Software Open Access

Traffic3D: A Rich 3D Traffic Environment to Train Intelligent Agents

Garg, Deepeka; Bugajski, Callum; Mount, Sarah; Vogiatzis, George; Chli, Maria


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">traffic</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">simulator</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">unity3d</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">intelligent agent</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">ai</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">reinforcement learning</subfield>
  </datafield>
  <controlfield tag="005">20200801005922.0</controlfield>
  <controlfield tag="001">3968432</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Beautiful Canoe</subfield>
    <subfield code="a">Bugajski, Callum</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Beautiful Canoe</subfield>
    <subfield code="0">(orcid)0000-0001-7575-8420</subfield>
    <subfield code="a">Mount, Sarah</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aston University</subfield>
    <subfield code="0">(orcid)0000-0002-3226-0603</subfield>
    <subfield code="a">Vogiatzis, George</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Aston University</subfield>
    <subfield code="0">(orcid)0000-0002-2840-4475</subfield>
    <subfield code="a">Chli, Maria</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">222500630</subfield>
    <subfield code="z">md5:7d01be88d17d88b3c947f1b4f560bee2</subfield>
    <subfield code="u">https://zenodo.org/record/3968432/files/traffic3d-0.1.0.zip</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-09-25</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">software</subfield>
    <subfield code="o">oai:zenodo.org:3968432</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Aston University</subfield>
    <subfield code="a">Garg, Deepeka</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Traffic3D: A Rich 3D Traffic Environment to Train Intelligent Agents</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://opensource.org/licenses/MPL-2.0</subfield>
    <subfield code="a">Mozilla Public License 2.0</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;Traffic3D is a new traffic simulation paradigm, built to push forward research in human-like learning (for example, based on photo-realistic visual input). It provides a fast, cheap and scalable proxy for real-world traffic environments. This implies effective simulation of diverse and dynamic 3D-road traffic scenarios, closely mimicking real-world traffic characteristics such as faithful simulation of individual vehicle behaviour, their precise physics of movement and photo-realism. Traffic3D can facilitate research across multiple domains, including reinforcement learning, object detection and segmentation, unsupervised representation learning and visual question answering.&lt;/p&gt;

&lt;p&gt;Traffic3D is based on the&amp;nbsp;&lt;a href="https://unity3d.com/unity"&gt;Unity 3d games engine&lt;/a&gt;. The AI is written in&amp;nbsp;&lt;a href="https://www.python.org/"&gt;Python3&lt;/a&gt;&amp;nbsp;with&amp;nbsp;&lt;a href="https://pytorch.org/"&gt;PyTorch&lt;/a&gt;. It is available for Windows, Linux and OSX.&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.3460496</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3968432</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">software</subfield>
  </datafield>
</record>
113
6
views
downloads
All versions This version
Views 11357
Downloads 62
Data volume 951.4 MB445.0 MB
Unique views 9747
Unique downloads 62

Share

Cite as