Search

Especificaciones de diseño y funcionamiento de una plataforma robótica para fertilizar planta a planta un cultivo ecológico

Los entornos pos-desastre, consecuencia de catástrofes naturales o atentados, dejan como resultado pérdidas humanas, en medio de zonas colapsadas de acceso potencialmente riesgoso para rescatistas, debido al colapso de estructuras o eventuales explosiones. La Robótica de Búsqueda y Rescate ha sido una línea con gran auge dentro de este campo en las últimas décadas, brindando principalmente soporte (transmisión de imagen o mapeo) a brigadas de intervención. El presente artículo muestra la implementación de un método para identificación automática de víctimas en estos entornos a través de redes neuronales convolucionales, imágenes térmicas y ROS (Robot Operating System). Para ello se ha utilizado el robot cuadrúpedo ARTU-R (A1 Rescue Task Unitree Robot) por a su gran destreza para moverse en terrenos no estructurados, el cual ha sido dotado de un sistema especializado de visión térmica. Para validar este desarrollo se han llevado a cabo pruebas en entornos pos-desastre reconstruidos. El método propuesto ha permitido generar mapas 2D enriquecidos con información de potenciales víctimas e incendios para su posterior uso. Los principales resultados han mostrado una eficacia superior al 90% para la identificación de víctimas totalmente visibles y victimas parcialmente cubiertas por escombros.

Mechanization in organic strip-crops is difficult due to plant layout on the ground. In this work, a prototype of automated robot for providing organic fertiliser at single plant scale is described.

The Sureveg project is a international consortium funded by CORE Organic Cofund devoted to foster biodiversity (above and below ground) by using new agricultural practices related to crop association in a strip-crop scheme, and applitying digital technologies (robotics, sensorics)for a organic sustainable production.

At the Organic World COngress 2021 (Rennes, France) a Workshop about the SUREVEG project was held to rise awareness about strip croppping, biodiversity and smart machines

In precision agriculture (PA), vegetation indices (VI) are commonly used to evaluate the health of crops with the use of multi-spectral cameras. These are often mounted on drones and used at high altitudes, where the translation of focal points and subsequent changes in perspective do not pose any difficulties. In proximal sensing, however, these translations and distortions pose a significant challenge on data processing. In this work, a Parrot Sequoia camera was mounted at a fixed height of 1.2 m and used at 3 sec and 1.5 sec intervals on an organic strip-cropping field beneath. Reference imaging revealed that the multi-spectral lenses suffer from significant barrel distortion of 30%, while the higher resolution RGB lens has a barely distinguishable 1% pincushion distortion. The subsequent field images were stitched together using an open-source panorama software to automatically detect and correct distortions. The resulting mosaics were then shifted to correct the relative position of the separate lenses, allowing for VI calculation with mm accuracy. This method allows for analysing single plants for inter-crop and even intra-crop variation, allowing the automation of tasks in an organic multicrop environment.

The increasing demand of organic vegetables has driven conventional farmers to change their businesses in order to develop organic methods for cultivation and the use of alternative techniques to avoid damaging the soil and the quality of the products. In some cases, to enhance biodiversity and soil fertility, crops are established in a mixed pattern called ‘strip cropping’ where single or dual lines of a given species are alternated with a second compatible species, with the aim to enhance resilience, system sustainability, local nutrient recycling, and soil carbon storage. However, this husbandry of crops grown and mixed in a strip design pose new challenges regarding mechanisation, which in many cases can only be overcome by increasing human tasks. To counteract the additional labour of a multi-crop system, one of the main objectives of the ‘Sureveg’ CORE Organic Cofund ERA-Net European project is to evaluate the benefits of growing in alternate rows for the production of organic vegetables and includes the use of robots as a tool to facilitate the automation of the process, allowing the individual treatment of organic fertilization at plant level. Within the project framework a modular proof-of-concept version has been produced, combining several sensing technologies (3x LiDAR, plus a multispectral RGB-NIR camera) with actuation in the form of a robotic arm operating upside down. The present work describes a method to develop fertilization tasks with recycled organic waste in strip-cropping farms, based on detection of plant species (cabbage) using and liquid fertilizer application with a robot. For that, it is necessary to identify the crop (variable in the rows) and place the robot with respect to the plants to apply the product. Test fields were located at ETSIAAB - UPM (40°26’33.1"N, 3°43’41.9"W) where stripped crops were established and monitored along the growing season. In order to detect autonomously each single plant, point clouds of the three LiDAR units were combined, soil was removed applying a weighted threshold, and plants were identified using clustering and convolutional neural network methodologies. To trigger the actuation system, the decision on which plant had to be sprayed with the liquid fertilizer was taken according to two factors: 1) the estimated volume of every single plant, and 2) the multispectral indexes calculated using the RGB-NIR camera. The prototype is fully functional, and further test are needed to quantify its performance

This working document (deliverable D4.2, non public) describes the robotic prototype designed and constructed in Madrid by the teams from the CAR-CSIC institute and the Univ Politécnica de Madrid (ETSIAAB) in the framework of the SUREVEG project (Core Organic Cofund)

This document is a compilation of algorithms grouped as the deliverable D4.3 in the project SUREVEG (Core Organic Cofund). They are needed for the acquisition of crop information using the sensorinc onboard the robotic platform, as well as for the control of the robotic actuator (arm motion, fertilization system) in a strip-crop organic environment

This presentation is aimed at estimating the position of the robot in row crops despite continuous changes in the environment (due to wind or small plant growth), using a LiDAR sensor to obtain global point clouds (previously registered, all-terrain) and local point clouds (from one part of the ground obtained during the advance of the robot), in fertilization tasks

The great potential, reliability and the high number of applications made through artificial vision, are fundamental for the development of a monitoring system pyroclastic flows for active volcanoes axis through a platform called Raspberry Pi based on free software (Ubuntu), the great potential of it allows you to run several software for the application of computer vision techniques, make data processing and also control outputs from the same board. Thus the main points to note when using an embedded system are a stable data acquisition, fast processing and control outputs to operate alarm systems, but especially the cost is reduced and reliable system. ESPE-L

Recent developments in bioinspired technologies combined with the advance of intelligent and soft materials have allowed soft robots to replicate the behavior of different animal species. These devices can perform complicated tasks such as reaching or adapting in constrained and unstructured environments. This article proposes a methodology to develop a soft robot called &ldquo, JellyRobcib&rdquo, inspired in morphology and behavior by jellyfish, using shape-memory alloy springs as actuators (as bio-muscles). Such actuators can move the jellyfish both vertically and laterally by applying closed-loop fuzzy and visual controls. Additionally, Computer-Assisted Designs and Computational Fluid Dynamics simulations have been carried out to validate the soft robot model. The results show that the robot movements are very close to the morphological behavior of a real jellyfish regarding the curves of displacements, speeds and accelerations, after performing several experiments for autonomous movement: vertical ascent, lateral movements and trajectory tracking, obtaining an accuracy of &plusmn, 1479 cm and repeatability of 0.944 for lateral movements for fuzzy visual control. Furthermore, thermal measurements were taken throughout a given path, allowing the generation of temperature gradients within the underwater environment for monitoring purposes.