What is Robotics? An Interdisciplinary Field Is Getting Even More Diverse [Education]
What is Robotics? An Interdisciplinary Field Is Getting Even More Diverse [Education]
复制标题
什么是机器人？
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
A. Birk
中科院分区：
文献类型：
--
作者：
A. Birk
机器人学是一个非常年轻的领域，它是一个跨学科的领域，因为它的本质是开发和构建系统，这些系统遵循真正的技术之前的科幻小说根源，将电子和机械身体部件与计算机大脑相结合。因此，机械工程、电气工程和计算机科学(CS)是机器人学的核心学科。这已经使机器人教育面临相当大的挑战。这三个学科的课程有一些自然的不同，特别是在本科生和研究生学习期间涉及的典型数学主题方面。然而，幸运的是，这些不同学科之间的边界近年来变得更加分散。机器人已经成为许多地方CS教育的流行工具，不仅是为了教授机器人学，而且是为了更广泛的目标，即教育CS学生关于各种物理系统方面的知识。与此同时，如今的机械和电气工程课程包括大量与CS相关的课程。我甚至敢说，不仅是机器人学，而且所有的工程领域现在都已经成为强烈的软件驱动，因此CS方面是他们教育活动的重要组成部分。然而，我们现在正面临着一种新的、更激进的范式转变，即生物/认知学科在机器人学中的相关性日益增强。我想通过图1和图2中显示的两个简单的统计分析来证实这些说法。它们基于对作者在机器人出版物中的从属关系中特定关键词的出现频率进行的天真统计。它们绝对不是一项彻底的研究，但它们给出了一些有趣的迹象，说明了事情是如何发展和正在发展的。具体地说，这些数据来自科学信息研究所科学信息网。图1基于1989年至2009年发表的所有出版物，根据科学引文索引按影响排名前十名的机器人期刊。总体而言，大约有5000篇文章被考虑在内。Web of Science使用了学科缩写的标准化方案，这使得在每篇文章的作者关系中简单地搜索代表这里感兴趣的学科的相关关键字，即机械工程、电气工程和CS。此外，还考虑了具有生物/认知联系的研究人员的数量，即生物学、神经科学、心理学和认知科学的相关关键词也被统计在内。这些百分比反映了不同学科每年发生的次数。当然，每篇文章可能有多个作者，每个作者都在不同的学科工作，一些从属关系甚至可能包括多个关键词，这些关键词都被相应地计算在内。图2显示了1981至1988年间的数据。由于科学网在这段时间内没有很好地涵盖机器人学期刊，所以简单地说，所有可以用关键字机器人检索到的出版物都被用于这一分析。尽管如此，这只导致了总共约1000份出版物。主要的分析就像图1一样，即通过作者所属学科中不同学科出现的频率计数。首先要注意的是，在过去的两年中，与CS相关的工作似乎主导了机器人技术
R obotics is a very young field, which is interdisciplinary due to its nature of developing and building systems that, following its science fiction roots that preceded the real technology, combine electrical and mechanical body components with computer brains. Accordingly, mechanical engineering, electrical engineering, and computer science (CS) are core disciplines involved in robotics. This already makes robotics education quite challenging. There are some natural differences in the curricula of these three disciplines, especially when it comes to the typical coverage of mathematical topics during undergraduate and graduate studies. However, fortunately, the borders between these different disciplines have become much more dispersed in recent years. Robots have become popular tools in CS education at many places, not necessarily to just teach robotics but for the more general goal to educate CS students about a variety of physical system aspects. At the same time, mechanical and electrical engineering programs nowadays include substantial amounts of CS-related courses. I even dare to claim that not only robotics but all engineering fields have nowadays become strongly software driven, and hence CS aspects are a significant part of their education activities. However, we are now facing a new, more radical paradigm shift, namely an increasing relevance of bio/cognitive disciplines in robotics. I want to substantiate these claims by two simple statistical analyses shown in Figures 1 and 2. They are based on a naive frequency count of the occurrence of certain key words in authors’ affiliations in robotics publications. They are by no means a thorough study, but they give some interesting indications of how things developed and are developing. Concretely, the data are taken from the Institute for Scientific Information Web of Science. Figure 1 is based on all publications that appeared from 1989 to 2009 in the top ten robotics journals ranked by impact according to the Science Citation Index. Overall, about 5,000 articles were taken into account. The Web of Science uses a standardized scheme for the abbreviation of disciplines, which eases a simple search in the authors’ affiliations of each article for the related key words representing the disciplines of interest here, namely mechanical engineering, electrical engineering, and CS. In addition, the number of researchers with biological/cognitive affiliations was taken into account, i.e., the related key words for biology, neuroscience, psychology, and cognitive science were also counted. The percentages reflect the number of occurrences of different disciplines each year. Each article, of course, may have multiple authors, each working in a different discipline, and some affiliations may even include multiple key words, which were all counted accordingly. Figure 2 shows data for the period from 1981 to 1988. As robotics journals are not well covered in this time period in the Web of Science, simply all publications that could be retrieved with the key word robot were used for this analysis. Still, this only led to about 1,000 publications in total. The main analysis was done just like for Figure 1, i.e., by a frequency count of the occurrence of the different disciplines in the authors’ affiliations. The first thing that can be noticed is that CS-related work, indeed, seems to be dominating robotics in the last two