Learning Lie Group Generators from Trajectories

This work investigates the inverse problem of generator recovery in matrix Lie groups from discretized trajectories. Let $G$ be a real matrix Lie group and $\mathfrak{g} = \text{Lie}(G)$ its corresponding Lie algebra. A smooth trajectory $\gamma($t$)$ generated by a fixed Lie algebra element $\xi \in \mathfrak{g}$ follows the exponential flow $\gamma($t$) = g_0 \cdot \exp(t \xi)$. The central task addressed in this work is the reconstruction of such a latent generator $\xi$ from a discretized sequence of poses $\{g_0, g_1, \dots, g_T\} \subset G$, sampled at uniform time intervals. This problem is formulated as a data-driven regression from normalized sequences of discrete Lie algebra increments $\log\left(g_{t}^{-1} g_{t+1}\right)$ to the constant generator $\xi \in \mathfrak{g}$. A feedforward neural network is trained to learn this mapping across several groups, including \text{SE(2)}, \text{SE(3)}, \text{SO(3)}, and \text{SL(2,\mathbb{R})}. It demonstrates strong empirical accuracy under both clean and noisy conditions, which validates the viability of data-driven recovery of Lie group generators using shallow neural architectures. This is Lie-RL GitHub Repothis https URL. Feel free to make suggestions and collaborations!

@article{hu2025_2504.03220,
  title={ Learning Lie Group Generators from Trajectories },
  author={ Lifan Hu },
  journal={arXiv preprint arXiv:2504.03220},
  year={ 2025 }
}