English

Probabilistic 3D Multilabel Real-time Mapping for Multi-object Manipulation

Robotics 2020-01-17 v1 Computer Vision and Pattern Recognition

Abstract

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 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 IU3dIU_{3d}), and robot successfully recognizes (86.9\%) and manipulates multiple objects (60.7\%) in an environment with heavy occlusions.

Keywords

Cite

@article{arxiv.2001.05752,
  title  = {Probabilistic 3D Multilabel Real-time Mapping for Multi-object Manipulation},
  author = {Kentaro Wada and Kei Okada and Masayuki Inaba},
  journal= {arXiv preprint arXiv:2001.05752},
  year   = {2020}
}

Comments

8 pages, 8 figures, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017

R2 v1 2026-06-23T13:12:50.693Z