Closed-chain pose estimation from wearable sensors

Vladimir Joukov, Jonathan Feng Shun Lin, Dana Kulic

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

Abstract

Inertial measurement unit sensors are commonly used for human pose estimation. However, a systematic and robust method to incorporate position and orientation constraints in the kinematic structure during environmental contact is lacking. In this paper, we estimate the pose using the extended Kalman filter, linearize the closed loop constraints about the predicted Kalman filter state, then project the unconstrained state estimate onto the constrained space. Multiple constraints that are representative of real world scenarios are derived. The proposed technique is tested on two human movement datasets and demonstrated to outperform unconstrained Kalman filter.

Original languageEnglish
Title of host publication2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids 2019)
EditorsSerena Ivaldi, Ko Ayusawa, Francesco Nori, Goldie Nejat
Place of PublicationPiscataway NJ USA
PublisherIEEE Computer Society
Pages594-600
Number of pages7
ISBN (Electronic)9781538676301
ISBN (Print)9781538676318
DOIs
Publication statusPublished - 2019
EventIEEE-RAS International Conference on Humanoid Robots 2019 - Toronto, Canada
Duration: 15 Oct 201917 Oct 2019
Conference number: 19th
https://humanoids2019.loria.fr/

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
PublisherInstitute of Electrical and Electronics Engineers Inc.
Volume2019-October
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Conference

ConferenceIEEE-RAS International Conference on Humanoid Robots 2019
Abbreviated titleHumanoids 2019
CountryCanada
CityToronto
Period15/10/1917/10/19
Internet address

Cite this