京都大学 / 0048 / 新制・課程博士 / 博士(農学) / 甲第22783号 / 農博第2426号 / 新制||農||1081(附属図書館) / 学位論文||R2||N5303(農学部図書室) / 京都大学大学院農学研究科地域環境科学専攻 / (主査)教授 近藤 直, 教授 飯田 訓久, 准教授 小川 雄一 / 学位規則第4条第1項該当 / Doctor of Agricultural Science / Kyoto University / DFAM

As the population continues to grow, so does the demand for food and raw materials. In order to keep up to supply this increased demand, a development of the way in which food is produced today is required. With the help of robots, there is a future in agriculture where crops can be produced more efficiently. The purpose of this study is to investigate how autonomous agricultural robots can be used to make today's agriculture more efficient, and what technologies are available for this. This has been done by studying how robots that have been involved in previous research work. What they are used for and what benefit they have added has also been studied. Research literature was selected and analyzed. The analysis took place via a literature study in which a number of sub-questions were asked regarding the three perspectives area of use, technology and utility. This was done with the intention of being able to answer the study's formulated research questions. This resulted in a compilation and analysis of a number of articles' views on the problem based on the three perspectives. The conclusions that were drawn were that agricultural robots should primarily be used for harvesting various crops, weed control and data collection for control of soil and crops. It was also found that some form of manipulator, machine vision, sensors, navigation systems, measurement systems, analysis systems and algorithms for cooperation between robots, are used and are available in most types of agricultural robots regardless of area of use. The study showed that the use of agricultural robots in these areas and with the help of this technology, could streamline the agricultural sector by reducing labor costs, saving time, increasing production levels, reducing the amount of crops wasted and contributing to reduced use of chemicals. / I takt med en ständigt växande befolkningsmängd ökar också efterfrågan på mat och råvaror. För att hinna med att tillförse denna ökade efterfrågan krävs det en utveckling av det sätt som det idag produceras mat på. Med hjälp av robotar finns det en framtid inom jordbruket där grödor kan produceras effektivare. Syftet med denna studie är att undersöka hur autonoma jordbruksrobotar kan användas för att effektivisera dagens jordbruk, samt vilka teknologier som finns tillgängliga för detta. Detta har utförts genom att studera hur de robotar som det tidigare utförts forskning kring fungerar. Även vad de används till samt vilken nytta de tillfört har studerats. Forskningslitteratur valdes ut och analyserades. Analysen skedde via en litteraturstudie där ett antal delfrågor ställdes upp gällande de tre perspektiven användningsområde, teknik och nytta. Detta gjordes med avsikt att kunna besvara studiens formulerade forskningsfrågor. Detta resulterade i en sammanställning och analys av ett antal artiklars syn på problemet utifrån de tre perspektiven. De slutsatser som drogs var att jordbruksrobotar i första hand bör användas för skörd av olika grödor, ogräskontroll samt datainsamling för kontroll av mark och grödor. Det konstaterades även att någon form av manipulator, maskinsyn, sensorer, navigationssystem, mätsystem, system för analys samt algoritmer för samarbete mellan robotar, används och finns tillgängliga i de flesta typer av jordbruksrobotar oavsett användningsområde. Studien gav att användning av jordbruksrobotar inom bland annat dessa områden och med hjälp av denna teknik, kan effektivisera jordbrukssektorn genom att minska kostnader för arbetskraft, spara tid, öka produktionsnivån, minska mängden grödor som går till spillo samt bidra till minskad användning av kemikalier.

[pt] Neste trabalho, apresenta-se diferentes esquemas de controle servovisuais para tarefas robóticas de colheita de fruta, na presença de incertezas paramétricas nos modelos do sistema. O primeiro esquema combina as abordagens de servovisão baseada em posição (PBVS) e servovisão baseada em imagem (IBVS) para realizar, respectivamente, a aproximação até a fruta e, em seguida, um ajuste fino para a colheita. O segundo esquema usa uma abordagem de servovisão híbrida (HVS) para realizar a tarefa de colheita completa, projetando uma lei de controle adequada que combina vetores de erro definidos no espaço operacional e no espaço da imagem. A fase de detecção utiliza um algoritmo baseado no espaço de cores OTHA e limiar da imagem Otsu para um rápido reconhecimento de frutos maduros em cenários complexos. Além disso, um método de detecção mais preciso emprega uma Rede Neural Convolucional Profunda (DCNN) pré-treinada baseada em uma versão Segnet minimizada para uma inferência rápida durante a execução da tarefa. A localização do objeto é realizada empregando uma técnica de triangulação de imagem, que combina os algoritmos SURF e RANSAC ou ORB e BF-Matcher para extrair a característica da imagem da fruta e associa-lo com o seu ponto correspondente na outra visualização. No entanto, como esses algoritmos exigem um elevado custo computacional para os requisitos da tarefa, um método de estimativa mais rápido utiliza o centróide da fruta e transformação homogênea para descobrir os pontos correspondentes. Finalmente, um esquema de controle em modos deslizantes (SMC) baseado em visão e uma função de monitoramento de comutação são empregados para lidar com incertezas nos parâmetros de calibração do sistema de câmera-robô. Nesse sentido, é possível garantir a estabilidade assintótica e a convergência do erro da característica da imagem, mesmo que o ângulo de desalinhamento, em torno do eixo z, entre os sistemas de coordenadas da câmera e do efetuador seja incerto. / [en] In this work, we present different eye-in-hand visual servoing control schemes applied to a robotic harvesting task of soft fruits in the presence of parametric uncertainties in the system models. The first scheme combines position-based visual servoing (PBVS) and image-based visual servoing (IBVS) approaches in order to perform respectively an approach phase to the fruit and then a fine tuning of the end-effector to harvest. The second scheme uses a hybrid visual servoing (HVS) approach to fulfill the complete harvesting task, by designing a suitable control law which combines error vectors defined in both the image and operational spaces. For detecting the fruits, an algorithm based on the combination of the OHTA color space and Otsu’s threshold method for a fast recognition of mature fruits in complex scenarios. In addition, a more accurate detection method employs a pre-trained deep encoder-decoder algorithm based on a minimized Segnet version for a fast and cheap inference during the task execution. The object localization is accomplished by employing an image triangulation technique, which combines the speeded-up-robust-features (SURF) and the-randomsample-consensus (RANSAC) or the Oriented FAST and Rotated BRIEF and the Brute-Force Matcher (BF-Matcher) algorithms to extract the fruit image feature and match it to its correspondent feature-point into the other view of the stereo camera. However, since these algorithms are computationally expensive for the task requirements, a faster estimation method uses the fruit centroid and a homogeneous transformation for discovering matching points. Finally, a vision-based sliding-mode-control scheme and a switching monitoring function are employed to cope with uncertainties in the calibration parameters of the camera-robot system. In this context, it is possible to guarantee the asymptotic stability and convergence of the image feature error, even if the misalignment angle, around the z-axis, between the camera and end-effector frames is uncertain. 3D computer simulations and preliminary experimental results, obtained with a Mitsubishi robot arm RV-2AJ carrying out a simple strawberry picking task, are included to illustrate the performance and effectiveness of the proposed control scheme.