Training a Robotic Arm Movement with Deep Reinforcement Learning

Xiaohan Ni; Xin He; Takafumi Matsumaru

doi:10.1109/ROBIO54168.2021.9739340

Training a Robotic Arm Movement with Deep Reinforcement Learning

Xiaohan Ni^*, Xin He, Takafumi Matsumaru

^*Corresponding author for this work

Graduate School of Information, Production and Systems

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

1 Citation (Scopus)

Abstract

This paper introduces a general experimental design scheme for conditions and parameter settings of robotic arm control under the specific task when using Deep Deterministic Policy Gradient(DDPG) algorithm to train the robotic arm for completing the control task. Based on the Coppelia simulation tool, this paper builds an interactive reinforcement learning environment for robotic arm control tasks, and designs two different control tasks to verify the validity of experimental design schemes. Conclusions in this paper provide an important reference for finding suitable environmental design and parameter settings for using DDPG to train a manipulator and improving the training effect.

Original language	English
Title of host publication	2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	595-600
Number of pages	6
ISBN (Electronic)	9781665405355
DOIs	https://doi.org/10.1109/ROBIO54168.2021.9739340
Publication status	Published - 2021
Event	2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021 - Sanya, China Duration: 2021 Dec 27 → 2021 Dec 31

Publication series

Name	2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

Conference

Conference	2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021
Country/Territory	China
City	Sanya
Period	21/12/27 → 21/12/31

ASJC Scopus subject areas

Artificial Intelligence
Mechanical Engineering
Control and Optimization

Access to Document

10.1109/ROBIO54168.2021.9739340

Cite this

Ni, X., He, X., & Matsumaru, T. (2021). Training a Robotic Arm Movement with Deep Reinforcement Learning. In 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021 (pp. 595-600). (2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBIO54168.2021.9739340

Training a Robotic Arm Movement with Deep Reinforcement Learning. / Ni, Xiaohan; He, Xin; Matsumaru, Takafumi.

2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 595-600 (2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021).

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

Ni, X, He, X & Matsumaru, T 2021, Training a Robotic Arm Movement with Deep Reinforcement Learning. in 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021. 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021, Institute of Electrical and Electronics Engineers Inc., pp. 595-600, 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021, Sanya, China, 21/12/27. https://doi.org/10.1109/ROBIO54168.2021.9739340

@inproceedings{f0ed6e8d770d4e4fa3a9f6a451bd41e0,

title = "Training a Robotic Arm Movement with Deep Reinforcement Learning",

abstract = "This paper introduces a general experimental design scheme for conditions and parameter settings of robotic arm control under the specific task when using Deep Deterministic Policy Gradient(DDPG) algorithm to train the robotic arm for completing the control task. Based on the Coppelia simulation tool, this paper builds an interactive reinforcement learning environment for robotic arm control tasks, and designs two different control tasks to verify the validity of experimental design schemes. Conclusions in this paper provide an important reference for finding suitable environmental design and parameter settings for using DDPG to train a manipulator and improving the training effect.",

author = "Xiaohan Ni and Xin He and Takafumi Matsumaru",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021 ; Conference date: 27-12-2021 Through 31-12-2021",

year = "2021",

doi = "10.1109/ROBIO54168.2021.9739340",

language = "English",

series = "2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021",

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

pages = "595--600",

booktitle = "2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021",

}

TY - GEN

T1 - Training a Robotic Arm Movement with Deep Reinforcement Learning

AU - Ni, Xiaohan

AU - He, Xin

AU - Matsumaru, Takafumi

PY - 2021

Y1 - 2021

N2 - This paper introduces a general experimental design scheme for conditions and parameter settings of robotic arm control under the specific task when using Deep Deterministic Policy Gradient(DDPG) algorithm to train the robotic arm for completing the control task. Based on the Coppelia simulation tool, this paper builds an interactive reinforcement learning environment for robotic arm control tasks, and designs two different control tasks to verify the validity of experimental design schemes. Conclusions in this paper provide an important reference for finding suitable environmental design and parameter settings for using DDPG to train a manipulator and improving the training effect.

AB - This paper introduces a general experimental design scheme for conditions and parameter settings of robotic arm control under the specific task when using Deep Deterministic Policy Gradient(DDPG) algorithm to train the robotic arm for completing the control task. Based on the Coppelia simulation tool, this paper builds an interactive reinforcement learning environment for robotic arm control tasks, and designs two different control tasks to verify the validity of experimental design schemes. Conclusions in this paper provide an important reference for finding suitable environmental design and parameter settings for using DDPG to train a manipulator and improving the training effect.

UR - http://www.scopus.com/inward/record.url?scp=85128203128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85128203128&partnerID=8YFLogxK

U2 - 10.1109/ROBIO54168.2021.9739340

DO - 10.1109/ROBIO54168.2021.9739340

M3 - Conference contribution

AN - SCOPUS:85128203128

T3 - 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

SP - 595

EP - 600

BT - 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Robotics and Biomimetics, ROBIO 2021

Y2 - 27 December 2021 through 31 December 2021

ER -

Training a Robotic Arm Movement with Deep Reinforcement Learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this