Meaningful Maps With Object-Oriented Semantic Mapping
This work addresses the need for intelligent robots to understand both geometry and semantics in their environment, which is incremental as it integrates existing techniques like SLAM and deep learning.
The paper tackles the problem of building environmental maps that combine semantically meaningful object-level entities with geometric representations, achieving simultaneous construction of geometric point cloud models for unseen object instances and integrating them into a map as central entities.
For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic mapping. In this paper we address the problem of building environmental maps that include both semantically meaningful, object-level entities and point- or mesh-based geometrical representations. We simultaneously build geometric point cloud models of previously unseen instances of known object classes and create a map that contains these object models as central entities. Our system leverages sparse, feature-based RGB-D SLAM, image-based deep-learning object detection and 3D unsupervised segmentation.