Prior-assisted propagation of spatial information for object search
Prior-assisted propagation of spatial information for object search
复制标题
DOI：
10.1109/iros.2014.6942962
复制
发表时间：
2014-10
期刊：
影响因子：
--
通讯作者：
M. Lorbach;S. Höfer;O. Brock
中科院分区：
文献类型：
--
作者：
M. Lorbach;S. Höfer;O. Brock
我们提出了一种新的方法，在现实环境中的对象搜索。我们将对象搜索形式化为可能对象位置的概率推理问题。该方法有两个贡献。首先，我们确定五个先验，每个先验都捕获与搜索问题相关的物理世界固有的结构。其次，我们提出了一个正式的对象搜索问题，利用这些先验知识。我们的形式化的概率图形模型是能够结合到一个一致的概率分布的对象位置的各种来源的信息。形式化使我们能够通过跨位置传播知识来锐化分布。我们采用推理方法来选择搜索机器人在模拟环境中的行动，并表明它会导致更有效的对象搜索。
We propose a novel method for object search in realistic environments. We formalize object search as a probabilistic inference problem over possible object locations. The method makes two contributions. First, we identify five priors, each capturing structure inherent to the physical world that is relevant to the search problem. Second, we propose a formalization of the object search problem that leverages these priors. Our formalization in form of a probabilistic graphical model is capable of combining the various sources of information into a consistent probability distribution over object locations. The formalization allows us to sharpen the distribution by propagating the knowledge across locations. We employ the reasoning method to select actions of a searching robot in a simulated environment and show that it results in more efficient object search.