Using penalized spline regression to calculate mean trajectories including confidence intervals of human motion data

Daniel Carton, Annemarie Turnwald, Wiktor Olszowy, Martin Buss, Dirk Wollherr

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Research in motion planning for mobile robots increasingly focuses on modeling human-like motions and behaviors. Applied to robots, these models help generating motions that are intuitively comprehensible for a human interaction partner. However, identifying the underlying parameters of such human motion models is challenging. These parameters are commonly estimated by analyzing measured single trajectories or means of trajectory sets. Indeed, raw trajectories as well as the means are often not representative for the data, as measurements are noisy and the amount of generated data is limited. For a reasonable analysis it is necessary to smooth the data and estimate an according confidence interval for the mean. In this paper we apply penalized splines to smooth single trajectories and to estimate means of trajectory sets, which ensures little distortion of the original data. Based on that, a method is presented that yields a confidence interval for the mean of human motion data. In order to cope with unknown distributions and small datasets our method employs bootstrapping. The analysis based on confidence intervals takes the variance of the data into account and allows for reasonable conclusions about underlying human motion parameters.

Original languageEnglish
Title of host publicationARSO 2014 - Workshop Digest, IEEE International Workshop on Advance Robotics and its Social Impacts
EditorsHenny Admoni, Tamim Asfour, Cindy Bethel, David Bourne, Anca Dragan, David Feil-Seifer, Birgit Graf, Jeonghye Han, Nathan Kirchner, Masashi Konyo, Shinya Kotosaka, Sonya Kwak, Changchun Liu, Bruce MacDonald, Selma Sabanovic, Pericle Salvini, Sebastian Scherer, Masahiro Shiomi, Giancarlo Teti, Stephen Tully, Bram Vanderborght, Kazuyoshi Wada, Britta Wrede, Fumin Zhang
PublisherIEEE Computer Society
Pages76-81
Number of pages6
EditionJanuary
ISBN (Electronic)9781479969685
DOIs
StatePublished - 23 Jan 2015
Event9th IEEE International Workshop on Advance Robotics and its Social Impacts, ARSO 2014 - Evanston, United States
Duration: 11 Sep 201413 Sep 2014

Publication series

NameProceedings of IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO
NumberJanuary
Volume2015-January
ISSN (Print)2162-7568
ISSN (Electronic)2162-7576

Conference

Conference9th IEEE International Workshop on Advance Robotics and its Social Impacts, ARSO 2014
Country/TerritoryUnited States
CityEvanston
Period11/09/1413/09/14

Fingerprint

Dive into the research topics of 'Using penalized spline regression to calculate mean trajectories including confidence intervals of human motion data'. Together they form a unique fingerprint.

Cite this