• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.37-38
• /
• 2017

최근 방제 및 예찰과 같은 농작업에 단일 UAV(Unmanned Aerial Vehicle)시스템이 적용되고 있지만, 가반하중과 체공시간 등 기존시스템의 문제가 점차 대두되면서 작업 시간을 보다 단축시키고 작업 효율을 극대화 할 수 있는 농업용 멀티 UAV시스템의 필요성이 증대되고 있다. 본 논문에서는 작업자가 다수의 농업용 UAV를 효과적으로 제어할 수 있는 분산군집제어 알고리즘을 제안하며 알고리즘 검증 및 평가를 위한 시뮬레이터를 소개한다. 분산군집제어는 UAV 제어 계층, VP(Virtual Point) 제어 계층, 원격제어 계층으로 이루어진 3계층 제어구조를 가진다. UAV 제어 계층에서 각 UAV는 point mass로 모델링 되는 VP의 이상적인 경로를 추종하도록 제어한다. VP 제어 계층에서 각 VP는 입력 $p_i(t)=u^c_i+u^o_i+u^{co}_i+u^h_i$-(1)을 받아 제어되는데 여기서, $u^c_i{\in}{\mathbb{R}}^3$는 VP 사이의 충돌방지제어, $u^o_i{\in}{\mathbb{R}}^3$는 장애물과의 충돌방지제어, $u^{co}_i{\in}{\mathbb{R}}^3$는 UAV 상호간의 협조제어, $u^h_i{\in}{\mathbb{R}}^3$는 작업자로부터의 원격제어명령이다. (1)의 제어입력에서 충돌방지제어는 각 $u^i_c:=-{\sum\limits_{j{\in}{\eta}_i}}{\frac {{\partial}{\phi}_{ij}^c({\parallel}p_i-p_j{\parallel})^T}{{\partial}p_i}}$-(2), $u^o_c:=-{\sum\limits_{r{\in}O_i}}{\frac {{\partial}{\phi}_{ir}^o({\parallel}p_i-p^o_r{\parallel})^T}{{\partial}p_i}}$-(3)로 정의되면 ${\phi}^c_{ij}$와 ${\phi}^o_{ir}$는 포텐셜 함수를 나타낸다. 원격제어 계층에서 작업자는 햅틱 인터페이스를 통해 VP의 속도를 제어하게 된다. 이때 스케일변수 ${\lambda}$에 대하여 VP의 원격제어명령은 $u^t_i(t)={\lambda}q(t)$로 정의한다. UAV 시뮬레이터는 리눅스 환경에서 ROS(Robot Operating Systems)를 기반한 3차원 시뮬레이터인 Gazebo상에 구축하였으며, 마스터와 슬레이브 간의 제어 명령은 TCPROS를 통해 서로 주고받는다. UAV는 PX4 기반의 3DR Solo 모델을 사용하였으며 MAVROS를 통해 MAVLink 통신 프로토콜에 접속하여 UAV의 고도, 속도 및 가속도 등의 상태정보를 받을 수 있다. 현재 멀티 드론 시스템을 Gazebo 환경에 구축하였으며, 추후 시뮬레이터 상에 분산군집제어 알고리즘을 구현하여 검증 및 평가를 진행하고자 한다.

• Journal of Biosystems Engineering
• /
• 제43권2호
• /
• pp.148-159
• /
• 2018

Purpose: Unmanned air vehicle (UAV) remote sensing was applied to test various vegetation indices and make prediction models of protein content of rice for monitoring grain quality and proper management practice. Methods: Image acquisition was carried out by using NIR (Green, Red, NIR), RGB and RE (Blue, Green, Red-edge) camera mounted on UAV. Sampling was done synchronously at the geo-referenced points and GPS locations were recorded. Paddy samples were air-dried to 15% moisture content, and then dehulled and milled to 92% milling yield and measured the protein content by near-infrared spectroscopy. Results: Artificial neural network showed the better performance with $R^2$ (coefficient of determination) of 0.740, NSE (Nash-Sutcliffe model efficiency coefficient) of 0.733 and RMSE (root mean square error) of 0.187% considering all 54 samples than the models developed by PR (polynomial regression), SLR (simple linear regression), and PLSR (partial least square regression). PLSR calibration models showed almost similar result with PR as 0.663 ($R^2$) and 0.169% (RMSE) for cloud-free samples and 0.491 ($R^2$) and 0.217% (RMSE) for cloud-shadowed samples. However, the validation models performed poorly. This study revealed that there is a highly significant correlation between NDVI (normalized difference vegetation index) and protein content in rice. For the cloud-free samples, the SLR models showed $R^2=0.553$ and RMSE = 0.210%, and for cloud-shadowed samples showed 0.479 as $R^2$ and 0.225% as RMSE respectively. Conclusion: There is a significant correlation between spectral bands and grain protein content. Artificial neural networks have the strong advantages to fit the nonlinear problem when a sigmoid activation function is used in the hidden layer. Quantitatively, the neural network model obtained a higher precision result with a mean absolute relative error (MARE) of 2.18% and root mean square error (RMSE) of 0.187%.

• Journal of Biosystems Engineering
• /
• 제34권4호
• /
• pp.278-285
• /
• 2009

Navigation system is applied in variety of fields including the simple location positioning, autopilot navigation of unmanned robot tractor, autonomous guidance systems for agricultural vehicles, construction of large field works that require high precision and map making process. Particularly utilization of GPS (Global Positioning System) is very common in the present navigation system. This study introduces a navigation system for autonomous field robot that travels to the pre-input path using GPS information. Performance of the GPS- based navigation is highly depended on its receiving rate because GPS receivers do not acquire any navigation information in the period between the refresh intervals. So this study presents an algorithm that improves an accuracy of the navigation by estimation the positional information during the blind period of a low rate GPS receiver. In fact the algorithm calculated the robot's heading in a 50 Hz rate, so the blind period of an 1 Hz GPS receiver is extensively covered. Consequently implementation of the algorithm to the GPS based navigation showed an improvement in guidance accuracy. The conventional field robot directly carried an expensive control computer and sensors onboard, therefore the miniaturization and weight reduction of the robot was limited. In this paper, the field robot carried only communication equipments such as GPS module, normal RC receiver, and bluetooth modem. This enabled the field robot to be built in an economic cost and miniature size.

• 농촌계획
• /
• 제26권3호
• /
• pp.67-77
• /
• 2020

The purpose of this study was to determine the problems of reclamation sites and the prospects of farming in reclamation areas seen by local governments and the KRC branches in Chungnam, Jeonbuk, and Jeonnam provinces. A mail survey method was used. The survey items were set for 15 items regarding the reclamation site situation, problems, and prospects. Seventy-five copies of the questionnaire were distributed to the local government, and 90 copies were sent to the KRC 165 copies in total. In response to the questionnaire, 72 recipients of the local governments responded, showing a 96% response rate, and 74 (82.2%) of the KRC responded. The overall response rate was 88.5%. The opinions on the rental method of the reclaimed land were found to differ according to the geographic conditions of the reclaimed land, the construction conditions, and the time. Regarding the survey on crops preferred for cultivation, rice was highest in both local governments (61%) and KRC (46%). When cultivating field crops in reclaimed land, 56% of local governments and 57% of KRC considered salinity as the most problematic or resolvable problem. Regarding growing other field crops in reclaimed land, salt and drainage problems were recognized as the biggest obstacles in all reclaimed land. As for technologies that need to be applied first for the future agriculture of reclamation land, KRC responded with automatic water management (48%) and local governments responded with unmanned agricultural machinery (32%). In order to diversify the land use in the reclamation area, it is necessary to reduce salt damage and ensure systematic maintenance, employing, for example, automatic water management facilities and drainage improvement methods. The results of this study can set a land use direction for reclamation sites and provide useful information for use in various forms.

• Journal of Biosystems Engineering
• /
• 제43권2호
• /
• pp.138-147
• /
• 2018

Purpose: A narrowband hyperspectral imaging sensor of high-dimensional spectral bands is advantageous for identifying the reflectance by selecting the significant spectral bands for predicting crop yield over the broadband multispectral imaging sensor for each wavelength range of the crop canopy. The images acquired by each imaging sensor were used to develop the models for predicting the Chinese cabbage yield. Methods: The models for predicting the Chinese cabbage (Brassica campestris L.) yield, with multispectral images based on unmanned aerial vehicle (UAV), were developed by simple linear regression (SLR) using vegetation indices, and forward stepwise multiple linear regression (MLR) using four spectral bands. The model with hyperspectral images based on the ground were developed using forward stepwise MLR from the significant spectral bands selected by dimension reduction methods based on a partial least squares regression (PLSR) model of high precision and accuracy. Results: The SLR model by the multispectral image cannot predict the yield well because of its low sensitivity in high fresh weight. Despite improved sensitivity in high fresh weight of the MLR model, its precision and accuracy was unsuitable for predicting the yield as its $R^2$ is 0.697, root-mean-square error (RMSE) is 1170 g/plant, relative error (RE) is 67.1%. When selecting the significant spectral bands for predicting the yield using hyperspectral images, the MLR model using four spectral bands show high precision and accuracy, with 0.891 for $R^2$, 616 g/plant for the RMSE, and 35.3% for the RE. Conclusions: Little difference was observed in the precision and accuracy of the PLSR model of 0.896 for $R^2$, 576.7 g/plant for the RMSE, and 33.1% for the RE, compared with the MLR model. If the multispectral imaging sensor composed of the significant spectral bands is produced, the crop yield of a wide area can be predicted using a UAV.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.521-535
• /
• 2023

논·밭 전환 시 수수(sorghum bicolor L. Moench)는 뛰어난 내습성으로 콩과 함께 안정적인 생산이 가능하여 국내 식량작물의 자급률 향상과 쌀 수급 불균형 문제를 해결할 수 있을 것으로 기대되는 작물이다. 그러나 수량 추정을 위한 재배면적과 같은 기본적인 통계조사는 많은 인력을 투입하여도 오래 걸리는 전통적인 조사 방식으로 인해 잘 이루어 지지 않고 있다. 이에 따라 본 연구에서는 무인기 기반 RGB 영상에 U-Net을 적용하여 수수 재배지 비파괴적 분할가능성을 확인하였다. 2022년에 7월 28일, 8월 13일, 8월 25일에 각각 영상이 취득되었다. 각 영상취득 날짜에서 512 × 512 영상크기로 훈련데이터셋 6,000장과 검증데이터셋 1,000장으로 나누어 학습을 진행하였으며 수수 농경지(sorghum), 벼와 콩 농경지(others)와 비 농경지(background)로 구성된 세 개 클래스와 수수 농경지와 배경(others+background)으로 구성된 두 개 클래스 기반으로 분류모델을 개발하였다. 모든 취득 날짜에서 세 개 클래스 기반 모델에서는 수수 재배지 분류 정확도가 0.91 이상으로 나타났지만 8월 데이터셋의 others 클래스에서 학습 혼동이 일어났다. 대조적으로 두 개 클래스 기반 모델에서는 8월 데이터셋의 안정적인 학습과 함께 모든 클래스에서 0.95 이상의 정확도를 나타내었다. 결과적으로 8월에 두개클래스 기반 모델을 현장에 재현하는 것이 수수 재배지 분류를 통한 재배면적 산출에 유리할 것으로 판단된다.