TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Learning from Demonstration for Hydraulic Manipulators

Tutkimustuotosvertaisarvioitu

Standard

Learning from Demonstration for Hydraulic Manipulators. / Suomalainen, M.; Koivumäki, J.; Lampinen, S.; Kyrki, V.; Mattila, J.

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018. s. 3579-3586.

Tutkimustuotosvertaisarvioitu

Harvard

Suomalainen, M, Koivumäki, J, Lampinen, S, Kyrki, V & Mattila, J 2018, Learning from Demonstration for Hydraulic Manipulators. julkaisussa 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, Sivut 3579-3586, IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, 1/01/00. https://doi.org/10.1109/IROS.2018.8594285

APA

Suomalainen, M., Koivumäki, J., Lampinen, S., Kyrki, V., & Mattila, J. (2018). Learning from Demonstration for Hydraulic Manipulators. teoksessa 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Sivut 3579-3586). IEEE. https://doi.org/10.1109/IROS.2018.8594285

Vancouver

Suomalainen M, Koivumäki J, Lampinen S, Kyrki V, Mattila J. Learning from Demonstration for Hydraulic Manipulators. julkaisussa 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE. 2018. s. 3579-3586 https://doi.org/10.1109/IROS.2018.8594285

Author

Suomalainen, M. ; Koivumäki, J. ; Lampinen, S. ; Kyrki, V. ; Mattila, J. / Learning from Demonstration for Hydraulic Manipulators. 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018. Sivut 3579-3586

Bibtex - Lataa

@inproceedings{2574ee4274434362bc973e25302c48d7,
title = "Learning from Demonstration for Hydraulic Manipulators",
abstract = "This paper presents, for the first time, a method for learning in-contact tasks from a teleoperated demonstration with a hydraulic manipulator. Due to the use of extremely powerful hydraulic manipulator, a force-reflected bilateral teleoperation is the most reasonable method of giving a human demonstration. An advanced subsystem-dynamic-based control design framework, virtual decomposition control (VDC), is used to design a stability-guaranteed controller for the teleoperation system, while taking into account the full nonlinear dynamics of the master and slave manipulators. The use of fragile force/torque sensor at the tip of the hydraulic slave manipulator is avoided by estimating the contact forces from the manipulator actuators' chamber pressures. In the proposed learning method, it is observed that a surface-sliding tool has a friction-dependent range of directions (between the actual direction of motion and the contact force) from which the manipulator can apply force to produce the sliding motion. By this intuition, an intersection of these ranges can be taken over a motion to robustly find a desired direction for the motion from one or more demonstrations. The compliant axes required to reproduce the motion can be found by assuming that all motions outside the desired direction is caused by the environment, signalling the need for compliance. Finally, the learning method is incorporated to a novel VDC-based impedance control method to learn compliant behaviour from teleoperated human demonstrations. Experiments with 2-DOF hydraulic manipulator with a 475kg payload demonstrate the suitability and effectiveness of the proposed method to perform learning from demonstration (LfD) with heavy-duty hydraulic manipulators.",
keywords = "Hydraulic systems, Force, Task analysis, Manipulator dynamics, Impedance, Control design",
author = "M. Suomalainen and J. Koivum{\"a}ki and S. Lampinen and V. Kyrki and J. Mattila",
year = "2018",
month = "10",
day = "1",
doi = "10.1109/IROS.2018.8594285",
language = "English",
isbn = "978-1-5386-8095-7",
publisher = "IEEE",
pages = "3579--3586",
booktitle = "2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Learning from Demonstration for Hydraulic Manipulators

AU - Suomalainen, M.

AU - Koivumäki, J.

AU - Lampinen, S.

AU - Kyrki, V.

AU - Mattila, J.

PY - 2018/10/1

Y1 - 2018/10/1

N2 - This paper presents, for the first time, a method for learning in-contact tasks from a teleoperated demonstration with a hydraulic manipulator. Due to the use of extremely powerful hydraulic manipulator, a force-reflected bilateral teleoperation is the most reasonable method of giving a human demonstration. An advanced subsystem-dynamic-based control design framework, virtual decomposition control (VDC), is used to design a stability-guaranteed controller for the teleoperation system, while taking into account the full nonlinear dynamics of the master and slave manipulators. The use of fragile force/torque sensor at the tip of the hydraulic slave manipulator is avoided by estimating the contact forces from the manipulator actuators' chamber pressures. In the proposed learning method, it is observed that a surface-sliding tool has a friction-dependent range of directions (between the actual direction of motion and the contact force) from which the manipulator can apply force to produce the sliding motion. By this intuition, an intersection of these ranges can be taken over a motion to robustly find a desired direction for the motion from one or more demonstrations. The compliant axes required to reproduce the motion can be found by assuming that all motions outside the desired direction is caused by the environment, signalling the need for compliance. Finally, the learning method is incorporated to a novel VDC-based impedance control method to learn compliant behaviour from teleoperated human demonstrations. Experiments with 2-DOF hydraulic manipulator with a 475kg payload demonstrate the suitability and effectiveness of the proposed method to perform learning from demonstration (LfD) with heavy-duty hydraulic manipulators.

AB - This paper presents, for the first time, a method for learning in-contact tasks from a teleoperated demonstration with a hydraulic manipulator. Due to the use of extremely powerful hydraulic manipulator, a force-reflected bilateral teleoperation is the most reasonable method of giving a human demonstration. An advanced subsystem-dynamic-based control design framework, virtual decomposition control (VDC), is used to design a stability-guaranteed controller for the teleoperation system, while taking into account the full nonlinear dynamics of the master and slave manipulators. The use of fragile force/torque sensor at the tip of the hydraulic slave manipulator is avoided by estimating the contact forces from the manipulator actuators' chamber pressures. In the proposed learning method, it is observed that a surface-sliding tool has a friction-dependent range of directions (between the actual direction of motion and the contact force) from which the manipulator can apply force to produce the sliding motion. By this intuition, an intersection of these ranges can be taken over a motion to robustly find a desired direction for the motion from one or more demonstrations. The compliant axes required to reproduce the motion can be found by assuming that all motions outside the desired direction is caused by the environment, signalling the need for compliance. Finally, the learning method is incorporated to a novel VDC-based impedance control method to learn compliant behaviour from teleoperated human demonstrations. Experiments with 2-DOF hydraulic manipulator with a 475kg payload demonstrate the suitability and effectiveness of the proposed method to perform learning from demonstration (LfD) with heavy-duty hydraulic manipulators.

KW - Hydraulic systems

KW - Force

KW - Task analysis

KW - Manipulator dynamics

KW - Impedance

KW - Control design

U2 - 10.1109/IROS.2018.8594285

DO - 10.1109/IROS.2018.8594285

M3 - Conference contribution

SN - 978-1-5386-8095-7

SP - 3579

EP - 3586

BT - 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - IEEE

ER -