CARLA is an open-source simulator designed for autonomous driving research, offering a robust platform for the development, training, and validation of autonomous systems. It provides open digital assets, including urban layouts, buildings, and vehicles, along with flexible sensor suite and environmental condition specifications. CARLA supports both Unreal Engine 5.5 and 4.26 versions, with distinct branches for each. The simulator is optimized for high-performance systems, requiring advanced hardware and specific operating systems (Ubuntu 22.04 or Windows 11). It features extensive documentation, a Python API, and integration with tools like ROS and AutoWare. CARLA’s ecosystem includes leaderboards, scenario runners, and reinforcement learning frameworks, making it a comprehensive tool for autonomous driving innovation.