xavierpuigf/virtualhome

• highreadme#1

  Reposition README opening to emphasize synthetic data generation

  Why:

  CURRENT

  VirtualHome is an interactive platform to simulate complex household activities via programs. Key aspect of VirtualHome is that it allows complex interactions with the environment, such as picking up objects, switching on/off appliances, opening appliances, etc. Our simulator can easily be called with a Python API: write the activity as a simple sequence of instructions which then get rendered in VirtualHome. You can choose between different agents and environments, as well as modify environments on the fly. You can also stream different ground-truth such as time-stamped actions, instance/semantic segmentation, and optical flow and depth. The platform allows to simulate multi-agent activities and can serve as an environment to train agents for embodied AI tasks.

  COPY-PASTE FIX

  Copy

  **VirtualHome** is an interactive platform to simulate complex household activities via programs, serving as a robust environment for embodied AI research and **synthetic data generation**. It provides rich ground-truth data, including instance/semantic segmentation, optical flow, and depth, alongside its core capability for complex interactions with the environment (picking up objects, switching appliances). Our simulator, easily called with a Python API, allows writing activities as simple instruction sequences, rendered in VirtualHome, and supports multi-agent activities and dynamic environment modification.

  OpenDoneDismiss
• mediumtopics#2

  Add specific topics for synthetic data and embodied AI

  Why:

  CURRENT

  computer-vision, deep-learning, graph, multi-agent, reinforcement-learning, simulator, unity

  COPY-PASTE FIX

  Copy

  computer-vision, deep-learning, graph, multi-agent, reinforcement-learning, simulator, unity, synthetic-data, data-generation, segmentation, depth-estimation, embodied-ai

  OpenDoneDismiss
• lowreadme#3

  Add a 'Key Capabilities' section to the README

  Why:

  COPY-PASTE FIX

  Copy

  ## Key Capabilities
  
  *   **Programmatic Control:** Define complex household activities via a simple Python API.
  *   **Multi-Agent Simulation:** Support for multiple AI agents interacting within the environment.
  *   **Rich Ground-Truth Data:** Stream instance/semantic segmentation, optical flow, and depth for synthetic data generation.
  *   **Interactive Environments:** Agents can pick up objects, switch appliances, open/close containers, and modify environments dynamically.
  *   **Procedural Generation:** Create infinite unique environments for diverse training scenarios.
  *   **Embodied AI Training:** An ideal environment for training agents in complex embodied AI tasks.

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What simulation environments support training multiple AI agents in interactive household settings?

  you: #3
  AI recommended (in order):

  1. AI2-THOR
  2. Habitat
  3. VirtualHome ← you
  4. iGibson
  5. MINERVA
  Show full AI answer
• CATEGORY QUERY

  Looking for a simulator to generate synthetic data for embodied AI, including segmentation and depth.

  you: not recommended
  AI recommended (in order):

  1. NVIDIA Isaac Sim
  2. Unity 3D
  3. Perception Package
  4. Unreal Engine
  5. AirSim
  6. CARLA
  7. Habitat-Sim
  8. Gazebo

  AI recommended 8 alternatives but never named xavierpuigf/virtualhome. This is the gap to close.

  Show full AI answer

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of xavierpuigf/virtualhome?

  pass
  ✓AI named xavierpuigf/virtualhome explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts xavierpuigf/virtualhome in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named xavierpuigf/virtualhome explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo xavierpuigf/virtualhome solve, and who is the primary audience?

  pass
  ✓AI named xavierpuigf/virtualhome explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?