A Probabilistic Language Based on Sampling Functions
A Probabilistic Language Based on Sampling Functions
复制标题
DOI：
10.1145/1452044.1452048
复制
发表时间：
2008-12-01
影响因子：
1.3
通讯作者：
Thrun, Sebastian
中科院分区：
文献类型：
--
作者：
Park, Sungwoo;Pfenning, Frank;Thrun, Sebastian
随着概率计算在解决各种问题中起着越来越多的作用，研究人员设计了将概率分布视为原始数据类型的概率语言。但是，大多数概率语言仅专注于离散分布，并且具有有限的表达能力。本文介绍了一种概率语言，称为lambda（Circle），其表现力超出了离散的分布。 Lambda（Circle）的丰富表现力是由于其使用采样函数，即从单位间隔（0.0，1.0）映射到概率域，指定概率分布。因此，Lambda（Circle）使程序员能够正式表达关于模拟理论中开发的采样方法的原因。跟踪和机器人映射。
As probabilistic computations play an increasing role in solving various problems, researchers have designed probabilistic languages which treat probability distributions as primitive datatypes. Most probabilistic languages, however, focus only on discrete distributions and have limited expressive power. This article presents a probabilistic language, called lambda(circle), whose expressive power is beyond discrete distributions. Rich expressiveness of lambda(circle) is due to its use of sampling functions, that is, mappings from the unit interval ( 0.0, 1.0] to probability domains, in specifying probability distributions. As such, lambda(circle) enables programmers to formally express and reason about sampling methods developed in simulation theory. The use of lambda(circle) is demonstrated with three applications in robotics: robot localization, people tracking, and robotic mapping. All experiments have been carried out with real robots.