TorchDriveSim Release
Wed Feb 07 202461 viewsInverted AI is pleased to announce the initial release of TorchDriveSim [github].
TorchDriveSim is the first open source lightweight 2D driving simulator built entirely in PyTorch. It is primarily intended as a training environment for developing autonomous driving algorithms. Its main features are:
- Fully differentiable execution producing a single computation graph, including state transition (kinematic models) and observation (differentiable rendering) models.
- First class support for batch processing, down to the lowest level.
- Support for heterogeneous agent types (vehicles, pedestrians, cyclists, etc.), each with its own kinematic model.
- Extensible and customizable implementation of kinematic models (unconstrained, unicycle, bicycle, etc.), rendering modes, and rendering backends.
- Support for extensible traffic control types, including traffic lights.
- Differentiable implementations of various infraction metrics (collisions, off-road, wrong way).
- Modular collection of wrappers modifying the simulator's behavior.
- Ability to ingest any map in Lanelet2 format out of the box.
- Integration with IAI API for initializing agent states and providing realistic behaviors.
Sign up here for an API key today to start using TorchDriveSim.