Releases: StanfordVL/iGibson
iGibson 2.0.0 release candidate 4
The version of iGibson to support Behavior Challenge. For more information please visit: http://svl.stanford.edu/behavior/challenge.html
iGibson 1.0.3
- In this version, we changed the package name from
gibson2
toigibson
. The pypi package is also updated. - Misc bug fixes
Release 1.0.1
Changes:
- Fix python2 compatibility issue.
- Ship examples and config files with the pip package.
- Fix shape caching issue.
Note: if you need to download source code, please download from gibson2-1.0.1.tar.gz, instead of the one GitHub provides, since the latter doesn't include submodules.
Release 1.0.0
Major update to iGibson to reach iGibson v1.0, for details please refer to our technical report.
- Release of iGibson dataset, which consists of 15 fully interactive scenes and 500+ object models.
- New features of the Simulator: Physically-based rendering; 1-beam and 16-beam lidar simulation; Domain
randomization support. - Code refactoring and cleanup.
Release 0.0.5
- Added support for Mac OSX
gibson2 0.0.4
iGibson, the Interactive Gibson Environment, is a simulation environment providing fast visual rendering and physics simulation (based on Bullet). It is packed with a dataset with hundreds of large 3D environments reconstructed from real homes and offices, and interactive objects that can be pushed and actuated. iGibson allows researchers to train and evaluate robotic agents that use RGB images and/or other visual sensors to solve indoor (interactive) navigation and manipulation tasks such as opening doors, picking and placing objects, or searching in cabinets.
Major changes since original GibsonEnv:
- Support agent interaction with the environment
- Support faster rendering, rendering to tensor support
- Removed dependencies of PyOpenGL, better support for headless rendering
- Support our latest version of assets.