Robot programming by demonstration of multiple tasks within a common environment

Tohid Alizadeh, Batyrkhan Saduanov

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

2 Citations (Scopus)

Abstract

Most of the available robot programming by demonstration (PbD) approaches focus on learning a single task, in a given environmental situation. In this paper, we propose to learn multiple tasks together, within a common environment, using one of the available PbD approaches. Task-parameterized Gaussian mixture model (TP-GMM) is used at the core of the proposed approach. A database of TP-GMMs will be constructed for the tasks, and it will be used to provide the reproduction when needed. The environment will be shared between different tasks, in other words, all the available objects will be considered as external task parameters (TPs), as they may modulate the task. During the learning part, the relevance of the task parameters will be extracted for each task, and the information will be stored together with the parameters of the corresponding updated TP-GMM. For reproduction, the end user will specify the task and the robot will be able to pick the relevant TP-GMM and the relevant task parameters and reproduce the movement. The proposed approach is tested both in simulation and using a robotic experiment.

Original languageEnglish
Title of host publicationMFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages608-613
Number of pages6
Volume2017-November
ISBN (Electronic)9781509060641
DOIs
Publication statusPublished - Dec 7 2017
Event13th IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2017 - Daegu, Korea, Republic of
Duration: Nov 16 2017Nov 18 2017

Conference

Conference13th IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2017
CountryKorea, Republic of
CityDaegu
Period11/16/1711/18/17

Fingerprint

Robot programming
Demonstrations
Robotics
Robots
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Science Applications

Cite this

Alizadeh, T., & Saduanov, B. (2017). Robot programming by demonstration of multiple tasks within a common environment. In MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (Vol. 2017-November, pp. 608-613). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MFI.2017.8170389

Robot programming by demonstration of multiple tasks within a common environment. / Alizadeh, Tohid; Saduanov, Batyrkhan.

MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2017-November Institute of Electrical and Electronics Engineers Inc., 2017. p. 608-613.

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

Alizadeh, T & Saduanov, B 2017, Robot programming by demonstration of multiple tasks within a common environment. in MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. vol. 2017-November, Institute of Electrical and Electronics Engineers Inc., pp. 608-613, 13th IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2017, Daegu, Korea, Republic of, 11/16/17. https://doi.org/10.1109/MFI.2017.8170389
Alizadeh T, Saduanov B. Robot programming by demonstration of multiple tasks within a common environment. In MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2017-November. Institute of Electrical and Electronics Engineers Inc. 2017. p. 608-613 https://doi.org/10.1109/MFI.2017.8170389
Alizadeh, Tohid ; Saduanov, Batyrkhan. / Robot programming by demonstration of multiple tasks within a common environment. MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2017-November Institute of Electrical and Electronics Engineers Inc., 2017. pp. 608-613
@inproceedings{caa3b890f7d947bab4794098cd41e980,
title = "Robot programming by demonstration of multiple tasks within a common environment",
abstract = "Most of the available robot programming by demonstration (PbD) approaches focus on learning a single task, in a given environmental situation. In this paper, we propose to learn multiple tasks together, within a common environment, using one of the available PbD approaches. Task-parameterized Gaussian mixture model (TP-GMM) is used at the core of the proposed approach. A database of TP-GMMs will be constructed for the tasks, and it will be used to provide the reproduction when needed. The environment will be shared between different tasks, in other words, all the available objects will be considered as external task parameters (TPs), as they may modulate the task. During the learning part, the relevance of the task parameters will be extracted for each task, and the information will be stored together with the parameters of the corresponding updated TP-GMM. For reproduction, the end user will specify the task and the robot will be able to pick the relevant TP-GMM and the relevant task parameters and reproduce the movement. The proposed approach is tested both in simulation and using a robotic experiment.",
author = "Tohid Alizadeh and Batyrkhan Saduanov",
year = "2017",
month = "12",
day = "7",
doi = "10.1109/MFI.2017.8170389",
language = "English",
volume = "2017-November",
pages = "608--613",
booktitle = "MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Robot programming by demonstration of multiple tasks within a common environment

AU - Alizadeh, Tohid

AU - Saduanov, Batyrkhan

PY - 2017/12/7

Y1 - 2017/12/7

N2 - Most of the available robot programming by demonstration (PbD) approaches focus on learning a single task, in a given environmental situation. In this paper, we propose to learn multiple tasks together, within a common environment, using one of the available PbD approaches. Task-parameterized Gaussian mixture model (TP-GMM) is used at the core of the proposed approach. A database of TP-GMMs will be constructed for the tasks, and it will be used to provide the reproduction when needed. The environment will be shared between different tasks, in other words, all the available objects will be considered as external task parameters (TPs), as they may modulate the task. During the learning part, the relevance of the task parameters will be extracted for each task, and the information will be stored together with the parameters of the corresponding updated TP-GMM. For reproduction, the end user will specify the task and the robot will be able to pick the relevant TP-GMM and the relevant task parameters and reproduce the movement. The proposed approach is tested both in simulation and using a robotic experiment.

AB - Most of the available robot programming by demonstration (PbD) approaches focus on learning a single task, in a given environmental situation. In this paper, we propose to learn multiple tasks together, within a common environment, using one of the available PbD approaches. Task-parameterized Gaussian mixture model (TP-GMM) is used at the core of the proposed approach. A database of TP-GMMs will be constructed for the tasks, and it will be used to provide the reproduction when needed. The environment will be shared between different tasks, in other words, all the available objects will be considered as external task parameters (TPs), as they may modulate the task. During the learning part, the relevance of the task parameters will be extracted for each task, and the information will be stored together with the parameters of the corresponding updated TP-GMM. For reproduction, the end user will specify the task and the robot will be able to pick the relevant TP-GMM and the relevant task parameters and reproduce the movement. The proposed approach is tested both in simulation and using a robotic experiment.

UR - http://www.scopus.com/inward/record.url?scp=85042371239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042371239&partnerID=8YFLogxK

U2 - 10.1109/MFI.2017.8170389

DO - 10.1109/MFI.2017.8170389

M3 - Conference contribution

AN - SCOPUS:85042371239

VL - 2017-November

SP - 608

EP - 613

BT - MFI 2017 - 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -