Applications
Learning Forced Multibody Dynamics on Lie Groups
arXiv:2607.12627v1 Announce Type: new Abstract: We propose an architecture for learning the dynamics of mechanical systems based on discrete forced Euler-Lagrange equations on Lie groups using only po
arXiv:2607.12627v1 Announce Type: new Abstract: We propose an architecture for learning the dynamics of mechanical systems based on discrete forced Euler-Lagrange equations on Lie groups using only position data. By formulating the dynamics directly on manifold-valued configuration spaces, the method naturally respects the geometric structure of the systems and preserves geometric invariants and conservation laws. The reliance on position measurements alone makes the framework applicable in settings where velocity data are unavailable or noisy. The approach extends naturally to multibody systems, accommodates external control inputs, and demonstrates strong performance on both synthetic and real-world datasets.
Related
- Advances in Neural Controlled Differential Equations
- Variational Grey-Box Dynamics Matching
- SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
- CT-OT Flow: Estimating Continuous-Time Dynamics from Discrete Temporal Snapshots
- In-Context Learning of Stochastic Differential Equations with Foundation Inference Models
Source: arXiv cs.LG | 2026-07-15