Learning to Explore and Build Maps
Learning to Explore and Build Maps
复制标题
学习探索和构建地图
DOI：
--
复制
发表时间：
1994
期刊：
影响因子：
--
通讯作者：
B. Kuipers
中科院分区：
文献类型：
--
作者：
David Pierce;B. Kuipers
使用本文中所展示的方法，具有未知感觉运动系统的机器人可以学习足以探索连续环境的特征和行为集，并将其抽象为有限状态自动机。这个自动机的结构可以从经验中学习，并构成环境的认知地图。一个生成和测试的方法是用来定义一个层次的功能定义的原始意义上的向量最终在一组连续可微的局部状态变量。基于这些局部状态变量的控制律被定义为鲁棒地遵循实现可重复状态转换的路径。这些状态转换是有限状态自动机的基础，是机器人连续世界的离散抽象。各种现有的方法可以学习由结果状态和转换定义的自动机的结构。我们实现的系统的性能的一个简单的例子。
Using the methods demonstrated in this paper, a robot with an unknown sensorimotor system can learn sets of features and behaviors adequate to explore a continuous environment and abstract it to a finite-state automaton. The structure of this automaton can then be learned from experience, and constitutes a cognitive map of the environment. A generate-and-test method is used to define a hierarchy of features defined on the raw sense vector culminating in a set of continuously differentiable local state variables. Control laws based on these local state variables are defined for robustly following paths that implement repeatable state transitions. These state transitions are the basis for a finite-state automaton, a discrete abstraction of the robot's continuous world. A variety of existing methods can learn the structure of the automaton defined by the resulting states and transitions. A simple example of the performance of our implemented system is presented.