Nachricht

On Wednesday, February 1, Kanak Mazumder will present intermediate results of his master's thesis with the title

Surfel based Semantic Maps for Exploration in Dynamic Environments

Abstract:

For the use of autonomous mobile robots, 3D mapping and localization is an integral part that is becoming more and more important. However, a bare point cloud-based map is insufficient to make an informed decision and plan for a high-level task such as search and rescue. A 3D semantic map, i.e. each point in the map is labeled with the corresponding class, improves planning and decision-making processes. This work focuses on creating a suitable semantic map representation and improving the accuracy of semantic labeling by reducing segmentation and projection errors. The resulting system should provide a 3D semantic map, which can reduce the computational complexity of traversability analysis, viewpoint selection and ensure better exploration behavior.