Saved in:
Bibliographic Details
Main Authors: Musavi, Negin, Guo, Ziyao, Dullerud, Geir, Li, Yingying
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00656
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913582318354432
author Musavi, Negin
Guo, Ziyao
Dullerud, Geir
Li, Yingying
author_facet Musavi, Negin
Guo, Ziyao
Dullerud, Geir
Li, Yingying
contents This paper focuses on the system identification of an important class of nonlinear systems: linearly parameterized nonlinear systems, which enjoys wide applications in robotics and other mechanical systems. We consider two system identification methods: least-squares estimation (LSE), which is a point estimation method; and set-membership estimation (SME), which estimates an uncertainty set that contains the true parameters. We provide non-asymptotic convergence rates for LSE and SME under i.i.d. control inputs and control policies with i.i.d. random perturbations, both of which are considered as non-active-exploration inputs. Compared with the counter-example based on piecewise-affine systems in the literature, the success of non-active exploration in our setting relies on a key assumption on the system dynamics: we require the system functions to be real-analytic. Our results, together with the piecewise-affine counter-example, reveal the importance of differentiability in nonlinear system identification through non-active exploration. Lastly, we numerically compare our theoretical bounds with the empirical performance of LSE and SME on a pendulum example and a quadrotor example.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00656
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
Musavi, Negin
Guo, Ziyao
Dullerud, Geir
Li, Yingying
Systems and Control
This paper focuses on the system identification of an important class of nonlinear systems: linearly parameterized nonlinear systems, which enjoys wide applications in robotics and other mechanical systems. We consider two system identification methods: least-squares estimation (LSE), which is a point estimation method; and set-membership estimation (SME), which estimates an uncertainty set that contains the true parameters. We provide non-asymptotic convergence rates for LSE and SME under i.i.d. control inputs and control policies with i.i.d. random perturbations, both of which are considered as non-active-exploration inputs. Compared with the counter-example based on piecewise-affine systems in the literature, the success of non-active exploration in our setting relies on a key assumption on the system dynamics: we require the system functions to be real-analytic. Our results, together with the piecewise-affine counter-example, reveal the importance of differentiability in nonlinear system identification through non-active exploration. Lastly, we numerically compare our theoretical bounds with the empirical performance of LSE and SME on a pendulum example and a quadrotor example.
title Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
topic Systems and Control
url https://arxiv.org/abs/2411.00656