Přístupnostní navigace
E-application
Search Search Close
Publication detail
LIGOCKI, A. JELÍNEK, A. ŽALUD, L.
Original Title
Atlas Fusion - Modern Framework for Autonomous Agent Sensor Data Fusion
Type
conference paper
Language
English
Original Abstract
In this paper, we present our new 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. Index Terms—Open Source, Autonomous Agent, Self Driving Car, Sensor Fusion, Mapping, ROS
Keywords
Open Source, Autonomous Agent, Self Driving Car, Sensor Fusion, Mapping, ROS
Authors
LIGOCKI, A.; JELÍNEK, A.; ŽALUD, L.
Released
23. 5. 2022
Publisher
IEEE
Location
Krakov
ISBN
978-1-66-546726-1
Book
14th International Conference ELEKTRO, ELEKTRO 2022 - Proceedings
Pages from
1
Pages to
6
Pages count
URL
https://ieeexplore.ieee.org/document/9803587
Full text in the Digital Library
http://hdl.handle.net/11012/209123
BibTex
@inproceedings{BUT180792, author="Adam {Ligocki} and Aleš {Jelínek} and Luděk {Žalud}", title="Atlas Fusion - Modern Framework for Autonomous Agent Sensor Data Fusion", booktitle="14th International Conference ELEKTRO, ELEKTRO 2022 - Proceedings", year="2022", pages="6", publisher="IEEE", address="Krakov", doi="10.1109/ELECTRO53996.2022.9803587", isbn="978-1-66-546726-1", url="https://ieeexplore.ieee.org/document/9803587" }