Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses

Jingeng Mai; Dongfang Xu; Haolin Li; Shichang Zhang; Jiaying Tan; Qining Wang

doi:10.1109/RCAR.2018.8621732

Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses

Jingeng Mai
, Dongfang Xu
, Haolin Li
, Shichang Zhang
, Jiaying Tan
, Qining Wang

Peking University

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

7 Scopus citations

Abstract

This paper presents an acceleration system for on-board support vector machine (SVM) model training for robotic transtibial prosthesis based on system on chip with field-programmable gate array (SoC-FPGA) hardware. A hardware prototype was developed and SVM-based model training algorithm was implemented with high-level synthesis technology. Experiments on a transtibial amputee subject demonstrated that the proposed system provided good speedups over ARM-based implementation for on-board training in six locomotion identification tasks (standing, level-ground walking, ramp ascent, ramp descent, stair ascent, stair descent). Meanwhile, the additional power consumption was not significant and acceptable.

Original language	English
Title of host publication	2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	150-155
Number of pages	6
ISBN (Electronic)	9781538668689
DOIs	https://doi.org/10.1109/RCAR.2018.8621732
State	Published - 2 Jul 2018
Externally published	Yes
Event	2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 - Kandima, Maldives Duration: 1 Aug 2018 → 5 Aug 2018

Publication series

Name	2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

Conference

Conference	2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
Country/Territory	Maldives
City	Kandima
Period	1/08/18 → 5/08/18

Access to Document

10.1109/RCAR.2018.8621732

Cite this

Mai, J., Xu, D., Li, H., Zhang, S., Tan, J., & Wang, Q. (2018). Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 (pp. 150-155). Article 8621732 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RCAR.2018.8621732

Mai, Jingeng ; Xu, Dongfang ; Li, Haolin et al. / Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses. 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 150-155 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).

@inproceedings{9f8617515b964681874802ea0965c9b5,

title = "Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses",

abstract = "This paper presents an acceleration system for on-board support vector machine (SVM) model training for robotic transtibial prosthesis based on system on chip with field-programmable gate array (SoC-FPGA) hardware. A hardware prototype was developed and SVM-based model training algorithm was implemented with high-level synthesis technology. Experiments on a transtibial amputee subject demonstrated that the proposed system provided good speedups over ARM-based implementation for on-board training in six locomotion identification tasks (standing, level-ground walking, ramp ascent, ramp descent, stair ascent, stair descent). Meanwhile, the additional power consumption was not significant and acceptable.",

author = "Jingeng Mai and Dongfang Xu and Haolin Li and Shichang Zhang and Jiaying Tan and Qining Wang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 ; Conference date: 01-08-2018 Through 05-08-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/RCAR.2018.8621732",

language = "英语",

series = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "150--155",

booktitle = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",

address = "美国",

}

Mai, J, Xu, D, Li, H, Zhang, S, Tan, J & Wang, Q 2018, Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses. in 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018., 8621732, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Institute of Electrical and Electronics Engineers Inc., pp. 150-155, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Kandima, Maldives, 1/08/18. https://doi.org/10.1109/RCAR.2018.8621732

Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses. / Mai, Jingeng; Xu, Dongfang; Li, Haolin et al.
2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 150-155 8621732 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).

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

TY - GEN

T1 - Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses

AU - Mai, Jingeng

AU - Xu, Dongfang

AU - Li, Haolin

AU - Zhang, Shichang

AU - Tan, Jiaying

AU - Wang, Qining

PY - 2018/7/2

Y1 - 2018/7/2

N2 - This paper presents an acceleration system for on-board support vector machine (SVM) model training for robotic transtibial prosthesis based on system on chip with field-programmable gate array (SoC-FPGA) hardware. A hardware prototype was developed and SVM-based model training algorithm was implemented with high-level synthesis technology. Experiments on a transtibial amputee subject demonstrated that the proposed system provided good speedups over ARM-based implementation for on-board training in six locomotion identification tasks (standing, level-ground walking, ramp ascent, ramp descent, stair ascent, stair descent). Meanwhile, the additional power consumption was not significant and acceptable.

AB - This paper presents an acceleration system for on-board support vector machine (SVM) model training for robotic transtibial prosthesis based on system on chip with field-programmable gate array (SoC-FPGA) hardware. A hardware prototype was developed and SVM-based model training algorithm was implemented with high-level synthesis technology. Experiments on a transtibial amputee subject demonstrated that the proposed system provided good speedups over ARM-based implementation for on-board training in six locomotion identification tasks (standing, level-ground walking, ramp ascent, ramp descent, stair ascent, stair descent). Meanwhile, the additional power consumption was not significant and acceptable.

UR - https://www.scopus.com/pages/publications/85062498317

U2 - 10.1109/RCAR.2018.8621732

DO - 10.1109/RCAR.2018.8621732

M3 - 会议稿件

AN - SCOPUS:85062498317

T3 - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

SP - 150

EP - 155

BT - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

Y2 - 1 August 2018 through 5 August 2018

ER -

Mai J, Xu D, Li H, Zhang S, Tan J, Wang Q. Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 150-155. 8621732. (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). doi: 10.1109/RCAR.2018.8621732

Implementing a SoC-FPGA based acceleration system for on-board SVM training for robotic transtibial prostheses

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this