当前位置: X-MOL 学术arXiv.cs.RO › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Probabilistic 3D Multilabel Real-time Mapping for Multi-object Manipulation
arXiv - CS - Robotics Pub Date : 2020-01-16 , DOI: arxiv-2001.05752
Kentaro Wada, Kei Okada, Masayuki Inaba

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

中文翻译:

用于多对象操作的概率 3D 多标签实时映射

概率 3D 地图已应用于具有多个摄像机视点的对象分割,但是,传统方法缺乏多标签对象映射的实时效率和功能。在本文中,我们提出了一种实时生成具有多标签占用的三维地图的方法。扩展我们之前仅映射目标标签占用的工作,我们在单个环视动作中实现了多标签对象分割。我们通过测试 39 个不同对象的分割精度来评估我们的方法,并将其应用于实验中多个对象的操作任务。我们基于映射的方法优于传统的基于投影的方法 40 - 96\% 相对(12.6 均值 $IU_{3d}$),并且机器人成功识别 (86.9\%) 并操纵多个对象 (60.
更新日期:2020-01-17
down
wechat
bug