Skip to content
Back to outputs

Online human in-hand manipulation skill recognition and learning

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

Standard

Online human in-hand manipulation skill recognition and learning. / Chen, Disi; Ju, Zhaojie; Zhou, Dalin; Li, Gongfa; Liu, Honghai.

TAROS 2019: Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II. ed. / Kaspar Althoefer; Jelizaveta Konstantinova; Ketao Zhang. Springer, 2019. p. 113-122 (Lecture Notes in Computer Science; Vol. 11650).

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

Harvard

Chen, D, Ju, Z, Zhou, D, Li, G & Liu, H 2019, Online human in-hand manipulation skill recognition and learning. in K Althoefer, J Konstantinova & K Zhang (eds), TAROS 2019: Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II. Lecture Notes in Computer Science, vol. 11650, Springer, pp. 113-122, 20th Annual Conference on Towards Autonomous Robotic Systems, London, United Kingdom, 3/07/19. https://doi.org/10.1007/978-3-030-25332-5_10

APA

Chen, D., Ju, Z., Zhou, D., Li, G., & Liu, H. (2019). Online human in-hand manipulation skill recognition and learning. In K. Althoefer, J. Konstantinova, & K. Zhang (Eds.), TAROS 2019: Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II (pp. 113-122). (Lecture Notes in Computer Science; Vol. 11650). Springer. https://doi.org/10.1007/978-3-030-25332-5_10

Vancouver

Chen D, Ju Z, Zhou D, Li G, Liu H. Online human in-hand manipulation skill recognition and learning. In Althoefer K, Konstantinova J, Zhang K, editors, TAROS 2019: Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II. Springer. 2019. p. 113-122. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-030-25332-5_10

Author

Chen, Disi ; Ju, Zhaojie ; Zhou, Dalin ; Li, Gongfa ; Liu, Honghai. / Online human in-hand manipulation skill recognition and learning. TAROS 2019: Towards Autonomous Robotic Systems: 20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part II. editor / Kaspar Althoefer ; Jelizaveta Konstantinova ; Ketao Zhang. Springer, 2019. pp. 113-122 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{70272852aef74e639d082cc202b03d35,
title = "Online human in-hand manipulation skill recognition and learning",
abstract = "This work intends to contribute to transfer human in-hand manipulation skills to a dexterous prosthetic hand. We proposed a probabilistic framework for both human skill representation and high efficient recognition. Gaussian Mixture Model (GMM) as a probabilistic model, is highly applicable in clustering, data fitting and classification. The human in-hand motions were perceived by a wearable data glove, CyberGlove, the motion trajectory data proposed and represented by GMMs. Firstly, only a certain amount of motion data were used for batch learning the parameters of GMMs. Then, the newly coming data of human motions will help to update the parameters of the GMMs without observation of the historical training data, through our proposed incremental parameter estimation framework. Recognition in the research takes full advantages of the probabilistic model, when the GMMs were trained, the log-likelihood of a candidate trajectory can be used as a measurement to achieve human in-hand manipulation skill recognition. The recognition results of the online trained GMMs show a steady increase in accuracy, which proved that the incremental learning process improved the performance of human in-hand manipulation skill recognition.",
keywords = "in-hand manipulation skills, GMMs, online learning",
author = "Disi Chen and Zhaojie Ju and Dalin Zhou and Gongfa Li and Honghai Liu",
year = "2019",
month = aug,
day = "1",
doi = "10.1007/978-3-030-25332-5_10",
language = "English",
isbn = "978-3-030-25331-8",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "113--122",
editor = "Kaspar Althoefer and Jelizaveta Konstantinova and Ketao Zhang",
booktitle = "TAROS 2019: Towards Autonomous Robotic Systems",
note = "20th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2019 ; Conference date: 03-07-2019 Through 05-07-2019",

}

RIS

TY - GEN

T1 - Online human in-hand manipulation skill recognition and learning

AU - Chen, Disi

AU - Ju, Zhaojie

AU - Zhou, Dalin

AU - Li, Gongfa

AU - Liu, Honghai

PY - 2019/8/1

Y1 - 2019/8/1

N2 - This work intends to contribute to transfer human in-hand manipulation skills to a dexterous prosthetic hand. We proposed a probabilistic framework for both human skill representation and high efficient recognition. Gaussian Mixture Model (GMM) as a probabilistic model, is highly applicable in clustering, data fitting and classification. The human in-hand motions were perceived by a wearable data glove, CyberGlove, the motion trajectory data proposed and represented by GMMs. Firstly, only a certain amount of motion data were used for batch learning the parameters of GMMs. Then, the newly coming data of human motions will help to update the parameters of the GMMs without observation of the historical training data, through our proposed incremental parameter estimation framework. Recognition in the research takes full advantages of the probabilistic model, when the GMMs were trained, the log-likelihood of a candidate trajectory can be used as a measurement to achieve human in-hand manipulation skill recognition. The recognition results of the online trained GMMs show a steady increase in accuracy, which proved that the incremental learning process improved the performance of human in-hand manipulation skill recognition.

AB - This work intends to contribute to transfer human in-hand manipulation skills to a dexterous prosthetic hand. We proposed a probabilistic framework for both human skill representation and high efficient recognition. Gaussian Mixture Model (GMM) as a probabilistic model, is highly applicable in clustering, data fitting and classification. The human in-hand motions were perceived by a wearable data glove, CyberGlove, the motion trajectory data proposed and represented by GMMs. Firstly, only a certain amount of motion data were used for batch learning the parameters of GMMs. Then, the newly coming data of human motions will help to update the parameters of the GMMs without observation of the historical training data, through our proposed incremental parameter estimation framework. Recognition in the research takes full advantages of the probabilistic model, when the GMMs were trained, the log-likelihood of a candidate trajectory can be used as a measurement to achieve human in-hand manipulation skill recognition. The recognition results of the online trained GMMs show a steady increase in accuracy, which proved that the incremental learning process improved the performance of human in-hand manipulation skill recognition.

KW - in-hand manipulation skills

KW - GMMs

KW - online learning

U2 - 10.1007/978-3-030-25332-5_10

DO - 10.1007/978-3-030-25332-5_10

M3 - Conference contribution

SN - 978-3-030-25331-8

T3 - Lecture Notes in Computer Science

SP - 113

EP - 122

BT - TAROS 2019: Towards Autonomous Robotic Systems

A2 - Althoefer, Kaspar

A2 - Konstantinova, Jelizaveta

A2 - Zhang, Ketao

PB - Springer

T2 - 20th Annual Conference on Towards Autonomous Robotic Systems

Y2 - 3 July 2019 through 5 July 2019

ER -

ID: 16101225