Towards Tracking a Semi-autonomous, Pneumatic Colonoscope Robot

Bradley Woosley, Prithviraj Dasgupta, Hossein Dehghani, Ross Welch, José Baca, Carl Nelson, Benjamin Terry, Dmitry Oleynikov

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

We describe a semi-autonomous tracking technique based on a Bayesian prediction mechanism for a pneumatic colonoscopy robot. One of the principal problems in using a robot colonoscope is to determine its position or displacement after it has been inserted into the colon. To address this problem for our robot, we have developed a temporal Bayesian framework that uses the observations of the air flow rate and pressure in the tube guiding the robot to predict the current location of the robot. Our experimental results show that the predicted location and velocity of the robot are accurate over most of the time-steps, with a maximum error of 11.5 cm (about 2.5 times the length of the robot’s head) occurring only 7% of the time.

Original languageEnglish (US)
Title of host publicationLecture Notes in Networks and Systems
PublisherSpringer Science and Business Media Deutschland GmbH
Pages110-122
Number of pages13
DOIs
StatePublished - 2017

Publication series

NameLecture Notes in Networks and Systems
Volume13
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Towards Tracking a Semi-autonomous, Pneumatic Colonoscope Robot'. Together they form a unique fingerprint.

Cite this