Trend Technologies for Robotic Fertilization Process in Row Crops

Frontiers in Robotics and AI

Antonio Barrientos¹  Jaime del Cerro¹  Christyan Cruz Ulloa¹  Constantino Valero²  Anne Krus² 

[1] Centro de Automática y Robótica, Consejo Superior de Investigaciones Científicas, Universidad Politécnica de Madrid, Madrid, Spain;Departamento de Ingeniería Agroforestal, ETSI Agronómica, Alimentaria y de Biosistemas, Universidad Politécnica de Madrid, Madrid, Spain;

关键词: smart farming;    robotics in agriculture;    multi-spectral images;    precision agriculture;    point clouds;   

DOI  :  10.3389/frobt.2022.808484

来源: DOAJ

【 摘 要 】

The development of new sensory and robotic technologies in recent years and the increase in the consumption of organic vegetables have allowed the generation of specific applications around precision agriculture seeking to satisfy market demand. This article analyzes the use and advantages of specific optical sensory systems for data acquisition and processing in precision agriculture for Robotic Fertilization process. The SUREVEG project evaluates the benefits of growing vegetables in rows, using different technological tools like sensors, embedded systems, and robots, for this purpose. A robotic platform has been developed consisting of Laser Sick AG LMS100 × 3, Multispectral, RGB sensors, and a robotic arm equipped with a fertilization system. Tests have been developed with the robotic platform in cabbage and red cabbage crops, information captured with the different sensors, allowed to reconstruct rows crops and extract information for fertilization with the robotic arm. The main advantages of each sensory have been analyzed with an quantitative comparison, based on information provided by each one; such as Normalized Difference Vegetation Index index, RGB Histograms, Point Cloud Clusters). Robot Operating System processes this information to generate trajectory planning with the robotic arm and apply the individual treatment in plants. Main results show that the vegetable characterization has been carried out with an efficiency of 93.1% using Point Cloud processing, while the vegetable detection has obtained an error of 4.6% through RGB images.

【 授权许可】

Unknown