Imitation and Social Learning in Robots, Humans and Animals: A Bayesian model of imitation in infants and robots
Imitation and Social Learning in Robots, Humans and Animals: A Bayesian model of imitation in infants and robots
复制标题
机器人、人类和动物的模仿和社会学习：婴儿和机器人的贝叶斯模仿模型
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
A. Meltzoff
中科院分区：
文献类型：
--
作者：
Rajesh P. N. Rao;A. P. Shon;A. Meltzoff
通过模仿学习是获取新行为的一种强大而通用的方法。人类的一系列行为，从社交互动方式到工具使用，都是通过模仿学习从一代人传递到另一代人的。尽管模仿是通过达尔文主义手段进化而来的，但它达到了拉马克主义的目的：它是一种遗传后天特征的机制。与强化学习等基于试错的学习方法不同，模仿可以实现快速学习。通过演示快速获取行为的潜力使得模仿学习成为手动编程机器人越来越有吸引力的替代方案。在本章中，我们回顾了婴儿如何通过模仿进行学习的最新研究结果，并讨论了梅尔佐夫和摩尔的模仿能力的四个阶段进展：（i）身体牙牙学语，（ii）模仿身体动作，（iii）模仿物体上的动作，以及（iv）基于推断他人意图的模仿。我们在学习和推理的概率框架内将这四个阶段形式化。该框架承认内部模型在感觉运动控制中的作用，并借鉴了机器学习领域关于图形模型中贝叶斯推理的最新想法。我们强调了概率方法的两个优点：（1）开发在嘈杂和不确定的环境中行动的机器人基于模仿的学习新算法，以及（2）使用贝叶斯方法（例如先验概率的操纵）和机器人技术来加深我们对人类模仿学习的理解的潜力。
Learning through imitation is a powerful and versatile method for acquiring new behaviors. In humans, a wide range of behaviors, from styles of social interaction to tool use, are passed from one generation to another through imitative learning. Although imitation evolved through Darwinian means, it achieves Lamarckian ends: it is a mechanism for the inheritance of acquired characteristics. Unlike trial-and-error-based learning methods such as reinforcement learning, imitation allows rapid learning. The potential for rapid behavior acquisition through demonstration has made imitation learning an increasingly attractive alternative to manually programming robots. In this chapter, we review recent results on how infants learn through imitation and discuss Meltzoff and Moore's four-stage progression of imitative abilities: (i) body babbling, (ii) imitation of body movements, (iii) imitation of actions on objects, and (iv) imitation based on inferring intentions of others. We formalize these four stages within a probabilistic framework for learning and inference. The framework acknowledges the role of internal models in sensorimotor control and draws on recent ideas from the field of machine learning regarding Bayesian inference in graphical models. We highlight two advantages of the probabilistic approach: (1) the development of new algorithms for imitation-based learning in robots acting in noisy and uncertain environments, and (2) the potential for using Bayesian methodologies (such as manipulation of prior probabilities) and robotic technologies to deepen our understanding of imitative learning in humans.
登录
查看更多内容
影响因子：
4
作者：
MELTZOFF, AN
通讯作者：
MELTZOFF, AN
影响因子：
4
作者：
HANNA, E;MELTZOFF, AN
通讯作者：
MELTZOFF, AN
影响因子：
3.7
作者：
Brooks, R;Meltzoff, AN
通讯作者：
Meltzoff, AN
影响因子：
3.7
作者：
Meltzoff, Andrew N.
通讯作者：
Meltzoff, Andrew N.
DOI：
10.1098/rstb.2002.1261
发表时间：
2003-03-29
影响因子：
6.3
作者：
Meltzoff, AN;Decety, J
通讯作者：
Decety, J