Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control

Dalia De Santis; Patrycja Dzialecka; Ferdinando A. Mussa-Ivaldi

doi:10.1109/BIOROB.2018.8487912

Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control

Dalia De Santis^*, Patrycja Dzialecka, Ferdinando A. Mussa-Ivaldi

^*Corresponding author for this work

Neuroscience

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Interfaces that exploit biological signals or movements to control the operation of lower-dimensional systems external to the body are at the frontier for augmenting human abilities, but also constitute a learning challenge for their users. We developed and tested an unsupervised coadaptive algorithm that changed the mapping of a body machine interface to match the natural movement distribution of the users. Users controlled a cursor on a computer monitor using arm and shoulder motions captured by a set of inertial sensors in either of three conditions: I) a constant body-to-cursor map obtained through Principal Component Analysis of calibration movements, ii) a map that was recomputed at specified points in time, iii) a map that adaptively changed over time. We used recursive online PCA to incrementally shift the projection space towards the 2-dimensional subspace capturing the greatest sensor signal variance. Results suggest that training with the coadaptive BMI allows for faster internalization of the control space while reducing user's reliance on visual feedback.

Original language	English (US)
Title of host publication	BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics
Publisher	IEEE Computer Society
Pages	801-806
Number of pages	6
ISBN (Electronic)	9781538681831
DOIs	https://doi.org/10.1109/BIOROB.2018.8487912
State	Published - Oct 9 2018
Event	7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018 - Enschede, Netherlands Duration: Aug 26 2018 → Aug 29 2018

Publication series

Name	Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
Volume	2018-August
ISSN (Print)	2155-1774

Other

Other	7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018
Country/Territory	Netherlands
City	Enschede
Period	8/26/18 → 8/29/18

Funding

*Research supported by NIDRR grant H133E120010 and NICHD grant 1R01HD072080. Results incorporated in this manuscript have received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie, project REBoT, G.A. No 750464.

ASJC Scopus subject areas

Artificial Intelligence
Biomedical Engineering
Mechanical Engineering

Access to Document

10.1109/BIOROB.2018.8487912

Cite this

De Santis, D., Dzialecka, P., & Mussa-Ivaldi, F. A. (2018). Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control. In BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (pp. 801-806). Article 8487912 (Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics; Vol. 2018-August). IEEE Computer Society. https://doi.org/10.1109/BIOROB.2018.8487912

De Santis, Dalia ; Dzialecka, Patrycja ; Mussa-Ivaldi, Ferdinando A. / Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control. BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. IEEE Computer Society, 2018. pp. 801-806 (Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics).

@inproceedings{668853c011fd4b54892589dea5ece8df,

title = "Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control",

abstract = "Interfaces that exploit biological signals or movements to control the operation of lower-dimensional systems external to the body are at the frontier for augmenting human abilities, but also constitute a learning challenge for their users. We developed and tested an unsupervised coadaptive algorithm that changed the mapping of a body machine interface to match the natural movement distribution of the users. Users controlled a cursor on a computer monitor using arm and shoulder motions captured by a set of inertial sensors in either of three conditions: I) a constant body-to-cursor map obtained through Principal Component Analysis of calibration movements, ii) a map that was recomputed at specified points in time, iii) a map that adaptively changed over time. We used recursive online PCA to incrementally shift the projection space towards the 2-dimensional subspace capturing the greatest sensor signal variance. Results suggest that training with the coadaptive BMI allows for faster internalization of the control space while reducing user's reliance on visual feedback.",

author = "{De Santis}, Dalia and Patrycja Dzialecka and Mussa-Ivaldi, {Ferdinando A.}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018 ; Conference date: 26-08-2018 Through 29-08-2018",

year = "2018",

month = oct,

day = "9",

doi = "10.1109/BIOROB.2018.8487912",

language = "English (US)",

series = "Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics",

publisher = "IEEE Computer Society",

pages = "801--806",

booktitle = "BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics",

address = "United States",

}

De Santis, D, Dzialecka, P & Mussa-Ivaldi, FA 2018, Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control. in BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics., 8487912, Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, vol. 2018-August, IEEE Computer Society, pp. 801-806, 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018, Enschede, Netherlands, 8/26/18. https://doi.org/10.1109/BIOROB.2018.8487912

Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control. / De Santis, Dalia; Dzialecka, Patrycja; Mussa-Ivaldi, Ferdinando A.
BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. IEEE Computer Society, 2018. p. 801-806 8487912 (Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics; Vol. 2018-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control

AU - De Santis, Dalia

AU - Dzialecka, Patrycja

AU - Mussa-Ivaldi, Ferdinando A.

PY - 2018/10/9

Y1 - 2018/10/9

N2 - Interfaces that exploit biological signals or movements to control the operation of lower-dimensional systems external to the body are at the frontier for augmenting human abilities, but also constitute a learning challenge for their users. We developed and tested an unsupervised coadaptive algorithm that changed the mapping of a body machine interface to match the natural movement distribution of the users. Users controlled a cursor on a computer monitor using arm and shoulder motions captured by a set of inertial sensors in either of three conditions: I) a constant body-to-cursor map obtained through Principal Component Analysis of calibration movements, ii) a map that was recomputed at specified points in time, iii) a map that adaptively changed over time. We used recursive online PCA to incrementally shift the projection space towards the 2-dimensional subspace capturing the greatest sensor signal variance. Results suggest that training with the coadaptive BMI allows for faster internalization of the control space while reducing user's reliance on visual feedback.

AB - Interfaces that exploit biological signals or movements to control the operation of lower-dimensional systems external to the body are at the frontier for augmenting human abilities, but also constitute a learning challenge for their users. We developed and tested an unsupervised coadaptive algorithm that changed the mapping of a body machine interface to match the natural movement distribution of the users. Users controlled a cursor on a computer monitor using arm and shoulder motions captured by a set of inertial sensors in either of three conditions: I) a constant body-to-cursor map obtained through Principal Component Analysis of calibration movements, ii) a map that was recomputed at specified points in time, iii) a map that adaptively changed over time. We used recursive online PCA to incrementally shift the projection space towards the 2-dimensional subspace capturing the greatest sensor signal variance. Results suggest that training with the coadaptive BMI allows for faster internalization of the control space while reducing user's reliance on visual feedback.

UR - http://www.scopus.com/inward/record.url?scp=85056579773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056579773&partnerID=8YFLogxK

U2 - 10.1109/BIOROB.2018.8487912

DO - 10.1109/BIOROB.2018.8487912

M3 - Conference contribution

AN - SCOPUS:85056579773

T3 - Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics

SP - 801

EP - 806

BT - BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics

PB - IEEE Computer Society

T2 - 7th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, BIOROB 2018

Y2 - 26 August 2018 through 29 August 2018

ER -

De Santis D, Dzialecka P, Mussa-Ivaldi FA. Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control. In BIOROB 2018 - 7th IEEE International Conference on Biomedical Robotics and Biomechatronics. IEEE Computer Society. 2018. p. 801-806. 8487912. (Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics). doi: 10.1109/BIOROB.2018.8487912

Unsupervised Coadaptation of an Assistive Interface to Facilitate Sensorimotor Learning of Redundant Control

Abstract

Publication series

Other

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this