Software Open Access

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

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


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>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.</p>\n\n<p>Traffic3D is based on the&nbsp;<a href=\"https://unity3d.com/unity\">Unity 3d games engine</a>. The AI is written in&nbsp;<a href=\"https://www.python.org/\">Python3</a>&nbsp;with&nbsp;<a href=\"https://pytorch.org/\">PyTorch</a>. It is available for Windows, Linux and OSX.</p>", 
  "license": "https://opensource.org/licenses/MPL-2.0", 
  "creator": [
    {
      "affiliation": "Aston University", 
      "@type": "Person", 
      "name": "Garg, Deepeka"
    }, 
    {
      "affiliation": "Beautiful Canoe", 
      "@type": "Person", 
      "name": "Bugajski, Callum"
    }, 
    {
      "affiliation": "Beautiful Canoe", 
      "@id": "https://orcid.org/0000-0001-7575-8420", 
      "@type": "Person", 
      "name": "Mount, Sarah"
    }, 
    {
      "affiliation": "Aston University", 
      "@id": "https://orcid.org/0000-0002-3226-0603", 
      "@type": "Person", 
      "name": "Vogiatzis, George"
    }, 
    {
      "affiliation": "Aston University", 
      "@id": "https://orcid.org/0000-0002-2840-4475", 
      "@type": "Person", 
      "name": "Chli, Maria"
    }
  ], 
  "url": "https://zenodo.org/record/3968432", 
  "datePublished": "2019-09-25", 
  "version": "0.1.0", 
  "keywords": [
    "traffic", 
    "simulator", 
    "unity3d", 
    "intelligent agent", 
    "ai", 
    "reinforcement learning"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3968432", 
  "@id": "https://doi.org/10.5281/zenodo.3968432", 
  "@type": "SoftwareSourceCode", 
  "name": "Traffic3D: A Rich 3D Traffic Environment to Train Intelligent Agents"
}
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