Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning

Haoda Zhu; Kaihong Ouyang; Hao Xiong; Wenjie Lu

doi:10.1109/ICARM58088.2023.10218923

Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning

Haoda Zhu
, Kaihong Ouyang
, Hao Xiong^*
, Wenjie Lu

^*Corresponding author for this work

Harbin Institute of Technology Shenzhen

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

Abstract

Cable-Driven Parallel Robots (CDPRs) have attracted the attention of a large number of researchers in recent years. Researchers proposed to allow wrapping phenomenon to expand the workspace of CDPRs, leading to challenges in the dynamic control of CDPRs. To this end, this study develops a sim-to-real Deep Reinforcement Learning (DRL)-based dynamic control approach for a CDPR allowing wrapping phenomenon. A planner CDPR prototype allowing wrapping phenomenon is established and the DRL-based dynamic control approach is evaluated based on the CDPR prototype. The effectiveness of the DRL-based dynamic control approach in controlling the pose of a CDPR allowing wrapping phenomenon is verified.

Original language	English
Title of host publication	2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1102-1106
Number of pages	5
ISBN (Electronic)	9798350300178
DOIs	https://doi.org/10.1109/ICARM58088.2023.10218923
State	Published - 2023
Externally published	Yes
Event	8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023 - Sanya, China Duration: 8 Jul 2023 → 10 Jul 2023

Publication series

Name	2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

Conference

Conference	8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023
Country/Territory	China
City	Sanya
Period	8/07/23 → 10/07/23

Access to Document

10.1109/ICARM58088.2023.10218923

Cite this

Zhu, H., Ouyang, K., Xiong, H., & Lu, W. (2023). Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning. In 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023 (pp. 1102-1106). (2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARM58088.2023.10218923

Zhu, Haoda ; Ouyang, Kaihong ; Xiong, Hao et al. / Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning. 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1102-1106 (2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023).

@inproceedings{95186d53a015471599907941d9d52756,

title = "Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning",

abstract = "Cable-Driven Parallel Robots (CDPRs) have attracted the attention of a large number of researchers in recent years. Researchers proposed to allow wrapping phenomenon to expand the workspace of CDPRs, leading to challenges in the dynamic control of CDPRs. To this end, this study develops a sim-to-real Deep Reinforcement Learning (DRL)-based dynamic control approach for a CDPR allowing wrapping phenomenon. A planner CDPR prototype allowing wrapping phenomenon is established and the DRL-based dynamic control approach is evaluated based on the CDPR prototype. The effectiveness of the DRL-based dynamic control approach in controlling the pose of a CDPR allowing wrapping phenomenon is verified.",

author = "Haoda Zhu and Kaihong Ouyang and Hao Xiong and Wenjie Lu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023 ; Conference date: 08-07-2023 Through 10-07-2023",

year = "2023",

doi = "10.1109/ICARM58088.2023.10218923",

language = "英语",

series = "2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023",

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

pages = "1102--1106",

booktitle = "2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023",

address = "美国",

}

Zhu, H, Ouyang, K, Xiong, H & Lu, W 2023, Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning. in 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023. 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1102-1106, 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023, Sanya, China, 8/07/23. https://doi.org/10.1109/ICARM58088.2023.10218923

Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning. / Zhu, Haoda; Ouyang, Kaihong; Xiong, Hao et al.
2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1102-1106 (2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023).

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

TY - GEN

T1 - Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning

AU - Zhu, Haoda

AU - Ouyang, Kaihong

AU - Xiong, Hao

AU - Lu, Wenjie

PY - 2023

Y1 - 2023

N2 - Cable-Driven Parallel Robots (CDPRs) have attracted the attention of a large number of researchers in recent years. Researchers proposed to allow wrapping phenomenon to expand the workspace of CDPRs, leading to challenges in the dynamic control of CDPRs. To this end, this study develops a sim-to-real Deep Reinforcement Learning (DRL)-based dynamic control approach for a CDPR allowing wrapping phenomenon. A planner CDPR prototype allowing wrapping phenomenon is established and the DRL-based dynamic control approach is evaluated based on the CDPR prototype. The effectiveness of the DRL-based dynamic control approach in controlling the pose of a CDPR allowing wrapping phenomenon is verified.

AB - Cable-Driven Parallel Robots (CDPRs) have attracted the attention of a large number of researchers in recent years. Researchers proposed to allow wrapping phenomenon to expand the workspace of CDPRs, leading to challenges in the dynamic control of CDPRs. To this end, this study develops a sim-to-real Deep Reinforcement Learning (DRL)-based dynamic control approach for a CDPR allowing wrapping phenomenon. A planner CDPR prototype allowing wrapping phenomenon is established and the DRL-based dynamic control approach is evaluated based on the CDPR prototype. The effectiveness of the DRL-based dynamic control approach in controlling the pose of a CDPR allowing wrapping phenomenon is verified.

UR - https://www.scopus.com/pages/publications/85171548320

U2 - 10.1109/ICARM58088.2023.10218923

DO - 10.1109/ICARM58088.2023.10218923

M3 - 会议稿件

AN - SCOPUS:85171548320

T3 - 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

SP - 1102

EP - 1106

BT - 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

Y2 - 8 July 2023 through 10 July 2023

ER -

Zhu H, Ouyang K, Xiong H , Lu W. Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning. In 2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1102-1106. (2023 8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023). doi: 10.1109/ICARM58088.2023.10218923

Dynamic Control of a Cable-Driven Parallel Robot Allowing Wrapping Phenomenon through Sim-to-Real Deep Reinforcement Learning

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this