An enhanced teaching interface for a robot using DMP and GMR

Chunxu Li; Chenguang Yang; Zhaojie Ju; Andy S. K. Annamalai

doi:10.1007/s41315-018-0046-x

An enhanced teaching interface for a robot using DMP and GMR

Chunxu Li
, Chenguang Yang
, Zhaojie Ju
, Andy S. K. Annamalai

UHI Moray

Publikation › Begutachtung

24 Zitate (Scopus)

191 Downloads (Pure)

Abstract

This paper develops an enhanced teaching interface tested on both a Baxter robot and a KUKA iiwa robot. Movements are
collected from a human demonstrator by using a Kinect v2 sensor, and then the data is sent to a remote PC for the teleoperation
with Baxter. Meanwhile, data is saved locally for the playback process of the Baxter. The dynamic movement primitive
(DMP) is used to model and generalize the movements. In order to learn from multiple demonstrations accurately, dynamic
time warping (DTW), is used to pretreat the data recorded by the robot platform and Gaussian mixture model (GMM), aiming
to generate multiple patterns after the teaching process, are employed for the calculation of the DMP. Then the Gaussian
mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space.
This proposed approach is tested by performing two tasks on a KUKA iiwa and a Baxter robot.

Originalsprache	English
Seiten (von - bis)	110-121
Seitenumfang	12
Fachzeitschrift	International Journal of Intelligent Robotics and Applications
Jahrgang	2
Ausgabenummer	1
DOIs	https://doi.org/10.1007/s41315-018-0046-x
Publikationsstatus	Published - 8 März 2018

Zugriff auf Dokument

10.1007/s41315-018-0046-xLizenz:

March 2018, International Journal of Intelligent Robotics and Applications PublicationFinal published version, 1,99 MBLizenz:

http://link.springer.com/10.1007/s41315-018-0046-x

Dieses zitieren

@article{742b30a70da04bd69764b2a4ff85c144,

title = "An enhanced teaching interface for a robot using DMP and GMR",

abstract = "This paper develops an enhanced teaching interface tested on both a Baxter robot and a KUKA iiwa robot. Movements are collected from a human demonstrator by using a Kinect v2 sensor, and then the data is sent to a remote PC for the teleoperation with Baxter. Meanwhile, data is saved locally for the playback process of the Baxter. The dynamic movement primitive (DMP) is used to model and generalize the movements. In order to learn from multiple demonstrations accurately, dynamic time warping (DTW), is used to pretreat the data recorded by the robot platform and Gaussian mixture model (GMM), aiming to generate multiple patterns after the teaching process, are employed for the calculation of the DMP. Then the Gaussian mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space. This proposed approach is tested by performing two tasks on a KUKA iiwa and a Baxter robot.",

author = "Chunxu Li and Chenguang Yang and Zhaojie Ju and Annamalai, \{Andy S. K.\}",

note = "{\textcopyright} The Author(s) 2018",

year = "2018",

month = mar,

day = "8",

doi = "10.1007/s41315-018-0046-x",

language = "English",

volume = "2",

pages = "110--121",

journal = "International Journal of Intelligent Robotics and Applications ",

issn = "2366-598X",

publisher = "Springer-Verlag",

number = "1",

}

TY - JOUR

T1 - An enhanced teaching interface for a robot using DMP and GMR

AU - Li, Chunxu

AU - Yang, Chenguang

AU - Ju, Zhaojie

AU - Annamalai, Andy S. K.

PY - 2018/3/8

Y1 - 2018/3/8

N2 - This paper develops an enhanced teaching interface tested on both a Baxter robot and a KUKA iiwa robot. Movements are collected from a human demonstrator by using a Kinect v2 sensor, and then the data is sent to a remote PC for the teleoperation with Baxter. Meanwhile, data is saved locally for the playback process of the Baxter. The dynamic movement primitive (DMP) is used to model and generalize the movements. In order to learn from multiple demonstrations accurately, dynamic time warping (DTW), is used to pretreat the data recorded by the robot platform and Gaussian mixture model (GMM), aiming to generate multiple patterns after the teaching process, are employed for the calculation of the DMP. Then the Gaussian mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space. This proposed approach is tested by performing two tasks on a KUKA iiwa and a Baxter robot.

AB - This paper develops an enhanced teaching interface tested on both a Baxter robot and a KUKA iiwa robot. Movements are collected from a human demonstrator by using a Kinect v2 sensor, and then the data is sent to a remote PC for the teleoperation with Baxter. Meanwhile, data is saved locally for the playback process of the Baxter. The dynamic movement primitive (DMP) is used to model and generalize the movements. In order to learn from multiple demonstrations accurately, dynamic time warping (DTW), is used to pretreat the data recorded by the robot platform and Gaussian mixture model (GMM), aiming to generate multiple patterns after the teaching process, are employed for the calculation of the DMP. Then the Gaussian mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space. This proposed approach is tested by performing two tasks on a KUKA iiwa and a Baxter robot.

U2 - 10.1007/s41315-018-0046-x

DO - 10.1007/s41315-018-0046-x

M3 - Article

SN - 2366-598X

VL - 2

SP - 110

EP - 121

JO - International Journal of Intelligent Robotics and Applications

JF - International Journal of Intelligent Robotics and Applications

IS - 1

ER -

An enhanced teaching interface for a robot using DMP and GMR

Abstract

Zugriff auf Dokument

Fingerprint

Dieses zitieren