Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics

In this paper, an innovative algorithm for averaging a set of multivariate time series with different lengths based on Constrained Dynamic Time Warping (CDTW) is proposed. This approach relies on the CDTW to provide the non-linear alignment of the multivariate time series, and employs the proposed M...

Full description

Bibliographic Details
Main Authors: Irati Rasines, Anthony Remazeilles, Miguel Prada, Itziar Cabanes
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10198412/
_version_ 1797752053189050368
author Irati Rasines
Anthony Remazeilles
Miguel Prada
Itziar Cabanes
author_facet Irati Rasines
Anthony Remazeilles
Miguel Prada
Itziar Cabanes
author_sort Irati Rasines
collection DOAJ
description In this paper, an innovative algorithm for averaging a set of multivariate time series with different lengths based on Constrained Dynamic Time Warping (CDTW) is proposed. This approach relies on the CDTW to provide the non-linear alignment of the multivariate time series, and employs the proposed Minimum Cost Averaging (MCA) technique to identify the optimum matches and get equal-length time series. MCA-CDTW is a task-agnostic approach that after selecting a reference curve, transforms the rest of the demonstrations in the set to obtain new curves that are time-aligned with the reference. From these transformed curves, not only the mean but also the signal variability can be directly extracted. This technique provides smooth mean curves even when there are large deviations between the demonstrations in the set, and still the complexity of the proposed algorithm is significantly reduced compared to other averaging techniques from the literature. When learning techniques are used to teach a motion to a robotic system, obtaining smooth trajectories is important to achieve good robotic behaviors. The new algorithm MCA-CDTW is tested and compared on two different databases: a literature database where humans move a robotic arm with kinaesthetic teaching, and a set of recordings of a teleoperated robotic arm performing laboratory manipulation. On both datasets, it is demonstrated that the new approach is providing smooth average trajectories.
first_indexed 2024-03-12T16:58:00Z
format Article
id doaj.art-b192fdc8e80b4b359314c50c90ae6029
institution Directory Open Access Journal
issn 2169-3536
language English
last_indexed 2024-03-12T16:58:00Z
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj.art-b192fdc8e80b4b359314c50c90ae60292023-08-07T23:00:28ZengIEEEIEEE Access2169-35362023-01-0111806008061210.1109/ACCESS.2023.330072010198412Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in RoboticsIrati Rasines0https://orcid.org/0000-0003-2143-6359Anthony Remazeilles1https://orcid.org/0000-0001-5257-2228Miguel Prada2https://orcid.org/0000-0002-1217-6914Itziar Cabanes3https://orcid.org/0000-0002-1949-953XDepartment of Automatic Control and Systems Engineering, Bilbao School of Engineering, University of the Basque Country (UPV/EHU), Bilbao, SpainTECNALIA, Basque Research and Technology Alliance (BRTA), Derio, SpainTECNALIA, Basque Research and Technology Alliance (BRTA), Derio, SpainDepartment of Automatic Control and Systems Engineering, Bilbao School of Engineering, University of the Basque Country (UPV/EHU), Bilbao, SpainIn this paper, an innovative algorithm for averaging a set of multivariate time series with different lengths based on Constrained Dynamic Time Warping (CDTW) is proposed. This approach relies on the CDTW to provide the non-linear alignment of the multivariate time series, and employs the proposed Minimum Cost Averaging (MCA) technique to identify the optimum matches and get equal-length time series. MCA-CDTW is a task-agnostic approach that after selecting a reference curve, transforms the rest of the demonstrations in the set to obtain new curves that are time-aligned with the reference. From these transformed curves, not only the mean but also the signal variability can be directly extracted. This technique provides smooth mean curves even when there are large deviations between the demonstrations in the set, and still the complexity of the proposed algorithm is significantly reduced compared to other averaging techniques from the literature. When learning techniques are used to teach a motion to a robotic system, obtaining smooth trajectories is important to achieve good robotic behaviors. The new algorithm MCA-CDTW is tested and compared on two different databases: a literature database where humans move a robotic arm with kinaesthetic teaching, and a set of recordings of a teleoperated robotic arm performing laboratory manipulation. On both datasets, it is demonstrated that the new approach is providing smooth average trajectories.https://ieeexplore.ieee.org/document/10198412/Dynamic time warpingjerk costmultivariate time seriessmoothnesstime series averaging
spellingShingle Irati Rasines
Anthony Remazeilles
Miguel Prada
Itziar Cabanes
Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
IEEE Access
Dynamic time warping
jerk cost
multivariate time series
smoothness
time series averaging
title Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
title_full Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
title_fullStr Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
title_full_unstemmed Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
title_short Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
title_sort minimum cost averaging for multivariate time series using constrained dynamic time warping a case study in robotics
topic Dynamic time warping
jerk cost
multivariate time series
smoothness
time series averaging
url https://ieeexplore.ieee.org/document/10198412/
work_keys_str_mv AT iratirasines minimumcostaveragingformultivariatetimeseriesusingconstraineddynamictimewarpingacasestudyinrobotics
AT anthonyremazeilles minimumcostaveragingformultivariatetimeseriesusingconstraineddynamictimewarpingacasestudyinrobotics
AT miguelprada minimumcostaveragingformultivariatetimeseriesusingconstraineddynamictimewarpingacasestudyinrobotics
AT itziarcabanes minimumcostaveragingformultivariatetimeseriesusingconstraineddynamictimewarpingacasestudyinrobotics