Schaal S
Department of Computer Science and Neuroscience, HNB-103, University of Southern California, Los Angeles, CA 90089-2520, USA.
Trends Cogn Sci. 1999 Jun;3(6):233-242. doi: 10.1016/s1364-6613(99)01327-3.
This review investigates two recent developments in artificial intelligence and neural computation: learning from imitation and the development of humanoid robots. It is postulated that the study of imitation learning offers a promising route to gain new insights into mechanisms of perceptual motor control that could ultimately lead to the creation of autonomous humanoid robots. Imitation learning focuses on three important issues: efficient motor learning, the connection between action and perception, and modular motor control in the form of movement primitives. It is reviewed here how research on representations of, and functional connections between, action and perception have contributed to our understanding of motor acts of other beings. The recent discovery that some areas in the primate brain are active during both movement perception and execution has provided a hypothetical neural basis of imitation. Computational approaches to imitation learning are also described, initially from the perspective of traditional AI and robotics, but also from the perspective of neural network models and statistical-learning research. Parallels and differences between biological and computational approaches to imitation are highlighted and an overview of current projects that actually employ imitation learning for humanoid robots is given.
从模仿中学习以及类人机器人的发展。据推测，对模仿学习的研究为深入了解感知运动控制机制提供了一条有前景的途径，最终可能导致自主类人机器人的创造。模仿学习关注三个重要问题：高效的运动学习、动作与感知之间的联系以及以运动原语形式存在的模块化运动控制。本文回顾了关于动作与感知的表征及其功能联系的研究如何有助于我们理解其他生物的运动行为。最近发现灵长类动物大脑中的一些区域在运动感知和执行过程中均处于活跃状态，这为模仿提供了一个假设的神经基础。还描述了模仿学习的计算方法，最初是从传统人工智能和机器人技术的角度，也从神经网络模型和统计学习研究的角度进行描述。强调了生物和计算模仿方法之间的异同，并概述了当前实际将模仿学习应用于类人机器人的项目。
