Using the Web to Interactively Learn to Find Objects
Using the Web to Interactively Learn to Find Objects
复制标题
DOI：
10.1609/aaai.v26i1.8387
复制
发表时间：
2012-07
期刊：
影响因子：
--
通讯作者：
M. Samadi;T. Kollar;M. Veloso
中科院分区：
文献类型：
--
作者：
M. Samadi;T. Kollar;M. Veloso
为了让机器人能够智能地与人类一起执行任务，它们必须能够获得关于它们所处环境的广泛背景知识。与其他倾向于手动定义机器人知识的方法不同，我们的方法使机器人能够主动查询万维网（WWW）以学习有关物理环境的背景知识。我们展示了我们的方法能够搜索Web来推断在某个位置（例如厨房）可以找到某个对象（例如“咖啡”）的概率。“我们的方法，称为ObjectEval，能够使用这种概率动态实例化实用函数，使机器人能够在室内环境中找到任意物体。我们的实验结果表明，ObjectEval的交互式版本访问的位置比离线训练的版本少28%，比不使用背景知识的基线方法访问的位置少71%。
In order for robots to intelligently perform tasks with humans, they must be able to access a broad set of background knowledge about the environments in which they operate. Unlike other approaches, which tend to manually define the knowledge of the robot, our approach enables robots to actively query the World Wide Web (WWW) to learn background knowledge about the physical environment. We show that our approach is able to search the Web to infer the probability that an object, such as a "coffee,'' can be found in a location, such as a "kitchen.'' Our approach, called ObjectEval, is able to dynamically instantiate a utility function using this probability, enabling robots to find arbitrary objects in indoor environments. Our experimental results show that the interactive version of ObjectEval visits 28% fewer locations than the version trained offline and 71% fewer locations than a baseline approach which uses no background knowledge.