针对无人车转角输出的端对端方法
DOI:
作者:
作者单位:

贵州大学 机械工程学院

作者简介:

通讯作者:

中图分类号:

文献标志码: A 中图分类号:TP273

基金项目:

黔科合支撑[2017]2027;黔科合平台人才[2017]5630;黔科合支撑[2018]2168.


Research on End-to-end Learning Method for Angle Output of Autopilot Model
Author:
Affiliation:

Department of Mechanical Engineering, Guizhou University

Fund Project:

Project Supported by Guizhou Province [2017]2027 Project Supported by Guizhou Province [2017]5630;Project Supported by Guizhou Province [2018] 2168.

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对端对端学习过程中的数据不均衡、时间成本高、输出不够鲁棒等问题,通过数据均衡、图像尺寸变换及双边滤波对数据集进行优化,降低了卷积神经网络(CNN)模型输出的误差,此外使用固定区域的图像剪切与图像尺寸变换降低了模型训练的时间成本。分别对是否经过均衡与处理的数据集进行训练获得两种模型,首先将两种模型的输出与原始数据进行对比,此外对平均训练时间进行比较,最终在智能小车上进行了自动驾驶实验。证明所提出方法改善了端对端输出的鲁棒性、降低了模型训练的时间成本。

    Abstract:

    In order to solve the problems of data unbalance, high time cost and insufficient output robustness in the end-to-end learning process, the data set is optimized by data equalization, image size conversion and bilateral filtering. Besides these the error in output of the convolutional neural network(CNN) mode is reduced. In addition to, image clipping and image size conversion was used to reduce the time cost of model training. Two models are trained separately for the data set that whether has been equalized and processed. Firstly, the output of the two models was compared with the original data. Secondly, the average training time was compared. finally, the self-driving experiment was carried out in the smart car. It is proved that the method improves the robustness of end-to-end output and reduces the time cost of model training.

    参考文献
    相似文献
    引证文献
引用本文

付浩龙,赵津,席阿行,等. 针对无人车转角输出的端对端方法[J]. 科学技术与工程, 2019, 19(36): 207-211.
付浩龙,, and. Research on End-to-end Learning Method for Angle Output of Autopilot Model[J]. Science Technology and Engineering,2019,19(36):207-211.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-05-08
  • 最后修改日期:2019-06-18
  • 录用日期:2019-07-14
  • 在线发布日期: 2020-01-21
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注