Learning Lie Group Generators from Trajectories
This addresses the inverse problem of generator recovery in matrix Lie groups, which is incremental as it applies existing neural network methods to a specific mathematical domain.
The paper tackles the problem of recovering Lie group generators from discretized trajectories by training a feedforward neural network to map discrete Lie algebra increments to constant generators, achieving strong empirical accuracy under clean and noisy conditions across groups like SE(2) and SO(3).
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 $γ($t$)$ generated by a fixed Lie algebra element $ξ\in \mathfrak{g}$ follows the exponential flow $γ($t$) = g_0 \cdot \exp(t ξ)$. The central task addressed in this work is the reconstruction of such a latent generator $ξ$ 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 $ξ\in \mathfrak{g}$. 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 Repo https://github.com/Anormalm/LieRL-on-Trajectories. Feel free to make suggestions and collaborations!