首页> 美国卫生研究院文献>Sensors (Basel Switzerland) >Vision-Based Target Finding and Inspection of a Ground Target Using a Multirotor UAV System
【2h】

Vision-Based Target Finding and Inspection of a Ground Target Using a Multirotor UAV System

机译:使用多旋翼无人机系统的基于视觉的目标查找和地面目标检查

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

In this paper, a system that uses an algorithm for target detection and navigation and a multirotor Unmanned Aerial Vehicle (UAV) for finding a ground target and inspecting it closely is presented. The system can also be used for accurate and safe delivery of payloads or spot spraying applications in site-specific crop management. A downward-looking camera attached to a multirotor is used to find the target on the ground. The UAV descends to the target and hovers above the target for a few seconds to inspect the target. A high-level decision algorithm based on an OODA (observe, orient, decide, and act) loop was developed as a solution to address the problem. Navigation of the UAV was achieved by continuously sending local position messages to the autopilot via Mavros. The proposed system performed hovering above the target in three different stages: locate, descend, and hover. The system was tested in multiple trials, in simulations and outdoor tests, from heights of 10 m to 40 m. Results show that the system is highly reliable and robust to sensor errors, drift, and external disturbance.
机译:本文提出了一种使用目标检测和导航算法以及多旋翼无人机(UAV)来寻找地面目标并对其进行仔细检查的系统。该系统还可用于在特定地点的作物管理中准确,安全地输送有效载荷或点喷应用。连接到多旋翼的向下看的摄像机用于在地面上找到目标。无人机下降到目标并悬停在目标上方几秒钟以检查目标。开发了一种基于OODA(观察,定向,决策和行动)循环的高级决策算法,作为解决该问题的解决方案。无人机的导航是通过Mavros连续向自动驾驶仪发送本地位置信息来实现的。拟议的系统在三个不同阶段执行了悬停在目标上方的操作:定位,下降和悬停。该系统在10 m至40 m的高度进行了多次试验,模拟和室外试验。结果表明,该系统对传感器错误,漂移和外部干扰具有高度的可靠性和鲁棒性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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