iGibson

iGibson

iGibson is an interactive simulation environment from Stanford Vision and Learning Lab built for training embodied AI agents in realistic indoor scenes. It features fully interactive objects, physics simulation, and a rich sensor suite, making it ideal for household robot learning tasks.

Key Features

• 15 fully interactive household scenes with 500+ object categories
• Physics-based interaction: grasp, push, place, pour, and toggle objects
• High-fidelity rendering with physically based materials and lighting
• Sensor suite: RGB, depth, LiDAR, instance/semantic segmentation
• OpenAI gym-compatible API with predefined task benchmarks

Quick Start

pip install igibson
python -m igibson.utils.assets_utils --download_assets

from igibson.envs.igibson_env import iGibsonEnv

env = iGibsonEnv(
    config_file="fetch_reaching.yaml",
    mode="gui_interactive",
)
obs = env.reset()
for _ in range(100):
    action = env.action_space.sample()
    obs, rew, done, info = env.step(action)

npx ai-supply add igibson-interactive-simulation

Curated mirror of the open-source iGibson (MIT). Get it from the source.