Probabilistic 3D multilabel real-time mapping for multi-object manipulation

Probabilistic 3D map has been applied to object segmentation with multiple camera viewpoints, however, conventional methods lack of real-time efficiency and functionality of multilabel object mapping. In this paper, we propose a method to generate three-dimensional map with multilabel occupancy in real-time. Extending our previous work [1] in which only target label occupancy is mapped, we achieve multilabel object segmentation in a single looking around action. We evaluate our method by testing segmentation accuracy with 39 different objects, and applying it to a manipulation task of multiple objects in the experiments. Our mapping-based method outperforms the conventional projection-based method by 40-96% relative (12.6 mean IU
_3d
), and robot successfuly recognizes (86.9%) and manipulates multiple objects (60.7%) in an environment with heavy occlusions.