Investigation of SIFT and ORB descriptors for Indoor Maps Fusion for the Multi-agent mobile robots

There are many applications for creating an indoor map by a single robot already. When using a single robot in a large working space like a factory, the performance and robustness are needed to be increased. Multi-Agent Robot System (MAR) is introduced to meet this requirement. MAR could increase productivity and flexibility while works in a dynamic environment because it is modular and can work simultaneously. When MAR combines with Simultaneous Localization and Mapping (SLAM) technology, it can explore and discover the indoor environment cooperatively and simultaneously. Each robot creates its map with different initial poses and path planning. The main issue of a Multi-Robot SLAM (MRSLAM) is how to combine maps from different robots correctly. In this research, we will focus on algorithms of map merging. SIFT and ORB descriptors are selected along with some image processing techniques, and a proposed approach including the algorithms is verified by general benchmark map data. The results will be shown and discussed. Then, the proposed approach will be deployed into a real robot platform based on Robot Operating System (ROS). Experiments will be conducted to prove the feasibility and the limitation of the proposed approach in the real-world scenario.