Coevolution of active vision and feature selection
Coevolution of active vision and feature selection
复制标题
DOI：
10.1007/s00422-004-0467-5
复制
发表时间：
2004-03-01
影响因子：
1.9
通讯作者：
Sauser, E
中科院分区：
文献类型：
--
作者：
Floreano, D;Kato, T;Sauser, E
我们表明，复杂的视觉任务，如位置和大小不变的形状识别和导航的环境中，可以解决简单的架构所产生的协同进化过程中的主动视觉和特征选择。行为机器配备了原始的视觉系统和视觉和运动神经元之间的直接通路，同时它们与环境自由互动。我们描述了这种方法在三组实验中的应用，即形状歧视，汽车驾驶和机器人导航。我们发现，这些系统开发的敏感性，一些定向，retinotopic，视觉功能为导向的边缘，角落，高度，和行为的剧目定位，带来，并保持这些功能在视觉系统的敏感区域，类似于在简单的昆虫观察到的策略。
We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while they freely interact with their environments. We describe the application of this methodology in three sets of experiments, namely, shape discrimination, car driving, and robot navigation. We show that these systems develop sensitivity to a number of oriented, retinotopic, visual-feature-oriented edges, corners, height, and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system, resembling strategies observed in simple insects.