A Caltech Library Service

Neural Stochastic Contraction Metrics for Learning-based Control and Estimation

Tsukamoto, Hiroyasu and Chung, Soon-Jo and Slotine, Jean-Jacques E. (2021) Neural Stochastic Contraction Metrics for Learning-based Control and Estimation. In: 2021 American Control Conference (ACC). IEEE , pp. 1275-1280. ISBN 978-1-6654-4197-1.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We present Neural Stochastic Contraction Metrics (NSCM), a new design framework for provably-stable learning-based control and estimation for a class of stochastic nonlinear systems. It uses a spectrally-normalized deep neural network to construct a contraction metric and its differential Lyapunov function, 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 trained NSCM model allows autonomous systems 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 NCM, as shown in simulation results.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ItemJournal Article ItemCode
Tsukamoto, Hiroyasu0000-0002-6337-2667
Chung, Soon-Jo0000-0002-6657-3907
Slotine, Jean-Jacques E.0000-0002-7161-7812
Additional Information:© 2021 AACC. This work was funded in part by the Raytheon Company and benefited from discussions with Nicholas Boffi and Quang-Cuong Pham.
Group:GALCIT, Center for Autonomous Systems and Technologies (CAST)
Funding AgencyGrant Number
Raytheon CompanyUNSPECIFIED
Subject Keywords:Machine learning, Stochastic optimal control, Observers for nonlinear systems
Record Number:CaltechAUTHORS:20210825-150704832
Persistent URL:
Official Citation:H. Tsukamoto, S. -J. Chung and J. -J. E. Slotine, "Neural Stochastic Contraction Metrics for Learning-based Control and Estimation," 2021 American Control Conference (ACC), 2021, pp. 1275-1280, doi: 10.23919/ACC50511.2021.9482701
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:110417
Deposited By: Tony Diaz
Deposited On:25 Aug 2021 17:06
Last Modified:25 Aug 2021 17:06

Repository Staff Only: item control page