New version of CARLA released
After more than eight months waiting, the 0.9.12 release of CARLA is finally availabe in, as usual, open-source code and protocols.
In this new version of the open-source simulator for autonomous driving research, in whose development the CVC, through the Advanced Driver Assistance Systems group lead by the ICREA researcher Antonio López is involved, there are important novelties comparing with the previous version, CARLA 0.9.11, such as:
Large Maps. Users can now perform simulations on vast maps that can span upwards of 10,000km². Also, with the updated Traffic Manager, CARLA users can now populate the map with hundreds of cars that can drive at high speeds
Physics improvements including full physics determinism in synchronous mode, improved wheel physics, custom vehicle wheel settings, and vehicle control telemetry.
New default town called HD Town 10
New generation of pedestrians and vehicles with improved meshes and details. There’s a lot of variety in the new pedestrians, who have a range of clothing, body shapes, and skin colors.
Addition of the Optical Flow Camera, allowing to capture the motion of pixels between frames.
OpenStreetMaps functionality has been extended to allow users to automatically generate traffic lights at junctions and control how and where those traffic lights are generated.
Ray/RLlib integration to enable to use CARLA as an environment in Ray for reinforcement learning experiments. This environment could be used for training and inference purposes.
Beta integration with Chrono, a highly realistic multi-physics simulation engine. This integration will allow users to delegate the simulation of advanced physics to Chrono, providing a more accurate simulation experience.
The CarSim integration is no longer in beta stages and is fully supported after making some fixes and updates to the functionality.
In this link you can find more detailed information about CARLA 0.9.12