A CONSISTENTLY CONVERGENT OBE ALGORITHM WITH AUTOMATIC ESTIMATION OF ERROR-BOUNDS

Authors
LIN TM NAYERI M DELLER JR
Citation
Tm. Lin et al., A CONSISTENTLY CONVERGENT OBE ALGORITHM WITH AUTOMATIC ESTIMATION OF ERROR-BOUNDS, International journal of adaptive control and signal processing, 12(4), 1998, pp. 305-324
Citations number
33
Categorie Soggetti
Robotics & Automatic Control","Robotics & Automatic Control","Engineering, Eletrical & Electronic
Journal title
International journal of adaptive control and signal processing → ACNP
ISSN journal
08906327
Volume
12
Issue
4
Year of publication
1998
Pages
305 - 324
Database
ISI
SICI code
0890-6327(1998)12:4<305:ACCOAW>2.0.ZU;2-H
Abstract
Conventional optimal bounding ellipsoid (OBE) algorithms require a pri ori knowledge of error bounds which is unknown in most applications. C onservative (overestimated) error bounds used in practice may lead to inconsistent parameter estimation. This paper presents an enhanced OBE algorithm that is proven to be consistently convergent without a prio ri knowledge of error bounds. Only a lower bound of the 'tail probabil ity' of the disturbance process is required. Simulations comparing con ventional and the enhanced OBE algorithm is provided. (C) 1998 John Wi ley & Sons, Ltd.