usdot-fhwa-stol/carma-platform

CARMA Platform is built on robot operating system (ROS) and utilizes open source software (OSS) that enables Cooperative Driving Automation (CDA) features to allow Automated Driving Systems to interact and cooperate with infrastructure and other vehicles through communication. Doxygen Source Code Documentation :

What it solves

CARMA provides a reusable and extensible software platform for controlling connected, automated vehicles (AVs). It addresses the complexity of managing automated vehicle motion by integrating navigation (localization), guidance (trajectory planning), and control (actuation) into a single framework, enabling researchers and engineers to develop and test cooperative driving automation without building the entire stack from scratch.

How it works

Written in C++ and running within a Robot Operating System (ROS) environment on Ubuntu, the platform manages the vehicle motion cycle: navigation determines the vehicle's position relative to the earth and path, guidance algorithms plan the trajectory to the destination, and control functions actuate the vehicle's physical devices. It uses a plugin-based architecture, allowing third parties to implement their own vehicle guidance algorithms. The current generation (CARMA3) leverages Autoware to provide SAE level 2 and 3 automation capabilities.

Who it’s for

It is designed for engineers and researchers focusing on cooperative driving automation, intelligent transportation systems, and the development of automated driving technology safety and security.

Highlights

  • SAE Level 2/3 Autonomy: Supports speed and steering control for light and heavy vehicles.
  • Cooperative Capabilities: Enables communication between vehicles, road users (pedestrians, bicyclists), and infrastructure via V2X or cellular means.
  • Extensible Architecture: Provides a generic API for third-party plugins to implement custom trajectory planning.
  • ROS Integration: Operates as a hybrid of ROS 1 Noetic and ROS 2 Humble components.
  • Multi-Vehicle Support: Designed to work across a variety of properly equipped vehicles, including heavy trucks.

Related

  • Project
    ucla-mobility/OpenCDA

    An open-source co-simulation framework for Cooperative Driving Automation (CDA) that integrates CARLA and SUMO to research multi-vehicle cooperation and V2X communication.

  • Project
    carla-simulator/carla

    An open-source simulator for autonomous driving research used to develop, train, and validate autonomous driving systems in simulated urban environments.

  • Project
    Thinklab-SJTU/Bench2Drive

    A closed-loop dataset and benchmark for autonomous driving systems using the CARLA simulator to evaluate driving scores, success rates, and specific driving abilities.

  • Project
    commaai/openpilot

    An open-source operating system for robotics that upgrades driver assistance systems in over 300 supported cars.

  • Project
    louiszengCN/CarlaAir

    A unified simulation infrastructure that integrates CARLA and AirSim into a single process to enable high-fidelity, synchronized air-ground embodied intelligence research.