期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 69, 期 -, 页码 5963-5978出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2021.3118540
关键词
Uncertainty; Linear systems; State estimation; Estimation; Measurement uncertainty; Optimization; Kalman filters; State estimation; linear system; distributional robustness; model uncertainty; moment ambiguity set; nonlinear semidefinite programming
资金
- NationalNatural Science Foundation of China [72071139]
- Natural Science Foundation ofChina [12001286]
- Startup Foundation for Introducing Talent of NUIST [2020r003]
- [NRF-RSS2016-004]
This paper introduces a new framework for distributionally robust state estimation in linear Markov systems, which efficiently deals with uncertainties in real linear systems and demonstrates advantages over existing methods through intensive experiments.
Modeling uncertainties for real linear systems are unavoidable. These uncertainties can significantly degrade the performance of optimal state estimators designed for nominal system models. The challenge is quantifying such uncertainties and devising robust estimators that are insensitive to them. This paper is therefore concerned with distributionally robust state estimation for linear Markov systems. We propose a new modeling framework that describes uncertainties using a family of distributions so that the worst-case robust estimate in the state space is made over the least-favorable distribution. This framework uses only one or two scalars to express the uncertainty set and does not require the structural information of model uncertainties. Furthermore, the moment-based ambiguity set is suggested to embody the distributional uncertainty family. As a result, the estimation problem transforms into a nonlinear semidefinite program with linear constraints, which can be analytically and efficiently solved. Intensive experiments illustrate the advantages of the proposed framework over existing methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据