Semantic Maps for Robotics
Semantic Maps for Robotics
复制标题
机器人语义图
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
D. Paulus
中科院分区：
文献类型：
--
作者：
D. Lang;D. Paulus
大多数移动的机器人系统使用所收集的信息的内部表示，这些信息不能被人类直观地理解，并且不足以从通常可用的源学习。将物体/地点分类和常识知识结合到语义地图中，以改善人机交互。其目的是将复杂的任务设置传递给机器人，以便它指导搜索解决方案本身。在本文中，我们提出了一个共同的形式化定义的语义机器人地图作为一个扩展的混合地图Buschka [1]。我们讨论了语义地图的设计，分类和挑战的不同标准。此外，我们提出了一个评估模板的基础上的定义，属性和挑战的语义映射的三个著名的语义映射方法。
Most mobile robotic systems use internal representations of the gathered information that is not intuitively understandable by humans and that is inadequate for learning from commonly available sources. The combination of object/place classification and common-sense knowledge to semantic maps found its way into indoor semantic mapping approaches in order to improve human-robot interaction. The aim is to pass complex task settings to the robot, so that it guides the search for the solution itself. In this paper, we present a common formal definition of semantic robotic maps as an extension of hybrid maps introduced by Buschka [1]. We discuss different criteria for design, classification and challenges of semantic maps. Furthermore, we present an evaluation template based on the definition, properties and challenges of semantic maps for three well known semantic mapping approaches.