Staged competence learning in developmental robotics
Staged competence learning in developmental robotics
复制标题
DOI：
10.1177/1059712307082085
复制
发表时间：
2007-01-01
影响因子：
1.6
通讯作者：
Chao, Fei
中科院分区：
文献类型：
--
作者：
Lee, Mark H.;Meng, Qinggang;Chao, Fei
发展心理学很早就认识到人类认知发展阶段的存在，尽管潜在的原因和过程仍然是一个开放的问题，并受到许多争论。本文从心理学中汲取灵感，并描述了一种在一般学习机制中利用自然约束的机器人发展增长方法。该方法，概括为升力约束，行为，饱和（LCAS），适用于所有级别的控制和行为，并可以在任何机器人配置。在婴儿早期的sensorymotor学习的基础上实现的描述和实验结果进行了介绍和讨论。
Developmental psychology has long recognized the presence of stages in human cognitive development, although the underlying causes and processes are still an open question and subject to much debate. This article draws inspiration from psychology and describes an approach towards developmental growth for robotics that utilizes natural constraints in a general learning mechanism. The method, summarized as Lift-Constraint, Act, Saturate (LCAS), is applicable to all levels of control and behavior, and can be implemented in any robotic configuration. An implementation based on sensorymotor learning in early infancy is described and the results from experiments are presented and discussed.