CARLA simulator screen image. Credit: Toyota Motor Corporation.

The Toyota Research Institute (TRI) has expanded its support of open source platforms to the Computer Vision Centre (CVC) to fast-track the development of an open-source simulator for automated driving known as Car Learning to Act (CARLA).

In this regard, TRI has donated $100,000 to CVC.

CVC advanced driver assistance systems (ADAS) group head Dr Antonio López said: “CARLA is born to democratise research on automated driving, supporting training and testing of AI drivers beyond real-world limitations.

“The joint work of CARLA engineers, artists and scientists are making this possible. Obviously, we need to keep working to allow CARLA reach its full maturity, and this is why the sponsorship from Toyota is highly valuable.”

“Technological advances and growth are made possible through collaboration and community support.”

Directed by the CVC at the Universitat Autònoma de Barcelona (UAB) in Spain, CARLA is a non-profit, open-source simulator, which is hosted on Github.

GitHub is a platform which has been created to bring together a global community of developers to discover, share, and build better software.

CARLA has been designed to ensure the stability of automated vehicles in various situations that are not always testable in the real world.

TRI driving simulation director Vangelis Kokkevis said: “Technological advances and growth are made possible through collaboration and community support.

“Fostering the development of a common open simulation platform will allow TRI and its academic and industrial partners to better exchange code, information and data.”

Over the two consecutive years, TRI is said to have provided significant donations to the Open Source Robotics Foundation (OSRF), which offers the global robotics community access to open source robotics software and development tools.

The donation provided by TRI will be used by CARLA team to expand its engineering team and the simulator’s capabilities.