No Cover Image

Staff Thesis 709 views 670 downloads

Learning Algorithm Design for Human-Robot Skill Transfer

Chunxu Li Orcid Logo

Swansea University Author: Chunxu Li Orcid Logo

  • Li_Chunxu_PhD_Thesis_Final_Redacted.pdf

    PDF | E-Thesis – open access

    A selection of third party content is redacted or is partially redacted from this thesis due to copyright restrictions.

    Download (9.55MB)

DOI (Published version): 10.23889/suthesis.54879

Abstract

In this research, we develop an intelligent learning scheme for performing human-robot skills transfer. Techniques adopted in the scheme include the Dynamic Movement Prim- itive (DMP) method with Dynamic Time Warping (DTW), Gaussian Mixture Model (G- MM) with Gaussian Mixture Regression (GMR) and th...

Full description

Published: Swansea Swansea University 2019
Online Access: http://dx.doi.org/10.23889/suthesis.54879
URI: https://cronfa.swan.ac.uk/Record/cronfa54879
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-08-05T09:49:54Z
last_indexed 2021-05-29T03:18:13Z
id cronfa54879
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>54879</id><entry>2020-08-05</entry><title>Learning Algorithm Design for Human-Robot Skill Transfer</title><swanseaauthors><author><sid>e0fb9afcfbd5e5d5b590a066538d3992</sid><ORCID>NULL</ORCID><firstname>Chunxu</firstname><surname>Li</surname><name>Chunxu Li</name><active>true</active><ethesisStudent>true</ethesisStudent></author></swanseaauthors><date>2020-08-05</date><abstract>In this research, we develop an intelligent learning scheme for performing human-robot skills transfer. Techniques adopted in the scheme include the Dynamic Movement Prim- itive (DMP) method with Dynamic Time Warping (DTW), Gaussian Mixture Model (G- MM) with Gaussian Mixture Regression (GMR) and the Radical Basis Function Neural Networks (RBFNNs). A series of experiments are conducted on a Baxter robot, a NAO robot and a KUKA iiwa robot to verify the effectiveness of the proposed design.During the design of the intelligent learning scheme, an online tracking system is de- veloped to control the arm and head movement of the NAO robot using a Kinect sensor. The NAO robot is a humanoid robot with 5 degrees of freedom (DOF) for each arm. The joint motions of the operator’s head and arm are captured by a Kinect V2 sensor, and this information is then transferred into the workspace via the forward and inverse kinematics. In addition, to improve the tracking performance, a Kalman filter is further employed to fuse motion signals from the operator sensed by the Kinect V2 sensor and a pair of MYO armbands, so as to teleoperate the Baxter robot. In this regard, a new strategy is developed using the vector approach to accomplish a specific motion capture task. For instance, the arm motion of the operator is captured by a Kinect sensor and programmed through a processing software. Two MYO armbands with embedded inertial measurement units are worn by the operator to aid the robots in detecting and replicating the operator’s arm movements. For this purpose, the armbands help to recognize and calculate the precise velocity of motion of the operator’s arm. Additionally, a neural network based adaptive controller is designed and implemented on the Baxter robot to illustrate the validation forthe teleoperation of the Baxter robot.Subsequently, an enhanced teaching interface has been developed for the robot using DMP and GMR. Motion signals are collected from a human demonstrator via the Kinect v2 sensor, and the data is sent to a remote PC for teleoperating the Baxter robot. At this stage, the DMP is utilized to model and generalize the movements. In order to learn from multiple demonstrations, DTW is used for the preprocessing of the data recorded on the robot platform, and GMM is employed for the evaluation of DMP to generate multiple patterns after the completion of the teaching process. Next, we apply the GMR algorithm to generate a synthesized trajectory to minimize position errors in the three dimensional (3D) space. This approach has been tested by performing tasks on a KUKA iiwa and a Baxter robot, respectively.Finally, an optimized DMP is added to the teaching interface. A character recombination technology based on DMP segmentation that uses verbal command has also been developed and incorporated in a Baxter robot platform. To imitate the recorded motion signals produced by the demonstrator, the operator trains the Baxter robot by physically guiding it to complete the given task. This is repeated five times, and the generated training data set is utilized via the playback system. Subsequently, the DTW is employed to preprocess the experimental data. For modelling and overall movement control, DMP is chosen. The GMM is used to generate multiple patterns after implementing the teaching process. Next, we employ the GMR algorithm to reduce position errors in the 3D space after a synthesized trajectory has been generated. The Baxter robot, remotely controlled by the user datagram protocol (UDP) in a PC, records and reproduces every trajectory. Additionally, Dragon Natural Speaking software is adopted to transcribe the voice data. This proposed approach has been verified by enabling the Baxter robot to perform a writing task of drawing robot has been taught to write only one character.</abstract><type>Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Swansea University</publisher><placeOfPublication>Swansea</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>17</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-10-17</publishedDate><doi>10.23889/suthesis.54879</doi><url>http://dx.doi.org/10.23889/suthesis.54879</url><notes/><college>COLLEGE NANME</college><department>College of Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Chenguang, Yang.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><apcterm/><funders/><projectreference/><lastEdited>2024-04-10T07:21:08.3287974</lastEdited><Created>2020-08-05T10:24:32.2119993</Created><path><level id="1">Professional Services</level><level id="2"/></path><authors><author><firstname>Chunxu</firstname><surname>Li</surname><orcid>NULL</orcid><order>1</order></author></authors><documents><document><filename>54879__17860__1b50888792b442a4b07df4e3b901f975.pdf</filename><originalFilename>Li_Chunxu_PhD_Thesis_Final_Redacted.pdf</originalFilename><uploaded>2020-08-05T10:51:05.9668354</uploaded><type>Output</type><contentLength>10010197</contentLength><contentType>application/pdf</contentType><version>E-Thesis – open access</version><cronfaStatus>true</cronfaStatus><documentNotes>A selection of third party content is redacted or is partially redacted from this thesis due to copyright restrictions.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling v2 54879 2020-08-05 Learning Algorithm Design for Human-Robot Skill Transfer e0fb9afcfbd5e5d5b590a066538d3992 NULL Chunxu Li Chunxu Li true true 2020-08-05 In this research, we develop an intelligent learning scheme for performing human-robot skills transfer. Techniques adopted in the scheme include the Dynamic Movement Prim- itive (DMP) method with Dynamic Time Warping (DTW), Gaussian Mixture Model (G- MM) with Gaussian Mixture Regression (GMR) and the Radical Basis Function Neural Networks (RBFNNs). A series of experiments are conducted on a Baxter robot, a NAO robot and a KUKA iiwa robot to verify the effectiveness of the proposed design.During the design of the intelligent learning scheme, an online tracking system is de- veloped to control the arm and head movement of the NAO robot using a Kinect sensor. The NAO robot is a humanoid robot with 5 degrees of freedom (DOF) for each arm. The joint motions of the operator’s head and arm are captured by a Kinect V2 sensor, and this information is then transferred into the workspace via the forward and inverse kinematics. In addition, to improve the tracking performance, a Kalman filter is further employed to fuse motion signals from the operator sensed by the Kinect V2 sensor and a pair of MYO armbands, so as to teleoperate the Baxter robot. In this regard, a new strategy is developed using the vector approach to accomplish a specific motion capture task. For instance, the arm motion of the operator is captured by a Kinect sensor and programmed through a processing software. Two MYO armbands with embedded inertial measurement units are worn by the operator to aid the robots in detecting and replicating the operator’s arm movements. For this purpose, the armbands help to recognize and calculate the precise velocity of motion of the operator’s arm. Additionally, a neural network based adaptive controller is designed and implemented on the Baxter robot to illustrate the validation forthe teleoperation of the Baxter robot.Subsequently, an enhanced teaching interface has been developed for the robot using DMP and GMR. Motion signals are collected from a human demonstrator via the Kinect v2 sensor, and the data is sent to a remote PC for teleoperating the Baxter robot. At this stage, the DMP is utilized to model and generalize the movements. In order to learn from multiple demonstrations, DTW is used for the preprocessing of the data recorded on the robot platform, and GMM is employed for the evaluation of DMP to generate multiple patterns after the completion of the teaching process. Next, we apply the GMR algorithm to generate a synthesized trajectory to minimize position errors in the three dimensional (3D) space. This approach has been tested by performing tasks on a KUKA iiwa and a Baxter robot, respectively.Finally, an optimized DMP is added to the teaching interface. A character recombination technology based on DMP segmentation that uses verbal command has also been developed and incorporated in a Baxter robot platform. To imitate the recorded motion signals produced by the demonstrator, the operator trains the Baxter robot by physically guiding it to complete the given task. This is repeated five times, and the generated training data set is utilized via the playback system. Subsequently, the DTW is employed to preprocess the experimental data. For modelling and overall movement control, DMP is chosen. The GMM is used to generate multiple patterns after implementing the teaching process. Next, we employ the GMR algorithm to reduce position errors in the 3D space after a synthesized trajectory has been generated. The Baxter robot, remotely controlled by the user datagram protocol (UDP) in a PC, records and reproduces every trajectory. Additionally, Dragon Natural Speaking software is adopted to transcribe the voice data. This proposed approach has been verified by enabling the Baxter robot to perform a writing task of drawing robot has been taught to write only one character. Thesis Swansea University Swansea 17 10 2019 2019-10-17 10.23889/suthesis.54879 http://dx.doi.org/10.23889/suthesis.54879 COLLEGE NANME College of Engineering COLLEGE CODE Swansea University Chenguang, Yang. Doctoral Ph.D 2024-04-10T07:21:08.3287974 2020-08-05T10:24:32.2119993 Professional Services Chunxu Li NULL 1 54879__17860__1b50888792b442a4b07df4e3b901f975.pdf Li_Chunxu_PhD_Thesis_Final_Redacted.pdf 2020-08-05T10:51:05.9668354 Output 10010197 application/pdf E-Thesis – open access true A selection of third party content is redacted or is partially redacted from this thesis due to copyright restrictions. true eng
title Learning Algorithm Design for Human-Robot Skill Transfer
spellingShingle Learning Algorithm Design for Human-Robot Skill Transfer
Chunxu Li
title_short Learning Algorithm Design for Human-Robot Skill Transfer
title_full Learning Algorithm Design for Human-Robot Skill Transfer
title_fullStr Learning Algorithm Design for Human-Robot Skill Transfer
title_full_unstemmed Learning Algorithm Design for Human-Robot Skill Transfer
title_sort Learning Algorithm Design for Human-Robot Skill Transfer
author_id_str_mv e0fb9afcfbd5e5d5b590a066538d3992
author_id_fullname_str_mv e0fb9afcfbd5e5d5b590a066538d3992_***_Chunxu Li
author Chunxu Li
author2 Chunxu Li
format Staff Thesis
publishDate 2019
institution Swansea University
doi_str_mv 10.23889/suthesis.54879
publisher Swansea University
college_str Professional Services
hierarchytype
hierarchy_top_id professionalservices
hierarchy_top_title Professional Services
hierarchy_parent_id professionalservices
hierarchy_parent_title Professional Services
url http://dx.doi.org/10.23889/suthesis.54879
document_store_str 1
active_str 0
description In this research, we develop an intelligent learning scheme for performing human-robot skills transfer. Techniques adopted in the scheme include the Dynamic Movement Prim- itive (DMP) method with Dynamic Time Warping (DTW), Gaussian Mixture Model (G- MM) with Gaussian Mixture Regression (GMR) and the Radical Basis Function Neural Networks (RBFNNs). A series of experiments are conducted on a Baxter robot, a NAO robot and a KUKA iiwa robot to verify the effectiveness of the proposed design.During the design of the intelligent learning scheme, an online tracking system is de- veloped to control the arm and head movement of the NAO robot using a Kinect sensor. The NAO robot is a humanoid robot with 5 degrees of freedom (DOF) for each arm. The joint motions of the operator’s head and arm are captured by a Kinect V2 sensor, and this information is then transferred into the workspace via the forward and inverse kinematics. In addition, to improve the tracking performance, a Kalman filter is further employed to fuse motion signals from the operator sensed by the Kinect V2 sensor and a pair of MYO armbands, so as to teleoperate the Baxter robot. In this regard, a new strategy is developed using the vector approach to accomplish a specific motion capture task. For instance, the arm motion of the operator is captured by a Kinect sensor and programmed through a processing software. Two MYO armbands with embedded inertial measurement units are worn by the operator to aid the robots in detecting and replicating the operator’s arm movements. For this purpose, the armbands help to recognize and calculate the precise velocity of motion of the operator’s arm. Additionally, a neural network based adaptive controller is designed and implemented on the Baxter robot to illustrate the validation forthe teleoperation of the Baxter robot.Subsequently, an enhanced teaching interface has been developed for the robot using DMP and GMR. Motion signals are collected from a human demonstrator via the Kinect v2 sensor, and the data is sent to a remote PC for teleoperating the Baxter robot. At this stage, the DMP is utilized to model and generalize the movements. In order to learn from multiple demonstrations, DTW is used for the preprocessing of the data recorded on the robot platform, and GMM is employed for the evaluation of DMP to generate multiple patterns after the completion of the teaching process. Next, we apply the GMR algorithm to generate a synthesized trajectory to minimize position errors in the three dimensional (3D) space. This approach has been tested by performing tasks on a KUKA iiwa and a Baxter robot, respectively.Finally, an optimized DMP is added to the teaching interface. A character recombination technology based on DMP segmentation that uses verbal command has also been developed and incorporated in a Baxter robot platform. To imitate the recorded motion signals produced by the demonstrator, the operator trains the Baxter robot by physically guiding it to complete the given task. This is repeated five times, and the generated training data set is utilized via the playback system. Subsequently, the DTW is employed to preprocess the experimental data. For modelling and overall movement control, DMP is chosen. The GMM is used to generate multiple patterns after implementing the teaching process. Next, we employ the GMR algorithm to reduce position errors in the 3D space after a synthesized trajectory has been generated. The Baxter robot, remotely controlled by the user datagram protocol (UDP) in a PC, records and reproduces every trajectory. Additionally, Dragon Natural Speaking software is adopted to transcribe the voice data. This proposed approach has been verified by enabling the Baxter robot to perform a writing task of drawing robot has been taught to write only one character.
published_date 2019-10-17T07:21:07Z
_version_ 1795927642850983936
score 11.037603

Similar Items