Nonlinear Stochastic Density Steering via Gaussian Mixture Schrodinger Bridges and Multiple Linearizations

TL;DR

This paper introduces a novel multi-linearization method using Gaussian Mixture Models to improve density steering in nonlinear stochastic systems, demonstrated on space transfer scenarios.

Contribution

It proposes a multiple distribution-to-distribution linearization approach that enhances approximation accuracy over traditional single-linearization methods.

Findings

Tighter approximation error bounds than single-linearization.

Effective in high-uncertainty nonlinear regions.

Validated on Earth-to-Mars orbit transfer scenario.

Abstract

The paper studies the optimal density steering problem for nonlinear continuous-time stochastic systems. To accurately capture nonlinear dynamics in high-uncertainty regions that deviate significantly from a nominal linearization point, we introduce the concept of Multiple Distribution-to-Distribution Linearization. The proposed approach first approximates the boundary distributions using Gaussian Mixture Models (GMMs), and decomposes the original nonlinear problem into a collection of Gaussian-to-Gaussian Optimal Covariance Steering (OCS) subproblems between pairs of mixture components. Each elementary OCS problem is solved via local linearization around the mean trajectory connecting the corresponding initial and terminal Gaussian components. The resulting elementary policies are then combined according to their associated conditional densities. We prove that the proposed multi-linearization approach yields tighter approximation error bounds than single-linearization for a broad class of problems. The effectiveness of the approach is demonstrated through numerical experiments on an Earth-to-Mars orbit transfer scenario.