Identification of LTV Dynamical Models with Smooth or Discontinuous Time Evolution by means of Convex Optimization

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

198 Downloads (Pure)

Abstract

We establish a connection between trend filtering and system identification which results in a family of new identification methods for linear, time-varying (LTV) dynamical models based on convex optimization. We demonstrate how the design of the cost function promotes a model with either a continuous change in dynamics over time, or causes discontinuous changes in model coefficients occurring at a finite (sparse) set of time instances. We further discuss the introduction of priors on the model parameters for situations where excitation is insufficient for identification. The identification problems are cast as convex optimization problems and are applicable to, e.g., ARX models and state-space models with time-varying parameters. We illustrate usage of the methods in simulations of jump-linear systems, a nonlinear robot arm with non-smooth friction and stiff contacts as well as in model-based, trajectory centric reinforcement learning on a smooth nonlinear system.
Original languageEnglish
Title of host publication 2018 IEEE 14th International Conference on Control and Automation (ICCA)
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)978-1-5386-6089-8
DOIs
Publication statusPublished - 2018
EventThe 14th IEEE International Conference on Control and Automation 2018 - Anchorage, Alaska, United States
Duration: 2018 Jun 122018 Jun 15

Conference

ConferenceThe 14th IEEE International Conference on Control and Automation 2018
Country/TerritoryUnited States
CityAnchorage, Alaska
Period2018/06/122018/06/15

Subject classification (UKÄ)

  • Control Engineering

Fingerprint

Dive into the research topics of 'Identification of LTV Dynamical Models with Smooth or Discontinuous Time Evolution by means of Convex Optimization'. Together they form a unique fingerprint.

Cite this