Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Mimicking of human hand motion on robot arm using point cloud and Machine learning techniques
University West, Department of Engineering Science, Division of Industrial Engineering and Management, Electrical- and Mechanical Engineering.
2018 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Collaborative robots may be required to do complex assembly operations during production and programming the Robot to perform such operations can be a challenging task. If the motions of the human palm could be mimicked on the Robot, it would mitigate the com-plexities involved in teaching such skills to the Robot. This mimicking action could also be used in other applications like robot based painting where it is necessary to capture motion generated by a skilled human hand and reproduce it on a robot.

To achieve this there may be many methods. A point cloud camera could be used to capture and store point cloud data of an object at different positions and orientations inside the Robot work volume. Corresponding Tool centre point positions and orientations read from the Robot controller serve as labelled data necessary for machine learning.

The task involves generation of Robot programs to synchronize point cloud capture and robot pose capture resulting in generation of data necessary for machine learning. The point cloud data is generated using Kinect point cloud camera by establishing the communication between the robot and the Kinect V2.

The objective in this paper is concluded by gathering the point cloud data for limited positions using Kinect V2 which is necessary for machine learning. Since machine learning techniques can be applied for further process huge amount of data is required hence this data is generated.

Place, publisher, year, edition, pages
2018. , p. 24
Keywords [en]
3D laser scanner, Point cloud, visualization
National Category
Robotics
Identifiers
URN: urn:nbn:se:hv:diva-13087Local ID: EXM810OAI: oai:DiVA.org:hv-13087DiVA, id: diva2:1260150
Subject / course
Robotics
Educational program
Robotteknik
Supervisors
Examiners
Available from: 2018-11-14 Created: 2018-11-01 Last updated: 2018-11-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Division of Industrial Engineering and Management, Electrical- and Mechanical Engineering
Robotics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 57 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf