Description
This was the longest and the most complex project I have done during my studies. It is a multi-mobile robot system designed to work in a warehouse-like environment. The system consists of multiple mobile robots that can communicate with each other and with a central server. The main goal of the system is to enable the robots to work together to perform tasks such as transporting goods, navigating through the environment, and avoiding obstacles and collisions.
The system is built using the Robot Operating System 2 (ROS2), which is a popular framework for developing robotic applications. The system is multi layered and consists of several components, including:
- high-level supervisory control,
- mid-level stage traversal control,
- low-level robot motion control,
In order to manage collision avoidance and deadlock avoidance, the system utilizes a centralized approach. The central server is responsible for monitoring the state of the robots and the environment, and it makes decisions about how the robots should move and interact with each other. Three algorithms were implemented to manage the robots path segmentation (for detailed information see the thesis):
- equal length division,
- optimal length division,
- grid based division.
Robots used in this project are Turtlebot2s, which are equipped with LIDAR sensors and RGB-D cameras.
Source code of this project is available on my Gitlab repository. The thesis itself is available here and is written in English.
This project was made as my master’s thesis at Wroclaw University of Science and Technology.