Site Search  

Resources » Publication Details

Publication Details

Reference TypeReport
Author(s)Ting, J.; Theodorou, E.; Schaal, S.
TitleLearning an Outlier-Robust Kalman Filter
Journal/Conference/Book TitleCLMC Technical Report: TR-CLMC-2007-1
Keywordsautomatic outlier detection, Kalman filter, system dynamics, weighted least squares, bayesian statistical learning
AbstractWe introduce a modified Kalman filter that performs robust, real-time outlier detection, without the need for manual parameter tuning by the user. Systems that rely on high quality sensory data (for instance, robotic systems) can be sensitive to data containing outliers. The standard Kalman filter is not robust to outliers, and other variations of the Kalman filter have been proposed to overcome this issue. However, these methods may require manual parameter tuning, use of heuristics or complicated parameter estimation procedures. Our Kalman filter uses a weighted least squares-like approach by introducing weights for each data sample. A data sample with a smaller weight has a weaker contribution when estimating the current time step’s state. Using an incremental variational Expectation-Maximization framework, we learn the weights and system dynamics. We evaluate our Kalman filter algorithm on data from a robotic dog.
Place PublishedLos Angeles, CA
Type of WorkCLMC Technical Report
Link to PDF
Research NotesA longer and more complete version of ECML paper by Ting, Theodorou & Schaal (2007), with the same title.

Designed by: Nerses Ohanyan & Jan Peters
Page last modified on June 20, 2013, at 07:00 PM