Learning reactive robot behavior for autonomous valve turning

Seyed Reza Ahmadzadeh, Petar Kormushev, Rodrigo S. Jamisola, Darwin G. Caldwell

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

3 Citations (Scopus)

Abstract

A learning approach is proposed for the challenging task of autonomous robotic valve turning in the presence of active disturbances and uncertainties. The valve turning task comprises two phases: reaching and turning. For the reaching phase the manipulator learns how to generate trajectories to reach or retract from the target. The learning is based on a set of trajectories demonstrated in advance by the operator. The turning phase is accomplished using a hybrid force/motion control strategy. Furthermore, a reactive decision making system is devised to react to the disturbances and uncertainties arising during the valve turning process. The reactive controller monitors the changes in force, movement of the arm with respect to the valve, and changes in the distance to the target. Observing the uncertainties, the reactive system modulates the valve turning task by changing the direction and rate of the movement. A real-world experiment with a robot manipulator mounted on a movable base is conducted to show the efficiency and validity of the proposed approach.

Original languageEnglish
Title of host publication2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
PublisherIEEE Computer Society
Pages366-373
Number of pages8
Volume2015-February
ISBN (Electronic)9781479971749
DOIs
Publication statusPublished - Jan 1 2015
Event2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014 - Madrid, Spain
Duration: Nov 18 2014Nov 20 2014

Other

Other2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
CountrySpain
CityMadrid
Period11/18/1411/20/14

Fingerprint

Robots
Manipulators
Trajectories
Force control
Motion control
Robotics
Decision making
Controllers
Uncertainty
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Ahmadzadeh, S. R., Kormushev, P., Jamisola, R. S., & Caldwell, D. G. (2015). Learning reactive robot behavior for autonomous valve turning. In 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014 (Vol. 2015-February, pp. 366-373). [7041386] IEEE Computer Society. https://doi.org/10.1109/HUMANOIDS.2014.7041386
Ahmadzadeh, Seyed Reza ; Kormushev, Petar ; Jamisola, Rodrigo S. ; Caldwell, Darwin G. / Learning reactive robot behavior for autonomous valve turning. 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014. Vol. 2015-February IEEE Computer Society, 2015. pp. 366-373
@inproceedings{48bb62fb328e4fd689e8f3795717bdd1,
title = "Learning reactive robot behavior for autonomous valve turning",
abstract = "A learning approach is proposed for the challenging task of autonomous robotic valve turning in the presence of active disturbances and uncertainties. The valve turning task comprises two phases: reaching and turning. For the reaching phase the manipulator learns how to generate trajectories to reach or retract from the target. The learning is based on a set of trajectories demonstrated in advance by the operator. The turning phase is accomplished using a hybrid force/motion control strategy. Furthermore, a reactive decision making system is devised to react to the disturbances and uncertainties arising during the valve turning process. The reactive controller monitors the changes in force, movement of the arm with respect to the valve, and changes in the distance to the target. Observing the uncertainties, the reactive system modulates the valve turning task by changing the direction and rate of the movement. A real-world experiment with a robot manipulator mounted on a movable base is conducted to show the efficiency and validity of the proposed approach.",
author = "Ahmadzadeh, {Seyed Reza} and Petar Kormushev and Jamisola, {Rodrigo S.} and Caldwell, {Darwin G.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/HUMANOIDS.2014.7041386",
language = "English",
volume = "2015-February",
pages = "366--373",
booktitle = "2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014",
publisher = "IEEE Computer Society",
address = "United States",

}

Ahmadzadeh, SR, Kormushev, P, Jamisola, RS & Caldwell, DG 2015, Learning reactive robot behavior for autonomous valve turning. in 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014. vol. 2015-February, 7041386, IEEE Computer Society, pp. 366-373, 2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, 11/18/14. https://doi.org/10.1109/HUMANOIDS.2014.7041386

Learning reactive robot behavior for autonomous valve turning. / Ahmadzadeh, Seyed Reza; Kormushev, Petar; Jamisola, Rodrigo S.; Caldwell, Darwin G.

2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014. Vol. 2015-February IEEE Computer Society, 2015. p. 366-373 7041386.

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

TY - GEN

T1 - Learning reactive robot behavior for autonomous valve turning

AU - Ahmadzadeh, Seyed Reza

AU - Kormushev, Petar

AU - Jamisola, Rodrigo S.

AU - Caldwell, Darwin G.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A learning approach is proposed for the challenging task of autonomous robotic valve turning in the presence of active disturbances and uncertainties. The valve turning task comprises two phases: reaching and turning. For the reaching phase the manipulator learns how to generate trajectories to reach or retract from the target. The learning is based on a set of trajectories demonstrated in advance by the operator. The turning phase is accomplished using a hybrid force/motion control strategy. Furthermore, a reactive decision making system is devised to react to the disturbances and uncertainties arising during the valve turning process. The reactive controller monitors the changes in force, movement of the arm with respect to the valve, and changes in the distance to the target. Observing the uncertainties, the reactive system modulates the valve turning task by changing the direction and rate of the movement. A real-world experiment with a robot manipulator mounted on a movable base is conducted to show the efficiency and validity of the proposed approach.

AB - A learning approach is proposed for the challenging task of autonomous robotic valve turning in the presence of active disturbances and uncertainties. The valve turning task comprises two phases: reaching and turning. For the reaching phase the manipulator learns how to generate trajectories to reach or retract from the target. The learning is based on a set of trajectories demonstrated in advance by the operator. The turning phase is accomplished using a hybrid force/motion control strategy. Furthermore, a reactive decision making system is devised to react to the disturbances and uncertainties arising during the valve turning process. The reactive controller monitors the changes in force, movement of the arm with respect to the valve, and changes in the distance to the target. Observing the uncertainties, the reactive system modulates the valve turning task by changing the direction and rate of the movement. A real-world experiment with a robot manipulator mounted on a movable base is conducted to show the efficiency and validity of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=84945174531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945174531&partnerID=8YFLogxK

U2 - 10.1109/HUMANOIDS.2014.7041386

DO - 10.1109/HUMANOIDS.2014.7041386

M3 - Conference contribution

AN - SCOPUS:84945174531

VL - 2015-February

SP - 366

EP - 373

BT - 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014

PB - IEEE Computer Society

ER -

Ahmadzadeh SR, Kormushev P, Jamisola RS, Caldwell DG. Learning reactive robot behavior for autonomous valve turning. In 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014. Vol. 2015-February. IEEE Computer Society. 2015. p. 366-373. 7041386 https://doi.org/10.1109/HUMANOIDS.2014.7041386