首页> 外文会议>Eighth Neural Computation and Psychology Workshop; 20030828-30; University of Kent(GB) >STAGED LEARNING OF SACCADIC EYE MOVEMENTS WITH A ROBOT CAMERA HEAD
【24h】

STAGED LEARNING OF SACCADIC EYE MOVEMENTS WITH A ROBOT CAMERA HEAD

机译:带有机器人摄像头的视线运动的分阶段学习

获取原文
获取原文并翻译 | 示例

摘要

In motor learning, two main problems arise: the missing teacher signal, and the necessity to explore high-dimensional sensorimotor spaces. Several solutions have been proposed, all of them limited in some respect. In the present work, an alternative learning mechanism is developed for the example of saccade control, imple-mented on a stereo vision robot camera head. This approach relies on two main principles: averaging over imperfect learning examples, and learning in multiple stages. In each stage, a saccade controller is trained with a set of imperfect learning examples. Afterwards, the output of this controller serves as starting point for the creation of a new training set with better quality. By the repetition of these steps, the controllers' performance can be incrementally improved without the need to search from scratch for the rare learning examples with very good quality.
机译:在运动学习中,出现两个主要问题:缺少教师信号,以及探索高维感觉运动空间的必要性。已经提出了几种解决方案,它们都在某些方面受到限制。在本工作中,针对扫视控制的示例开发了一种替代学习机制,该机制在立体视觉机器人摄像头上实现。该方法基于两个主要原理:对不完美的学习示例进行平均,以及分多个阶段进行学习。在每个阶段中,均使用一组不完善的学习示例来训练扫视控制器。之后,此控制器的输出将作为创建质量更好的新训练集的起点。通过重复这些步骤,可以逐渐提高控制器的性能,而无需从头开始搜索质量非常好的罕见学习示例。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号