A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences

Yizhe Chang, Mohammed Kutbi, Nikolaos Agadakos, Bo Sun, Philippos Mordohai

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

Abstract

Research on robotic wheelchairs covers a broad range from complete autonomy to shared autonomy to manual navigation by a joystick or other means. Shared autonomy is valuable because it allows the user and the robot to complement each other, to correct each other's mistakes and to avoid collisions. In this paper, we present an approach that can learn to replicate path selection according to the wheelchair user's individual, often subjective, criteria in order to reduce the number of times the user has to intervene during automatic navigation. This is achieved by learning to rank paths using a support vector machine trained on selections made by the user in a simulator. If the classifier's confidence in the top ranked path is high, it is executed without requesting confirmation from the user. Otherwise, the choice is deferred to the user. Simulations and laboratory experiments using two path generation strategies demonstrate the effectiveness of our approach.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1490-1499
Number of pages10
ISBN (Electronic)9781538610343
DOIs
StatePublished - Jan 19 2018
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: Oct 22 2017Oct 29 2017

Publication series

NameProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Volume2018-January

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
CountryItaly
CityVenice
Period10/22/1710/29/17

Fingerprint

Wheelchairs
Navigation
Support vector machines
Robotics
Classifiers
Simulators
Robots
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Chang, Y., Kutbi, M., Agadakos, N., Sun, B., & Mordohai, P. (2018). A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 (pp. 1490-1499). (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2017.176
Chang, Yizhe ; Kutbi, Mohammed ; Agadakos, Nikolaos ; Sun, Bo ; Mordohai, Philippos. / A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1490-1499 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017).
@inproceedings{2e972307e805429f8c23b30442c44e50,
title = "A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences",
abstract = "Research on robotic wheelchairs covers a broad range from complete autonomy to shared autonomy to manual navigation by a joystick or other means. Shared autonomy is valuable because it allows the user and the robot to complement each other, to correct each other's mistakes and to avoid collisions. In this paper, we present an approach that can learn to replicate path selection according to the wheelchair user's individual, often subjective, criteria in order to reduce the number of times the user has to intervene during automatic navigation. This is achieved by learning to rank paths using a support vector machine trained on selections made by the user in a simulator. If the classifier's confidence in the top ranked path is high, it is executed without requesting confirmation from the user. Otherwise, the choice is deferred to the user. Simulations and laboratory experiments using two path generation strategies demonstrate the effectiveness of our approach.",
author = "Yizhe Chang and Mohammed Kutbi and Nikolaos Agadakos and Bo Sun and Philippos Mordohai",
year = "2018",
month = "1",
day = "19",
doi = "https://doi.org/10.1109/ICCVW.2017.176",
language = "English (US)",
series = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1490--1499",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
address = "United States",

}

Chang, Y, Kutbi, M, Agadakos, N, Sun, B & Mordohai, P 2018, A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences. in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1490-1499, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 10/22/17. https://doi.org/10.1109/ICCVW.2017.176

A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences. / Chang, Yizhe; Kutbi, Mohammed; Agadakos, Nikolaos; Sun, Bo; Mordohai, Philippos.

Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1490-1499 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January).

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

TY - GEN

T1 - A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences

AU - Chang, Yizhe

AU - Kutbi, Mohammed

AU - Agadakos, Nikolaos

AU - Sun, Bo

AU - Mordohai, Philippos

PY - 2018/1/19

Y1 - 2018/1/19

N2 - Research on robotic wheelchairs covers a broad range from complete autonomy to shared autonomy to manual navigation by a joystick or other means. Shared autonomy is valuable because it allows the user and the robot to complement each other, to correct each other's mistakes and to avoid collisions. In this paper, we present an approach that can learn to replicate path selection according to the wheelchair user's individual, often subjective, criteria in order to reduce the number of times the user has to intervene during automatic navigation. This is achieved by learning to rank paths using a support vector machine trained on selections made by the user in a simulator. If the classifier's confidence in the top ranked path is high, it is executed without requesting confirmation from the user. Otherwise, the choice is deferred to the user. Simulations and laboratory experiments using two path generation strategies demonstrate the effectiveness of our approach.

AB - Research on robotic wheelchairs covers a broad range from complete autonomy to shared autonomy to manual navigation by a joystick or other means. Shared autonomy is valuable because it allows the user and the robot to complement each other, to correct each other's mistakes and to avoid collisions. In this paper, we present an approach that can learn to replicate path selection according to the wheelchair user's individual, often subjective, criteria in order to reduce the number of times the user has to intervene during automatic navigation. This is achieved by learning to rank paths using a support vector machine trained on selections made by the user in a simulator. If the classifier's confidence in the top ranked path is high, it is executed without requesting confirmation from the user. Otherwise, the choice is deferred to the user. Simulations and laboratory experiments using two path generation strategies demonstrate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=85046247435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046247435&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/ICCVW.2017.176

DO - https://doi.org/10.1109/ICCVW.2017.176

M3 - Conference contribution

T3 - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

SP - 1490

EP - 1499

BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chang Y, Kutbi M, Agadakos N, Sun B, Mordohai P. A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1490-1499. (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017). https://doi.org/10.1109/ICCVW.2017.176