CPFL/Autoware
Autoware
Autoware is a modular autonomous driving stack and open-source platform for advanced driver assistance systems. It functions as an integrated operating environment that manages the full pipeline from sensor data processing to vehicle actuation, utilizing the ROS 2 robotics framework for distributed communication and hardware abstraction.
The system provides a comprehensive software architecture to enable autonomous driving across various vehicle platforms. It coordinates perception, planning, and control systems to operate vehicles without human intervention.
The platform covers several core capability areas, including automated vehicle control for steering and acceleration, vehicle perception and planning to identify obstacles, and the deployment of self-driving architectures across different hardware setups.
Features
- Autonomous Driving Stacks - Provides a comprehensive production software suite for perception, planning, and control across various vehicle platforms.
- Sensor Fusion - Combines LiDAR, camera, and radar data using probabilistic filters to create a unified representation of the surroundings.
- Robotics Frameworks - Integrates the ROS 2 framework for distributed communication and hardware abstraction in robotics applications.
- Advanced Driver Assistance Systems - Provides an open-source platform for implementing both advanced driver assistance systems and full autonomy.
- Vehicle Sensor Processing - Processes data from cameras, radar, and lidar to identify obstacles and determine safe navigation paths.
- Vehicle Operating Environments - Functions as an integrated operating environment managing the complete pipeline from sensor processing to vehicle actuation.
- Vehicle Motion Control - Manages vehicle steering and acceleration based on inputs from autonomous planning systems.
- Publish-Subscribe Messaging - Utilizes a distributed publish-subscribe model via ROS 2 to exchange sensor data and control commands.
- Hardware Abstraction Layers - Provides a standardized interface that decouples high-level driving logic from specific vehicle actuators and sensors.
- Perception Pipelines - Processes raw sensor data through discrete stages of detection and tracking to build a consistent world model.
- Behavior Trees - Implements a hierarchical behavior tree to determine driving maneuvers based on environmental conditions.
- Kinematic Path Planning - Calculates optimal trajectories by accounting for vehicle-specific kinematic constraints using Frenet frames.
- Deployment Frameworks - Provides the means to install and configure autonomous driving architectures across diverse vehicle platforms.
- Detection Architectures - Real-time multiclass detection framework utilizing 3D LiDAR data.
