论文标题
使用局部稳定先验学习动态系统
Learning Dynamical Systems using Local Stability Priors
论文作者
论文摘要
提出了一种同时学习向量场的耦合计算方法，并提出了从系统的产生轨迹中的平衡点吸引区域。非线性识别利用局部稳定信息作为系统的先验，有效地赋予了这种重要的结构特性。此外，对吸引区域的知识通过告知生成轨迹的初始条件的选择，并通过启用系统的lyapunov函数作为正规化项来扮演实验设计角色。数值结果表明，所提出的方法允许有效采样，并在其吸引力区域内部近似中对动力学进行了准确的估计。
A coupled computational approach to simultaneously learn a vector field and the region of attraction of an equilibrium point from generated trajectories of the system is proposed. The nonlinear identification leverages the local stability information as a prior on the system, effectively endowing the estimate with this important structural property. In addition, the knowledge of the region of attraction plays an experiment design role by informing the selection of initial conditions from which trajectories are generated and by enabling the use of a Lyapunov function of the system as a regularization term. Numerical results show that the proposed method allows efficient sampling and provides an accurate estimate of the dynamics in an inner approximation of its region of attraction.
