Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning

Gabriele Trovato, M. Shikanai, G. Ukawa, J. Kinoshita, N. Murai, J. W. Lee, Hiroyuki Ishii, Atsuo Takanishi, K. Tanoue, S. Ieiri, K. Konishi, M. Hashizume

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Purpose Fibre optic colonoscopy is usually performed with manual introduction and advancement of the endoscope, but there is potential for a robot capable of locomoting autonomously from the rectum to the caecum. A prototype robot was designed and tested. Methods The robot colonic endoscope consists in a front body with clockwise helical fin and a rear body with anticlockwise one, both connected via a DC motor. Input voltage is adjusted automatically by the robot, through the use of reinforcement learning, determining speed and direction (forward or backward). Results Experiments were performed both in-vitro and in-vivo, showing the feasibility of the robot. The device is capable of moving in a slippery environment, and reinforcement learning algorithms such as Q-learning and SARSA can obtain better results than simply applying full tension to the robot. Conclusions This self-propelled robotic endoscope has potential as an alternative to current fibre optic colonoscopy examination methods, especially with the addition of new sensors under development.

Original languageEnglish
Pages (from-to)317-325
Number of pages9
JournalInternational journal of computer assisted radiology and surgery
Volume5
Issue number4
DOIs
Publication statusPublished - 2010 Jul

Fingerprint

Endoscopy
Endoscopes
Reinforcement learning
Locomotion
Colon
Learning
Robots
Colonoscopy
Robotics
Rectum
Fiber optics
Equipment and Supplies
DC motors
Learning algorithms
Reinforcement (Psychology)
Sensors
Electric potential
Experiments

Keywords

  • Autonomous colonoscope
  • Colon endoscope
  • Forward/reverse screw
  • Medical robot
  • Reinforcement learning

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Surgery

Cite this

Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning. / Trovato, Gabriele; Shikanai, M.; Ukawa, G.; Kinoshita, J.; Murai, N.; Lee, J. W.; Ishii, Hiroyuki; Takanishi, Atsuo; Tanoue, K.; Ieiri, S.; Konishi, K.; Hashizume, M.

In: International journal of computer assisted radiology and surgery, Vol. 5, No. 4, 07.2010, p. 317-325.

Research output: Contribution to journalArticle

Trovato, Gabriele ; Shikanai, M. ; Ukawa, G. ; Kinoshita, J. ; Murai, N. ; Lee, J. W. ; Ishii, Hiroyuki ; Takanishi, Atsuo ; Tanoue, K. ; Ieiri, S. ; Konishi, K. ; Hashizume, M. / Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning. In: International journal of computer assisted radiology and surgery. 2010 ; Vol. 5, No. 4. pp. 317-325.
@article{da8b3f69d52341bba347cf058bf2221b,
title = "Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning",
abstract = "Purpose Fibre optic colonoscopy is usually performed with manual introduction and advancement of the endoscope, but there is potential for a robot capable of locomoting autonomously from the rectum to the caecum. A prototype robot was designed and tested. Methods The robot colonic endoscope consists in a front body with clockwise helical fin and a rear body with anticlockwise one, both connected via a DC motor. Input voltage is adjusted automatically by the robot, through the use of reinforcement learning, determining speed and direction (forward or backward). Results Experiments were performed both in-vitro and in-vivo, showing the feasibility of the robot. The device is capable of moving in a slippery environment, and reinforcement learning algorithms such as Q-learning and SARSA can obtain better results than simply applying full tension to the robot. Conclusions This self-propelled robotic endoscope has potential as an alternative to current fibre optic colonoscopy examination methods, especially with the addition of new sensors under development.",
keywords = "Autonomous colonoscope, Colon endoscope, Forward/reverse screw, Medical robot, Reinforcement learning",
author = "Gabriele Trovato and M. Shikanai and G. Ukawa and J. Kinoshita and N. Murai and Lee, {J. W.} and Hiroyuki Ishii and Atsuo Takanishi and K. Tanoue and S. Ieiri and K. Konishi and M. Hashizume",
year = "2010",
month = "7",
doi = "10.1007/s11548-010-0481-0",
language = "English",
volume = "5",
pages = "317--325",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "4",

}

TY - JOUR

T1 - Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning

AU - Trovato, Gabriele

AU - Shikanai, M.

AU - Ukawa, G.

AU - Kinoshita, J.

AU - Murai, N.

AU - Lee, J. W.

AU - Ishii, Hiroyuki

AU - Takanishi, Atsuo

AU - Tanoue, K.

AU - Ieiri, S.

AU - Konishi, K.

AU - Hashizume, M.

PY - 2010/7

Y1 - 2010/7

N2 - Purpose Fibre optic colonoscopy is usually performed with manual introduction and advancement of the endoscope, but there is potential for a robot capable of locomoting autonomously from the rectum to the caecum. A prototype robot was designed and tested. Methods The robot colonic endoscope consists in a front body with clockwise helical fin and a rear body with anticlockwise one, both connected via a DC motor. Input voltage is adjusted automatically by the robot, through the use of reinforcement learning, determining speed and direction (forward or backward). Results Experiments were performed both in-vitro and in-vivo, showing the feasibility of the robot. The device is capable of moving in a slippery environment, and reinforcement learning algorithms such as Q-learning and SARSA can obtain better results than simply applying full tension to the robot. Conclusions This self-propelled robotic endoscope has potential as an alternative to current fibre optic colonoscopy examination methods, especially with the addition of new sensors under development.

AB - Purpose Fibre optic colonoscopy is usually performed with manual introduction and advancement of the endoscope, but there is potential for a robot capable of locomoting autonomously from the rectum to the caecum. A prototype robot was designed and tested. Methods The robot colonic endoscope consists in a front body with clockwise helical fin and a rear body with anticlockwise one, both connected via a DC motor. Input voltage is adjusted automatically by the robot, through the use of reinforcement learning, determining speed and direction (forward or backward). Results Experiments were performed both in-vitro and in-vivo, showing the feasibility of the robot. The device is capable of moving in a slippery environment, and reinforcement learning algorithms such as Q-learning and SARSA can obtain better results than simply applying full tension to the robot. Conclusions This self-propelled robotic endoscope has potential as an alternative to current fibre optic colonoscopy examination methods, especially with the addition of new sensors under development.

KW - Autonomous colonoscope

KW - Colon endoscope

KW - Forward/reverse screw

KW - Medical robot

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=77955984530&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955984530&partnerID=8YFLogxK

U2 - 10.1007/s11548-010-0481-0

DO - 10.1007/s11548-010-0481-0

M3 - Article

C2 - 20480247

AN - SCOPUS:77955984530

VL - 5

SP - 317

EP - 325

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 4

ER -