Atlas Fusion -- Modern Framework for Autonomous Agent Sensor Data Fusion
This provides a practical tool for researchers and developers in robotics and autonomous systems to integrate and extend sensor fusion pipelines, though it is incremental as it builds on existing ROS-based architectures.
The authors introduced Atlas Fusion, a universal and scalable software framework for fusing sensor data like RGB/thermal cameras, LiDAR, IMU, and GNSS to build a robust 3D environment model for autonomous agents such as self-driving cars, with full ROS compatibility and open-source availability under the MIT license.
In this paper, we present our software sensor fusion framework for self-driving cars and other autonomous robots. We have designed our framework as a universal and scalable platform for building up a robust 3D model of the agent's surrounding environment by fusing a wide range of various sensors into the data model that we can use as a basement for the decision making and planning algorithms. Our software currently covers the data fusion of the RGB and thermal cameras, 3D LiDARs, 3D IMU, and a GNSS positioning. The framework covers a complete pipeline from data loading, filtering, preprocessing, environment model construction, visualization, and data storage. The architecture allows the community to modify the existing setup or to extend our solution with new ideas. The entire software is fully compatible with ROS (Robotic Operation System), which allows the framework to cooperate with other ROS-based software. The source codes are fully available as an open-source under the MIT license. See https://github.com/Robotics-BUT/Atlas-Fusion.