Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912444223324160 |
|---|---|
| author | Trinh, Minh Geist, Andreas René Monnet, Josefine Vilceanu, Stefan Trimpe, Sebastian Brecher, Christian |
| author_facet | Trinh, Minh Geist, Andreas René Monnet, Josefine Vilceanu, Stefan Trimpe, Sebastian Brecher, Christian |
| contents | Accurate inverse dynamics models are essential tools for controlling industrial robots. Recent research combines neural network regression with inverse dynamics formulations of the Newton-Euler and the Euler-Lagrange equations of motion, resulting in so-called Newtonian neural networks and Lagrangian neural networks, respectively. These physics-informed models seek to identify unknowns in the analytical equations from data. Despite their potential, current literature lacks guidance on choosing between Lagrangian and Newtonian networks. In this study, we show that when motor torques are estimated instead of directly measuring joint torques, Lagrangian networks prove less effective compared to Newtonian networks as they do not explicitly model dissipative torques. The performance of these models is compared to neural network regression on data of a MABI MAX 100 industrial robot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17994 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification Trinh, Minh Geist, Andreas René Monnet, Josefine Vilceanu, Stefan Trimpe, Sebastian Brecher, Christian Robotics Machine Learning I.2.9; I.2.6; I.6.4 Accurate inverse dynamics models are essential tools for controlling industrial robots. Recent research combines neural network regression with inverse dynamics formulations of the Newton-Euler and the Euler-Lagrange equations of motion, resulting in so-called Newtonian neural networks and Lagrangian neural networks, respectively. These physics-informed models seek to identify unknowns in the analytical equations from data. Despite their potential, current literature lacks guidance on choosing between Lagrangian and Newtonian networks. In this study, we show that when motor torques are estimated instead of directly measuring joint torques, Lagrangian networks prove less effective compared to Newtonian networks as they do not explicitly model dissipative torques. The performance of these models is compared to neural network regression on data of a MABI MAX 100 industrial robot. |
| title | Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification |
| topic | Robotics Machine Learning I.2.9; I.2.6; I.6.4 |
| url | https://arxiv.org/abs/2506.17994 |