FBG-Based Position Estimation of Highly Deformable Continuum Manipulators: Model-Dependent vs. Data-Driven Approaches

Shahriar Sefati, Rachel Hegeman, Farshid Alambeigi, Iulian Iordachita, Mehran Armand

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Conventional shape sensing techniques using Fiber Bragg Grating (FBG) involve finding the curvature at discrete FBG active areas and integrating curvature over the length of the continuum dexterous manipulator (CDM) for tip position estimation (TPE). However, due to limited number of sensing locations and many geometrical assumptions, these methods are prone to large error propagation especially when the CDM undergoes large deflections. In this paper, we study the complications of using the conventional TPE methods that are dependent on sensor model and propose a new data-driven method that overcomes these challenges. The proposed method consists of a regression model that takes FBG wavelength raw data as input and directly estimates the CDM's tip position. This model is pre-operatively (off-line) trained on position information from optical trackers/cameras (as the ground truth) and it intra-operatively (on-line) estimates CDM tip position using only the FBG wavelength data. The method's performance is evaluated on a CDM developed for orthopedic applications, and the results are compared to conventional model-dependent methods during large deflection bendings. Mean absolute TPE error (and standard deviation) of 1.52 (0.67) mm and 0.11 (0.1) mm with maximum absolute errors of 3.63 mm and 0.62 mm for the conventional and the proposed data-driven techniques were obtained, respectively. These results demonstrate a significant out-performance of the proposed data-driven approach versus the conventional estimation technique.

Original languageEnglish (US)
Title of host publication2019 International Symposium on Medical Robotics, ISMR 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538678251
DOIs
StatePublished - May 8 2019
Event2019 International Symposium on Medical Robotics, ISMR 2019 - Atlanta, United States
Duration: Apr 3 2019Apr 5 2019

Publication series

Name2019 International Symposium on Medical Robotics, ISMR 2019

Conference

Conference2019 International Symposium on Medical Robotics, ISMR 2019
CountryUnited States
CityAtlanta
Period4/3/194/5/19

Fingerprint

Fiber Bragg gratings
Manipulators
Wavelength
Orthopedics
Error analysis
Cameras
Sensors

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Sefati, S., Hegeman, R., Alambeigi, F., Iordachita, I., & Armand, M. (2019). FBG-Based Position Estimation of Highly Deformable Continuum Manipulators: Model-Dependent vs. Data-Driven Approaches. In 2019 International Symposium on Medical Robotics, ISMR 2019 [8710179] (2019 International Symposium on Medical Robotics, ISMR 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISMR.2019.8710179

FBG-Based Position Estimation of Highly Deformable Continuum Manipulators : Model-Dependent vs. Data-Driven Approaches. / Sefati, Shahriar; Hegeman, Rachel; Alambeigi, Farshid; Iordachita, Iulian; Armand, Mehran.

2019 International Symposium on Medical Robotics, ISMR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8710179 (2019 International Symposium on Medical Robotics, ISMR 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sefati, S, Hegeman, R, Alambeigi, F, Iordachita, I & Armand, M 2019, FBG-Based Position Estimation of Highly Deformable Continuum Manipulators: Model-Dependent vs. Data-Driven Approaches. in 2019 International Symposium on Medical Robotics, ISMR 2019., 8710179, 2019 International Symposium on Medical Robotics, ISMR 2019, Institute of Electrical and Electronics Engineers Inc., 2019 International Symposium on Medical Robotics, ISMR 2019, Atlanta, United States, 4/3/19. https://doi.org/10.1109/ISMR.2019.8710179
Sefati S, Hegeman R, Alambeigi F, Iordachita I, Armand M. FBG-Based Position Estimation of Highly Deformable Continuum Manipulators: Model-Dependent vs. Data-Driven Approaches. In 2019 International Symposium on Medical Robotics, ISMR 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8710179. (2019 International Symposium on Medical Robotics, ISMR 2019). https://doi.org/10.1109/ISMR.2019.8710179
Sefati, Shahriar ; Hegeman, Rachel ; Alambeigi, Farshid ; Iordachita, Iulian ; Armand, Mehran. / FBG-Based Position Estimation of Highly Deformable Continuum Manipulators : Model-Dependent vs. Data-Driven Approaches. 2019 International Symposium on Medical Robotics, ISMR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 International Symposium on Medical Robotics, ISMR 2019).
@inproceedings{af656379e29b47cf98f9226c25e25a8e,
title = "FBG-Based Position Estimation of Highly Deformable Continuum Manipulators: Model-Dependent vs. Data-Driven Approaches",
abstract = "Conventional shape sensing techniques using Fiber Bragg Grating (FBG) involve finding the curvature at discrete FBG active areas and integrating curvature over the length of the continuum dexterous manipulator (CDM) for tip position estimation (TPE). However, due to limited number of sensing locations and many geometrical assumptions, these methods are prone to large error propagation especially when the CDM undergoes large deflections. In this paper, we study the complications of using the conventional TPE methods that are dependent on sensor model and propose a new data-driven method that overcomes these challenges. The proposed method consists of a regression model that takes FBG wavelength raw data as input and directly estimates the CDM's tip position. This model is pre-operatively (off-line) trained on position information from optical trackers/cameras (as the ground truth) and it intra-operatively (on-line) estimates CDM tip position using only the FBG wavelength data. The method's performance is evaluated on a CDM developed for orthopedic applications, and the results are compared to conventional model-dependent methods during large deflection bendings. Mean absolute TPE error (and standard deviation) of 1.52 (0.67) mm and 0.11 (0.1) mm with maximum absolute errors of 3.63 mm and 0.62 mm for the conventional and the proposed data-driven techniques were obtained, respectively. These results demonstrate a significant out-performance of the proposed data-driven approach versus the conventional estimation technique.",
author = "Shahriar Sefati and Rachel Hegeman and Farshid Alambeigi and Iulian Iordachita and Mehran Armand",
year = "2019",
month = "5",
day = "8",
doi = "10.1109/ISMR.2019.8710179",
language = "English (US)",
series = "2019 International Symposium on Medical Robotics, ISMR 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 International Symposium on Medical Robotics, ISMR 2019",

}

TY - GEN

T1 - FBG-Based Position Estimation of Highly Deformable Continuum Manipulators

T2 - Model-Dependent vs. Data-Driven Approaches

AU - Sefati, Shahriar

AU - Hegeman, Rachel

AU - Alambeigi, Farshid

AU - Iordachita, Iulian

AU - Armand, Mehran

PY - 2019/5/8

Y1 - 2019/5/8

N2 - Conventional shape sensing techniques using Fiber Bragg Grating (FBG) involve finding the curvature at discrete FBG active areas and integrating curvature over the length of the continuum dexterous manipulator (CDM) for tip position estimation (TPE). However, due to limited number of sensing locations and many geometrical assumptions, these methods are prone to large error propagation especially when the CDM undergoes large deflections. In this paper, we study the complications of using the conventional TPE methods that are dependent on sensor model and propose a new data-driven method that overcomes these challenges. The proposed method consists of a regression model that takes FBG wavelength raw data as input and directly estimates the CDM's tip position. This model is pre-operatively (off-line) trained on position information from optical trackers/cameras (as the ground truth) and it intra-operatively (on-line) estimates CDM tip position using only the FBG wavelength data. The method's performance is evaluated on a CDM developed for orthopedic applications, and the results are compared to conventional model-dependent methods during large deflection bendings. Mean absolute TPE error (and standard deviation) of 1.52 (0.67) mm and 0.11 (0.1) mm with maximum absolute errors of 3.63 mm and 0.62 mm for the conventional and the proposed data-driven techniques were obtained, respectively. These results demonstrate a significant out-performance of the proposed data-driven approach versus the conventional estimation technique.

AB - Conventional shape sensing techniques using Fiber Bragg Grating (FBG) involve finding the curvature at discrete FBG active areas and integrating curvature over the length of the continuum dexterous manipulator (CDM) for tip position estimation (TPE). However, due to limited number of sensing locations and many geometrical assumptions, these methods are prone to large error propagation especially when the CDM undergoes large deflections. In this paper, we study the complications of using the conventional TPE methods that are dependent on sensor model and propose a new data-driven method that overcomes these challenges. The proposed method consists of a regression model that takes FBG wavelength raw data as input and directly estimates the CDM's tip position. This model is pre-operatively (off-line) trained on position information from optical trackers/cameras (as the ground truth) and it intra-operatively (on-line) estimates CDM tip position using only the FBG wavelength data. The method's performance is evaluated on a CDM developed for orthopedic applications, and the results are compared to conventional model-dependent methods during large deflection bendings. Mean absolute TPE error (and standard deviation) of 1.52 (0.67) mm and 0.11 (0.1) mm with maximum absolute errors of 3.63 mm and 0.62 mm for the conventional and the proposed data-driven techniques were obtained, respectively. These results demonstrate a significant out-performance of the proposed data-driven approach versus the conventional estimation technique.

UR - http://www.scopus.com/inward/record.url?scp=85066304181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066304181&partnerID=8YFLogxK

U2 - 10.1109/ISMR.2019.8710179

DO - 10.1109/ISMR.2019.8710179

M3 - Conference contribution

AN - SCOPUS:85066304181

T3 - 2019 International Symposium on Medical Robotics, ISMR 2019

BT - 2019 International Symposium on Medical Robotics, ISMR 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -