/) (2022)
- [Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs](https://mlsanity.com/paper/2201.05715/) (2022)
- [Geometry-Informed Neural Networks](https://mlsanity.com/paper/2402.14009/) (2024)
- [How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations](https://mlsanity.com/paper/2306.06335/) (2023)
- [A Hybrid Rule-Based and Data-Driven Approach to Driver Modeling through Particle Filtering](https://mlsanity.com/paper/2108.12820/) (2021)
- [Guaranteed Conformance of Neurosymbolic Models to Natural Constraints](https://mlsanity.com/paper/2212.01346/) (2022)
- [Data-Driven Control with Inherent Lyapunov Stability](https://mlsanity.com/paper/2303.03157/) (2023)
- [Learning Control-Oriented Dynamical Structure from Data](https://mlsanity.com/paper/2302.02529/) (2023)
- [Learning Modular Simulations for Homogeneous Systems](https://mlsanity.com/paper/2210.16294/) (2022)
- [Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System](https://mlsanity.com/paper/2011.10605/) (2020)
- [Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand](https://mlsanity.com/paper/2201.02753/) (2022)
- [End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control](https://mlsanity.com/paper/2205.13804/) (2022)
- [Sample Efficient Dynamics Learning for Symmetrical Legged Robots:Leveraging Physics Invariance and Geometric Symmetries](https://mlsanity.com/paper/2210.07329/) (2022)
- [Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control](https://mlsanity.com/paper/2301.03565/) (2023)
- [Learning Long-Horizon Predictions for Quadrotor Dynamics](https://mlsanity.com/paper/2407.12964/) (2024)
- [Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification](https://mlsanity.com/paper/2506.17994/) (2025)
- [Training Structured Mechanical Models by Minimizing Discrete Euler-Lagrange Residual](https://mlsanity.com/paper/2105.01811/) (2021)

## Abstract (arXiv)

Model-based methods are the dominant paradigm for controlling robotic systems, though their efficacy depends heavily on the accuracy of the model used. Deep neural networks have been used to learn models of robot dynamics from data, but they suffer from data-inefficiency and the difficulty to incorporate prior knowledge. We introduce Structured Mechanical Models, a flexible model class for mechanical systems that are data-efficient, easily amenable to prior knowledge, and easily usable with model-based control techniques. The goal of this work is to demonstrate the benefits of using Structured Mechanical Models in lieu of black-box neural networks when modeling robot dynamics. We demonstrate that they generalize better from limited data and yield more reliable model-based controllers on a variety of simulated robotic domains.