Adaptation as a more powerful tool than decomposition and integration: experimental evidences from evolutionary robotics
Adaptation as a more powerful tool than decomposition and integration: experimental evidences from evolutionary robotics
复制标题
适应是比分解和整合更强大的工具：进化机器人学的实验证据
DOI：
10.1109/fuzzy.1998.687473
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
S. Nolfi
中科院分区：
文献类型：
--
作者：
S. Nolfi
一种新的建立控制系统的方法，被称为基于行为的机器人，已经被提出来克服传统的人工智能机器人方法的困难。在基于行为的机器人中完成的大部分工作涉及分解过程(在该过程中，所需的行为被分解成更简单的子组件)和整合过程(在该过程中，为产生子行为而设计的模块被组合在一起)。我们认为，分解和整合应该是适应过程的结果，而不是实验者的决定。在本文中，我们通过展示在两种不同的情况下如何通过让整个行为通过进化技术出现而不是试图设计一组模块并协调它们来获得更简单和健壮的解决方案来支持这一假设。
A new way of building control systems, known as behavior based robotics, has been proposed to overcome the difficulties of the traditional Al approach to robotics. Most of the work done in behavior-based robotics involves a decomposition process (in which the behavior required is broken down into simpler sub-components) and an integration process (in which the modules designed to produce the sub-behaviors are put together). We claim that decomposition and integration should be the result of an adaptation process and not of the decision of the experimenter. In this paper we support this hypothesis by showing how in two different cases a more simple and robust solution can be obtained by letting the entire behavior emerge through an evolutionary technique than by trying to design a set of modules and to coordinate them.