Distributionally Robust GMM Steering Under Wasserstein Ambiguity Sets
- 26 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 10, 13-18
Abstract
This letter addresses the problem of steering a discrete-time linear system from an initial Gaussian Mixture Model (GMM) distribution, where the component weights are uncertain, to a prescribed terminal Gaussian distribution. We formulate a distributionally robust optimal control (DRO) problem by modeling the weight uncertainty via a Wasserstein-type ambiguity set. The resulting non-convex min-max problem is shown to be equivalently transformed into a tractable, deterministic Semidefinite Program (SDP) by leveraging duality theory and convex lifting techniques. The standard nominal (non-robust) controller can fail to satisfy terminal constraints under plausible worst-case weight distributions within the ambiguity set. In contrast, the proposed DRO controller successfully guarantees constraint satisfaction in these scenarios, demonstrating its improved robustness.Keywords
This publication has 20 references indexed in Scilit:
- Steering Large Agent Populations Using Mean-Field Schrödinger Bridges With Gaussian Mixture ModelsIEEE Control Systems Letters, 2025
- Chance-Constrained Gaussian Mixture Steering to a Terminal Gaussian Distribution2024
- Discrete-Time Optimal Covariance Steering via Semidefinite Programming2023
- Distributionally robust optimization using optimal transport for Gaussian mixture modelsOptimization and Engineering, 2023
- A Distributionally Robust Optimization Based Method for Stochastic Model Predictive ControlIEEE Transactions on Automatic Control, 2021
- Wasserstein Distributionally Robust Stochastic Control: A Data-Driven ApproachIEEE Transactions on Automatic Control, 2020
- Optimal Transport for Gaussian Mixture ModelsIEEE Access, 2018
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulationsMathematical Programming, 2017
- Optimal Steering of a Linear Stochastic System to a Final Probability Distribution, Part IIEEE Transactions on Automatic Control, 2015
- Convex Optimization2004