计算机工程 ›› 2019, Vol. 45 ›› Issue (4): 311-315,320.doi: 10.19678/j.issn.1000-3428.0050023

• 开发研究与工程应用 • 上一篇    下一篇

基于IHDR的自主学习巡检技术研究

俞玉瑾1,韩军1,赵庆喜2,张红梅3   

  1. 1.上海大学 上海先进通信与数据科学研究院,上海 200444; 2.河南立新监理咨询有限公司,郑州 450052; 3.国网河南省电力公司濮阳供电公司,河南 濮阳 457000
  • 收稿日期:2018-01-08 出版日期:2019-04-15 发布日期:2019-04-15
  • 作者简介:俞玉瑾(1993—),女,硕士研究生,主研方向为无人机巡检;韩军,副教授;赵庆喜、张红梅,高级工程师。
  • 基金项目:

    国家自然科学基金面上项目(61471230)。

Research on Autonomous Learning Inspection Technology Based on IHDR

YU Yujin1,HAN Jun1,ZHAO Qingxi2,ZHANG Hongmei3   

  1. 1.Shanghai Institute for Advanced Communication and Data Science,Shanghai University,Shanghai 200444,China; 2.Henan Lixin Supervision Consulting Co.,Ltd.,Zhengzhou 450052,China; 3.Puyang Power Supply Bureau,Henan Electric Power Corporation,Puyang,Henan 457000,China
  • Received:2018-01-08 Online:2019-04-15 Published:2019-04-15

摘要:

针对无人机路径规划存在只适用于静态场景的问题,提出一种自主飞行巡检方法。利用增量分层判别回归(IHDR)树存储无人机飞行经验,通过当前位置矢量搜索IHDR树,得到飞行控制量。根据当前位置与期望位置的偏差调整输出控制量,实现人造目标的巡检。实验结果表明,与IHDR方法相比,该方法学习时间缩短12.2%,且具有较高的准确率,适用于无人机巡检。

关键词: 无人机, 自主飞行, 姿态学习, 任务学习, 增量分层判别回归, 动态场景, 飞行控制

Abstract:

Aiming at the problem that unmanned aerial vehicle path planning only applies to static scenes,an autonomous flight inspection method is proposed.The drone stores the flight experience in the structure of the Incremental Hierarchical Discriminant Regression(IHDR) tree.The current position vector is input to search the IHDR tree to obtain the flight control amount.The output control amount is adjusted according to the deviation between the current position and the desired position,and the inspection of the artificial target is realized.Experimental results show that compared with the IDHR method,the learning time of the method is shortened by about 12.2%,and the method has high accuracy,and is suitable for drone inspection.

Key words: unmanned aerial vehicle, autonomous flight, attitude learning, task learning, Incremental Hierarchical Discriminant Regression(IHDR), dynamic scenes, flight control

中图分类号: