Software Open Access

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

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

Citation Style Language JSON Export

  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3968432", 
  "language": "eng", 
  "title": "Traffic3D: A Rich 3D Traffic Environment to Train Intelligent Agents", 
  "issued": {
    "date-parts": [
  "abstract": "<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=\"\">Unity 3d games engine</a>. The AI is written in&nbsp;<a href=\"\">Python3</a>&nbsp;with&nbsp;<a href=\"\">PyTorch</a>. It is available for Windows, Linux and OSX.</p>", 
  "author": [
      "family": "Garg, Deepeka"
      "family": "Bugajski, Callum"
      "family": "Mount, Sarah"
      "family": "Vogiatzis, George"
      "family": "Chli, Maria"
  "version": "0.1.0", 
  "type": "article", 
  "id": "3968432"
All versions This version
Views 11357
Downloads 62
Data volume 951.4 MB445.0 MB
Unique views 9747
Unique downloads 62


Cite as