Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learning
- 231 Downloads
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.
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).
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.
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.
KeywordsColon endoscope Medical robot Autonomous colonoscope Forward/reverse screw Reinforcement learning
Unable to display preview. Download preview PDF.
- 1.Boyle P, Levin B (2008) World Cancer Report 2008. Int Agency Res Cancer Treat 88(1):123–132 (in Japanese)Google Scholar
- 4.Church JM (1995) Endoscopy of the colon, rectum and anus. Igaku-Shoin Medical Publishers, New YorkGoogle Scholar
- 5.Wickham J (1996) Editorial. Min Invas Ther & Allied TechGoogle Scholar
- 7.Kassim I, Phee L, Ng WS, Gong F, Dario P, Mosse CA (2006) Locomotion techniques for robotic colonoscopy, Inst. of Nat. Neuroscience, Singapore; Engineering in Medicine and Biology MagazineGoogle Scholar
- 10.Accoto D, Stefanini C, Phee L, Arena A, Pernorio G, Menciassi A, Carrozza MC, Dario P (2001) Measurements of the frictional properties of the gastrointestinal tract. In: Proceedings of the 2nd World Tribology Congress. Vienna, p 728Google Scholar
- 11.Tanaka S et al (2006) The present condition of a capsule endoscope and a double balloon endoscope, a view. Med Treat 88(1):123–132 (in Japanese)Google Scholar
- 13.Grundfest WS, Burdick IV JW, Slatkin AB (1994) Robotic endoscopy. US Patent 5,337,732, 1994Google Scholar
- 14.Slatkin AB, Burdick G, Grundfest WS (1995) The development of a robotic endoscope Intelligent Robots and Systems. IEEE/RSJ Int Conf Intell Robots Syst 2: 2162Google Scholar
- 15.Menciassi A, Park JH, Lee S, Gorini S, Dario P, Park JO (2002) Robotic solutions and mechanisms for a semi-autonomous endoscope. In: Proceedings of the IEEE RSJ International Conference on intelligent robots and systems, Lausanne, Switzerland, pp. 1379–1384Google Scholar
- 17.Kalmár Z, Szepesvári C, Lorincz A (1998) Modular reinforcement learning: an application a real robot task. Lecture notes in computer science, ISSN 0302-9743Google Scholar
- 18.Abbeel P, Ng AY (2005) Exploration and apprenticeship learning in reinforcement learning. In: ICML ’05 proceedings of the 22nd international conference on Machine learning, pp 1–8Google Scholar
- 19.Abbeel P, Quigley M, Ng AY (2006) Using inaccurate models in reinforcement learning. In: ICML ’06 proceedings of the 23rd international conference on Machine learningGoogle Scholar
- 20.Ito et al (2007) Development of colon endoscope robots with new drive mechanisms—self-propelled endoscope robots of rotatory inertia and reverse screw types. In: Proceedings of the 25th Annual conference of the robotics society of Japan 2J17 (in Japanese)Google Scholar
- 21.Moore A (1990) Efficient memory-based learning for robot control. PhD. Thesis, Technical Report No.229, Computer Laboratory, University of CambridgeGoogle Scholar
- 22.Sutton RS, Barto G (1998) Reinforcement learning: an introduction. MIT Press, CambridgeGoogle Scholar
- 23.Asada M, Noda S, Tawaratsumida S, Hosoda K (1996) Purposive behavior acquisition for a real robot by vision-based reinforcement learning. Mach Learn 23: 279–303Google Scholar
- 24.Uchibe E, Asada M, Hosoda K (1996) Behavior coordination for a mobile robot using modular reinforcement learning. In: Proceedings of IEEE/RSJ Int Conf on Intelligent Robot and Sytems. pp 1329–1336Google Scholar