November 1, 2019 Conference paper Open Access

Koutras, Leonidas; Doulgeri, Zoe

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Dynamic Movement Primitives</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Control in Orientation Trajectories</subfield>
  </datafield>
  <controlfield tag="005">20200204151257.0</controlfield>
  <controlfield tag="001">3537791</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">30 October - 1 November 2019</subfield>
    <subfield code="g">CoRL</subfield>
    <subfield code="a">Conference on Robot Learning</subfield>
    <subfield code="c">Osaka, Japan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="0">(orcid)0000-0003-2188-9358</subfield>
    <subfield code="a">Doulgeri, Zoe</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3475183</subfield>
    <subfield code="z">md5:b54cef107a384f9915bc6e72057f22a1</subfield>
    <subfield code="u">https://zenodo.org/record/3537791/files/A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">https://www.robot-learning.org/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-11-01</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-collaborate_project</subfield>
    <subfield code="o">oai:zenodo.org:3537791</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Aristotle University of Thessaloniki</subfield>
    <subfield code="0">(orcid)0000-0002-3521-6958</subfield>
    <subfield code="a">Koutras, Leonidas</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">A correct formulation for the Orientation Dynamic Movement Primitives for robot control in the Cartesian space</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-collaborate_project</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">820767</subfield>
    <subfield code="a">Co-production CeLL performing Human-Robot Collaborative AssEmbly</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Dynamic movement primitives (DMP) are an efficient way for learning&lt;br&gt;
and reproducing complex robot behaviors. A singularity free DMP formulation&lt;br&gt;
for orientation in the Cartesian space is proposed by Ude et al. in 2014 and has been&lt;br&gt;
largely adopted by the research community. In this work, we demonstrate the&lt;br&gt;
undesired oscillatory behavior that may arise when controlling the robot&amp;rsquo;s orien-&lt;br&gt;
tation with this formulation, producing a motion pattern highly deviant from the&lt;br&gt;
desired and highlight its source. A correct formulation is then proposed that alle-&lt;br&gt;
viates such problems while guaranteeing generation of orientation parameters that&lt;br&gt;
lie in SO(3). We further show that all aspects and advantages of DMP including&lt;br&gt;
ease of learning, temporal and spatial scaling and the ability to include coupling&lt;br&gt;
terms are maintained in the proposed formulation. Simulations and experiments&lt;br&gt;
with robot control in SO(3) are performed to demonstrate the performance of the&lt;br&gt;
proposed formulation and compare it with the previously adopted one.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3537790</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3537791</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>