Indirect Object Search based on Qualitative Spatial Relations
Indirect Object Search based on Qualitative Spatial Relations
复制标题
基于定性空间关系的间接对象搜索
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Nick Hawes
中科院分区：
文献类型：
--
作者：
Lars Kunze;Nick Hawes
在人类环境中完成目标搜索任务需要自主移动的机器人对潜在的目标位置进行推理，并相应地规划下一个最佳视图。通过使用关于环境的3D结构的信息、关于地标对象及其与所寻找对象的空间关系的知识，可以通过将机器人引导到最可能的对象位置来改进搜索。在本文中，我们已经设计，实施和评估的基础上的定性空间关系（QSR），如左和接近的对象搜索的方法。基于一个地标和所寻找的对象之间的QSR，我们生成了一个高斯混合模型（GMM），用于表示使用三元点演算的潜在对象位置的度量姿态。在对象搜索中采用GMM来规划下一个最佳视图。初步结果表明，基于QSR的搜索方法比不考虑它们的方法更快，更可靠。
Accomplishing object search tasks in human environments requires autonomous mobile robots to reason about potential object locations and to plan for the next best view accordingly. By using information about the 3D structure of the environment, knowledge about landmark objects and their spatial relationship to the sought object, the search can be improved by directing the robot towards the most likely object locations. In this paper we have designed, implemented and evaluated an approach for searching for objects on the basis of Qualitative Spatial Relations (QSRs) such as left-of and close-to. On the basis of QSRs between a landmark and the sought object we generate a Gaussian Mixture Model (GMM) for representing metric poses of potential object locations using a ternary point calculus. The GMM is employed within object search for planning the next best view. Preliminary results show that search methods based on QSRs are faster and more reliably than methods not considering them.
影响因子：
3.5
作者：
Hornung, Armin;Wurm, Kai M.;Burgard, Wolfram
通讯作者：
Burgard, Wolfram