Tutelage and socially guided robot learning
Tutelage and socially guided robot learning
复制标题
监护和社会引导的机器人学习
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
C. Breazeal
中科院分区：
文献类型：
--
作者：
A. Thomaz;C. Breazeal
我们认为机器学习的问题是人与机器之间的协作。受人类指导风格的启发，我们将学习问题置于一个对话中，在这个对话中，社会互动构建了学习经验，提供指导，引导注意力，控制任务的复杂性。我们提出了一种学习机制，在人形机器人上实现，以证明协作对话框架允许机器人有效地从人类那里学习任务，将这种能力推广到新的任务配置，并显示对学习任务的总体目标的承诺。我们还将这种方法与传统的机器学习方法进行了比较。
We view the problem of machine learning as a collaboration between the human and the machine. Inspired by human-style tutelage, we situate the learning problem within a dialog in which social interaction structures the learning experience, providing instruction, directing attention, and controlling the complexity of the task. We present a learning mechanism, implemented on a humanoid robot, to demonstrate that a collaborative dialog framework allows a robot to efficiently learn a task from a human, generalize this ability to a new task configuration, and show commitment to the overall goal of the learned task. We also compare this approach to traditional machine learning approaches.