Neural Stochastic Contraction Metrics for Learning-based Control and Estimation
From MaRDI portal
Publication:6353113
arXiv2011.03168MaRDI QIDQ6353113
Author name not available (Why is that?)
Publication date: 5 November 2020
Abstract: We present Neural Stochastic Contraction Metrics (NSCM), a new design framework for provably-stable robust control and estimation for a class of stochastic nonlinear systems. It uses a spectrally-normalized deep neural network to construct a contraction metric, sampled via simplified convex optimization in the stochastic setting. Spectral normalization constrains the state-derivatives of the metric to be Lipschitz continuous, thereby ensuring exponential boundedness of the mean squared distance of system trajectories under stochastic disturbances. The NSCM framework allows autonomous agents to approximate optimal stable control and estimation policies in real-time, and outperforms existing nonlinear control and estimation techniques including the state-dependent Riccati equation, iterative LQR, EKF, and the deterministic neural contraction metric, as illustrated in simulation results.
Has companion code repository: https://github.com/astrohiro/nscm
This page was built for publication: Neural Stochastic Contraction Metrics for Learning-based Control and Estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353113)
