Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms

Yukitoshi Minami Shiguematsu, Martim Brandao, Kenji Hashimoto, Atsuo Takanishi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Motivated by experiments showing that humans regulate their walking speed in order to improve localization performance, in this paper we explore the effects of walking gait on biped humanoid localization. We focus on step length as a proxy for speed and because of its ready applicability to current footstep planners, and we compare the performance of three different sparse visual odometry (VO) algorithms as a function of step length: a direct, a semi-direct and an indirect algorithm. The direct algorithm's performance decreased the longer the step lengths, which along with the analysis of inertial and force/torque data, point to a decrease in performance due to an increase of mechanical vibrations. The indirect algorithm's performance decreased in an opposite way, i.e., showing more errors with shorter step lengths, which we show to be due to the effects of drift over time. The semi-direct algorithm showed a performance in-between the previous two. These observations show that footstep planning could be used to improve the performance of VO algorithms in the future.

    Original languageEnglish
    Title of host publication2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018
    PublisherIEEE Computer Society
    Pages160-165
    Number of pages6
    ISBN (Electronic)9781538672839
    DOIs
    Publication statusPublished - 2019 Jan 23
    Event18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018 - Beijing, China
    Duration: 2018 Nov 62018 Nov 9

    Publication series

    NameIEEE-RAS International Conference on Humanoid Robots
    Volume2018-November
    ISSN (Print)2164-0572
    ISSN (Electronic)2164-0580

    Conference

    Conference18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018
    CountryChina
    CityBeijing
    Period18/11/618/11/9

    Fingerprint

    Robots
    Torque
    Planning
    Experiments

    Keywords

    • Ego-motion
    • Humanoid robot
    • Localization
    • Visual odometry
    • WABIAN-2R

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Vision and Pattern Recognition
    • Hardware and Architecture
    • Human-Computer Interaction
    • Electrical and Electronic Engineering

    Cite this

    Shiguematsu, Y. M., Brandao, M., Hashimoto, K., & Takanishi, A. (2019). Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms. In 2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018 (pp. 160-165). [8625015] (IEEE-RAS International Conference on Humanoid Robots; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2018.8625015

    Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms. / Shiguematsu, Yukitoshi Minami; Brandao, Martim; Hashimoto, Kenji; Takanishi, Atsuo.

    2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018. IEEE Computer Society, 2019. p. 160-165 8625015 (IEEE-RAS International Conference on Humanoid Robots; Vol. 2018-November).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Shiguematsu, YM, Brandao, M, Hashimoto, K & Takanishi, A 2019, Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms. in 2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018., 8625015, IEEE-RAS International Conference on Humanoid Robots, vol. 2018-November, IEEE Computer Society, pp. 160-165, 18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018, Beijing, China, 18/11/6. https://doi.org/10.1109/HUMANOIDS.2018.8625015
    Shiguematsu YM, Brandao M, Hashimoto K, Takanishi A. Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms. In 2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018. IEEE Computer Society. 2019. p. 160-165. 8625015. (IEEE-RAS International Conference on Humanoid Robots). https://doi.org/10.1109/HUMANOIDS.2018.8625015
    Shiguematsu, Yukitoshi Minami ; Brandao, Martim ; Hashimoto, Kenji ; Takanishi, Atsuo. / Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms. 2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018. IEEE Computer Society, 2019. pp. 160-165 (IEEE-RAS International Conference on Humanoid Robots).
    @inproceedings{3e6966afa9e645a08bb21e467c609510,
    title = "Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms",
    abstract = "Motivated by experiments showing that humans regulate their walking speed in order to improve localization performance, in this paper we explore the effects of walking gait on biped humanoid localization. We focus on step length as a proxy for speed and because of its ready applicability to current footstep planners, and we compare the performance of three different sparse visual odometry (VO) algorithms as a function of step length: a direct, a semi-direct and an indirect algorithm. The direct algorithm's performance decreased the longer the step lengths, which along with the analysis of inertial and force/torque data, point to a decrease in performance due to an increase of mechanical vibrations. The indirect algorithm's performance decreased in an opposite way, i.e., showing more errors with shorter step lengths, which we show to be due to the effects of drift over time. The semi-direct algorithm showed a performance in-between the previous two. These observations show that footstep planning could be used to improve the performance of VO algorithms in the future.",
    keywords = "Ego-motion, Humanoid robot, Localization, Visual odometry, WABIAN-2R",
    author = "Shiguematsu, {Yukitoshi Minami} and Martim Brandao and Kenji Hashimoto and Atsuo Takanishi",
    year = "2019",
    month = "1",
    day = "23",
    doi = "10.1109/HUMANOIDS.2018.8625015",
    language = "English",
    series = "IEEE-RAS International Conference on Humanoid Robots",
    publisher = "IEEE Computer Society",
    pages = "160--165",
    booktitle = "2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018",

    }

    TY - GEN

    T1 - Effects of Biped Humanoid Robot Walking Gaits on Sparse Visual Odometry Algorithms

    AU - Shiguematsu, Yukitoshi Minami

    AU - Brandao, Martim

    AU - Hashimoto, Kenji

    AU - Takanishi, Atsuo

    PY - 2019/1/23

    Y1 - 2019/1/23

    N2 - Motivated by experiments showing that humans regulate their walking speed in order to improve localization performance, in this paper we explore the effects of walking gait on biped humanoid localization. We focus on step length as a proxy for speed and because of its ready applicability to current footstep planners, and we compare the performance of three different sparse visual odometry (VO) algorithms as a function of step length: a direct, a semi-direct and an indirect algorithm. The direct algorithm's performance decreased the longer the step lengths, which along with the analysis of inertial and force/torque data, point to a decrease in performance due to an increase of mechanical vibrations. The indirect algorithm's performance decreased in an opposite way, i.e., showing more errors with shorter step lengths, which we show to be due to the effects of drift over time. The semi-direct algorithm showed a performance in-between the previous two. These observations show that footstep planning could be used to improve the performance of VO algorithms in the future.

    AB - Motivated by experiments showing that humans regulate their walking speed in order to improve localization performance, in this paper we explore the effects of walking gait on biped humanoid localization. We focus on step length as a proxy for speed and because of its ready applicability to current footstep planners, and we compare the performance of three different sparse visual odometry (VO) algorithms as a function of step length: a direct, a semi-direct and an indirect algorithm. The direct algorithm's performance decreased the longer the step lengths, which along with the analysis of inertial and force/torque data, point to a decrease in performance due to an increase of mechanical vibrations. The indirect algorithm's performance decreased in an opposite way, i.e., showing more errors with shorter step lengths, which we show to be due to the effects of drift over time. The semi-direct algorithm showed a performance in-between the previous two. These observations show that footstep planning could be used to improve the performance of VO algorithms in the future.

    KW - Ego-motion

    KW - Humanoid robot

    KW - Localization

    KW - Visual odometry

    KW - WABIAN-2R

    UR - http://www.scopus.com/inward/record.url?scp=85062301835&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85062301835&partnerID=8YFLogxK

    U2 - 10.1109/HUMANOIDS.2018.8625015

    DO - 10.1109/HUMANOIDS.2018.8625015

    M3 - Conference contribution

    T3 - IEEE-RAS International Conference on Humanoid Robots

    SP - 160

    EP - 165

    BT - 2018 IEEE-RAS 18th International Conference on Humanoid Robots, Humanoids 2018

    PB - IEEE Computer Society

    ER -