Project information
- Category: Robotic Autonomous Investigation
- Client: INRIA
- Project date: January 2023 - June 2023
- Project URL: https://github.com/Sevla8/Multi-robot_navigation_and_control_for_acoustic_inspection_of_metal_plate_structures
Multi-robot Navigation and Control for Acoustic Inspection of Metal plate Structures
Context
This project was part of my master's thesis at INSA Lyon and GeorgiaTech. It is also part of the European project BugWright2, which aims to develop autonomous robotic inspection and maintenance on ship hulls. The purpose of this project was to propose and develop multi-robot algorithms for the inspection of metal plate structures, in order to detect and localize corrosion areas.
Actions
- State of the Art: I conducted a thorough review of the literature to gain a comprehensive understanding of the state of the art in multi-robot inspection.
- Algorithm Proposition and Specification: I proposed a three algorithmic solutions for multi-robot inspection. I also specified the algorithms in detail and studied their theoretical properties.
- Algorithm Implementation: I implemented the algorithms in Python and C++, using ROS libraries.
- Simulation: I simulated the algorithms in Gazebo and used RViz to help visualize the results.
- Experimentation: I set an experimentation environment to test the algorithms and evaluate their performance.
- Results Analysis: I analyzed the results of the simulations to evaluate the algorithms' performance and compare them to each other.
Results
I successfully implemented the three algorithms and simulated them in Gazebo.The results of the simulations showed that the algorithms were able to successfully inspect the metal plate structures, each algorithm having its own advantages and disadvantages.
I encountered some difficulties in the experimentation phase, especially when using a large number of robots. A more sophisticated collision avoidance system would have been necessary to avoid the robots getting stuck.