• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>配管·装置·プラント技術 >Studies on self-learning autonomous vehicles (part 3)-positioning system for autonomous vehicle
【24h】

Studies on self-learning autonomous vehicles (part 3)-positioning system for autonomous vehicle

机译：自学自动驾驶汽车研究（第三部分）-自动驾驶汽车定位系统

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The environment in which an agricultural vehicle works is a time variant and nonlinear system therefore, an adaptive steering controller is required for navigating the vehicle precisely. In this paper, the positioning system which utilized avision information was modified, so as to be applied for the neuro-controller which is one of nonlinear controllers. The classifier of the visual marker and the background which we developed, is based on the chromaticities subjected to a rotation and atranslation of coordinates. The accuracy of the positioning system which was investigated by a field experiment, showed maximum error of 13cm on a flat meadow of 40 m×60 m. In addition, the recognition method of the visual marker, which applied a neuralnetwork, was also developed to improve the measurement accuracy. Finally, the vehicle automation experiment was conducted on a flat meadow hypothesized on a reciprocating work. As a result, the autonomous vehicle was able to travel in a desired work width using the positioning system, and indicated satisfied performance.
机译：农用车辆的工作环境是时变的并且是非线性系统，因此需要自适应转向控制器来精确地导航车辆。本文对利用视觉信息的定位系统进行了改进，以应用于非线性控制器之一的神经控制器。视觉标记和我们开发的背景的分类器基于经过坐标旋转和平移的色度。通过现场实验研究的定位系统的精度在40 m×60 m的平坦草地上显示出13cm的最大误差。此外，还开发了应用神经网络的视觉标记识别方法，以提高测量精度。最后，在假设为往复式作业的平坦草地上进行了车辆自动化实验。结果，自动驾驶车辆能够使用定位系统以期望的工作宽度行驶，并表现出令人满意的性能。

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