Learning multiple collaborative tasks with a mixture of Interaction Primitives

Marco Ewerton, Gerhard Neumann, Rudolf Lioutikov, Hani Ben Amor, Jan Peters, Guilherme Maeda

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

32 Citations (Scopus)

Abstract

Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1535-1542
Number of pages8
Volume2015-June
EditionJune
DOIs
StatePublished - Jun 29 2015
Externally publishedYes
Event2015 IEEE International Conference on Robotics and Automation, ICRA 2015 - Seattle, United States
Duration: May 26 2015May 30 2015

Other

Other2015 IEEE International Conference on Robotics and Automation, ICRA 2015
CountryUnited States
CitySeattle
Period5/26/155/30/15

Fingerprint

Robots
Demonstrations
Robotic arms
Experiments

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Ewerton, M., Neumann, G., Lioutikov, R., Ben Amor, H., Peters, J., & Maeda, G. (2015). Learning multiple collaborative tasks with a mixture of Interaction Primitives. In Proceedings - IEEE International Conference on Robotics and Automation (June ed., Vol. 2015-June, pp. 1535-1542). [7139393] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2015.7139393

Learning multiple collaborative tasks with a mixture of Interaction Primitives. / Ewerton, Marco; Neumann, Gerhard; Lioutikov, Rudolf; Ben Amor, Hani; Peters, Jan; Maeda, Guilherme.

Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1535-1542 7139393.

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

Ewerton, M, Neumann, G, Lioutikov, R, Ben Amor, H, Peters, J & Maeda, G 2015, Learning multiple collaborative tasks with a mixture of Interaction Primitives. in Proceedings - IEEE International Conference on Robotics and Automation. June edn, vol. 2015-June, 7139393, Institute of Electrical and Electronics Engineers Inc., pp. 1535-1542, 2015 IEEE International Conference on Robotics and Automation, ICRA 2015, Seattle, United States, 5/26/15. https://doi.org/10.1109/ICRA.2015.7139393
Ewerton M, Neumann G, Lioutikov R, Ben Amor H, Peters J, Maeda G. Learning multiple collaborative tasks with a mixture of Interaction Primitives. In Proceedings - IEEE International Conference on Robotics and Automation. June ed. Vol. 2015-June. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1535-1542. 7139393 https://doi.org/10.1109/ICRA.2015.7139393
Ewerton, Marco ; Neumann, Gerhard ; Lioutikov, Rudolf ; Ben Amor, Hani ; Peters, Jan ; Maeda, Guilherme. / Learning multiple collaborative tasks with a mixture of Interaction Primitives. Proceedings - IEEE International Conference on Robotics and Automation. Vol. 2015-June June. ed. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1535-1542
@inproceedings{3e269c73b84648239b5e714ea2058a2a,
title = "Learning multiple collaborative tasks with a mixture of Interaction Primitives",
abstract = "Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.",
author = "Marco Ewerton and Gerhard Neumann and Rudolf Lioutikov and {Ben Amor}, Hani and Jan Peters and Guilherme Maeda",
year = "2015",
month = "6",
day = "29",
doi = "10.1109/ICRA.2015.7139393",
language = "English (US)",
volume = "2015-June",
pages = "1535--1542",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
edition = "June",

}

TY - GEN

T1 - Learning multiple collaborative tasks with a mixture of Interaction Primitives

AU - Ewerton, Marco

AU - Neumann, Gerhard

AU - Lioutikov, Rudolf

AU - Ben Amor, Hani

AU - Peters, Jan

AU - Maeda, Guilherme

PY - 2015/6/29

Y1 - 2015/6/29

N2 - Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.

AB - Robots that interact with humans must learn to not only adapt to different human partners but also to new interactions. Such a form of learning can be achieved by demonstrations and imitation. A recently introduced method to learn interactions from demonstrations is the framework of Interaction Primitives. While this framework is limited to represent and generalize a single interaction pattern, in practice, interactions between a human and a robot can consist of many different patterns. To overcome this limitation this paper proposes a Mixture of Interaction Primitives to learn multiple interaction patterns from unlabeled demonstrations. Specifically the proposed method uses Gaussian Mixture Models of Interaction Primitives to model nonlinear correlations between the movements of the different agents. We validate our algorithm with two experiments involving interactive tasks between a human and a lightweight robotic arm. In the first, we compare our proposed method with conventional Interaction Primitives in a toy problem scenario where the robot and the human are not linearly correlated. In the second, we present a proof-of-concept experiment where the robot assists a human in assembling a box.

UR - http://www.scopus.com/inward/record.url?scp=84938276816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938276816&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2015.7139393

DO - 10.1109/ICRA.2015.7139393

M3 - Conference contribution

VL - 2015-June

SP - 1535

EP - 1542

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - Institute of Electrical and Electronics Engineers Inc.

ER -