Assist system for remote manipulation of electric drills by the robot WAREC-1R using deep reinforcement learning

Xiao Sun; Hiroshi Naito; Akio Namiki; Yang Liu; Takashi Matsuzawa; Atsuo Takanishi

doi:10.1017/S0263574721000618

Assist system for remote manipulation of electric drills by the robot WAREC-1R using deep reinforcement learning

Xiao Sun^*, Hiroshi Naito, Akio Namiki, Yang Liu, Takashi Matsuzawa, Atsuo Takanishi

^*Corresponding author for this work

School of Creative Science and Engineering

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Operation of tools has long been studied in robotics. Although appropriate hold of the tool by robots is the base of successful tool operation, it is not with ease especially for tools with complicated shape. In this paper, an assist system for a four-limbed robot is proposed for remote operation of reaching and grasping electric drills using deep reinforcement learning. Through comparative evaluation experiments, the increase of success rate for reaching and grasping is verified and the decrease in both physical and mental workload of the operator is also validated by the index of NASA-TLX.

Original language	English
Pages (from-to)	365-376
Number of pages	12
Journal	Robotica
Volume	40
Issue number	2
DOIs	https://doi.org/10.1017/S0263574721000618
Publication status	Published - 2022 Feb 4

Keywords

Deep reinforcement learning
Manipulation
Remote operation

ASJC Scopus subject areas

Control and Systems Engineering
Software
Mathematics(all)
Computer Science Applications

Access to Document

10.1017/S0263574721000618

Cite this

@article{91ee297e46b3436a932325a2e633fc74,

title = "Assist system for remote manipulation of electric drills by the robot WAREC-1R using deep reinforcement learning",

abstract = "Operation of tools has long been studied in robotics. Although appropriate hold of the tool by robots is the base of successful tool operation, it is not with ease especially for tools with complicated shape. In this paper, an assist system for a four-limbed robot is proposed for remote operation of reaching and grasping electric drills using deep reinforcement learning. Through comparative evaluation experiments, the increase of success rate for reaching and grasping is verified and the decrease in both physical and mental workload of the operator is also validated by the index of NASA-TLX.",

keywords = "Deep reinforcement learning, Manipulation, Remote operation",

author = "Xiao Sun and Hiroshi Naito and Akio Namiki and Yang Liu and Takashi Matsuzawa and Atsuo Takanishi",

year = "2022",

month = feb,

day = "4",

doi = "10.1017/S0263574721000618",

language = "English",

volume = "40",

pages = "365--376",

journal = "Robotica",

issn = "0263-5747",

publisher = "Cambridge University Press",

number = "2",

}

TY - JOUR

T1 - Assist system for remote manipulation of electric drills by the robot WAREC-1R using deep reinforcement learning

AU - Sun, Xiao

AU - Naito, Hiroshi

AU - Namiki, Akio

AU - Liu, Yang

AU - Matsuzawa, Takashi

AU - Takanishi, Atsuo

PY - 2022/2/4

Y1 - 2022/2/4

N2 - Operation of tools has long been studied in robotics. Although appropriate hold of the tool by robots is the base of successful tool operation, it is not with ease especially for tools with complicated shape. In this paper, an assist system for a four-limbed robot is proposed for remote operation of reaching and grasping electric drills using deep reinforcement learning. Through comparative evaluation experiments, the increase of success rate for reaching and grasping is verified and the decrease in both physical and mental workload of the operator is also validated by the index of NASA-TLX.

AB - Operation of tools has long been studied in robotics. Although appropriate hold of the tool by robots is the base of successful tool operation, it is not with ease especially for tools with complicated shape. In this paper, an assist system for a four-limbed robot is proposed for remote operation of reaching and grasping electric drills using deep reinforcement learning. Through comparative evaluation experiments, the increase of success rate for reaching and grasping is verified and the decrease in both physical and mental workload of the operator is also validated by the index of NASA-TLX.

KW - Deep reinforcement learning

KW - Manipulation

KW - Remote operation

UR - http://www.scopus.com/inward/record.url?scp=85108060937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85108060937&partnerID=8YFLogxK

U2 - 10.1017/S0263574721000618

DO - 10.1017/S0263574721000618

M3 - Article

AN - SCOPUS:85108060937

SN - 0263-5747

VL - 40

SP - 365

EP - 376

JO - Robotica

JF - Robotica

IS - 2

ER -

Assist system for remote manipulation of electric drills by the robot WAREC-1R using deep reinforcement learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this