Scene recognition for confined spaces in mobile robotics: current state and tendencies

Abstract

The article discusses the problem of scene recognition for mobile robotics. Subtasks that have to be solved to implement a high-level understanding of the environment are considered. The basis here is an understanding of the geometry and semantics of the scene, which can be decomposed into subtasks of robot localization, mapping and semantic analysis. Simultaneous localization and mapping (SLAM) techniques have already been successfully applied and, although they have some as yet unresolved problems for dynamic environments, do not present a problem for this issue. The focus of the work is on the task of semantic analysis of the scene, which assumes three-dimensional segmentation. The field of 3D segmentation, like the field of image segmentation, has been decomposed into semantic and object segmentation, contrary to the needs of many potential applications. However, at present, panoptic segmentation is beginning to develop, combining the two previous ones and most fully describing the scene. The paper reviews the methods of 3D panoptic segmentation, identifies promising approaches. The actual problems of the scene recognition problem are also discussed. There is a clear trend towards the development of complex incremental methods of metric-semantic SLAM, which combine segmentation with SLAM methods, and the use of scene graphs, which allow describing the geometry, semantics of scene elements and the relationship between them. Scene graphs are especially promising for the field of mobile robotics, since they provide a transition from low-level representations of objects and spaces (for example, segmented point clouds) to describing a scene at a high level of abstraction, close to a human one (a list of objects in a scene, their properties and location relative to each other).