Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Augmented Perception for Agricultural Robots Navigation

  • Rovira Más, Francisco|||0000-0002-2589-9281
  • Saiz Rubio, Verónica|||0000-0003-4188-3666
  • Cuenca Cuenca, Andres
[EN] Producing food in a sustainable way is becoming very challenging today due to the lack of skilled labor, the unaffordable costs of labor when available, and the limited returns for growers as a result of low produce prices demanded by big supermarket chains in contrast to ever-increasing costs of inputs such as fuel, chemicals, seeds, or water. Robotics emerges as a technological advance that can counterweight some of these challenges, mainly in industrialized countries. However, the deployment of autonomous machines in open environments exposed to uncertainty and harsh ambient conditions poses an important defiance to reliability and safety. Consequently, a deep parametrization of the working environment in real time is necessary to achieve autonomous navigation. This article proposes a navigation strategy for guiding a robot along vineyard rows for field monitoring. Given that global positioning cannot be granted permanently in any vineyard, the strategy is based on local perception, and results from fusing three complementary technologies: 3D vision, lidar, and ultrasonics. Several perception-based navigation algorithms were developed between 2015 and 2019. After their comparison in real environments and conditions, results showed that the augmented perception derived from combining these three technologies provides a consistent basis for outlining the intelligent behavior of agricultural robots operating within orchards., This work was supported by the European Union Research and Innovation Programs under Grant N. 737669 and Grant N. 610953. The associate editor coordinating the review of this article and approving it for publication was Dr. Oleg Sergiyenko.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

Uso de la espectroscopía NIR como herramienta de monitorización no invasiva del estado hídrico del viñedo

  • Diago, Maria P.
  • Fernández-Novales, Juan
  • Gutiérrez, Salvador
  • Marañón Grandes, Miguel
  • Tardáguila, Javier
Trabajo presentado a las II Jornadas del Grupo de Viticultura y Enología (SECH), celebradas en Madrid el 3 y 4 de noviembre de 2016., La espectroscopía NIR se utiliza ampliamente para caracterizar numerosos sistemas biológicos mediante el estudio de las principales bandas de absorción del agua. Este trabajo presenta y compara con métodos de referencia clásicos una nueva herramienta no invasiva, basada en la espectroscopía NIR, para determinar el estado hídrico de la vid de forma continua en el viñedo. Los datos experimentales se tomaron en cuatro fechas, entre envero y vendimia, en el año 2015, en un viñedo comercial de la variedad Tempranillo (orientación N-S) en Tudelilla (La Rioja). Con el fin de generar una variabilidad del estado hídrico de las cepas, se implantaron tres regímenes de riego distintos .. Las medidas espectrales se tomaron a 30 cm de distancia de la espaldera, en ambas caras de la misma, al mediodía solar con un espectrómetro NIR montado en un quad que circulaba a 5 km/h. De forma simultánea, se tomaron medidas de potencial hídrico del tallo (s) y de conductancia estomática (gs) Los modelos de validación cruzada (CV) y predicción externa (P) obtenidos mediante regresión de mínimos cuadrados parciales (PLS) mostraron los mejores resultados de coeficiente de determinación (R2) y error típico (SE) cuando se midió en la cara este de la espaldera. Para el s, se obtuvieron valores de R2 cv=0.88 y SECV= 1.61 MPa, y de R2 P= 0.92 y SEP=1.27 MPa, mientras que para gs los resultados obtenidos fueron R2 cv=0.72 y SECV= 81.7 mmol H2O m-2 s-1, y R2 P= 0.75, SEP=74.9 mmol H2O m-2 s-1. Estos resultados son prometedores y muestran el potencial de la espectroscopía NIR, no invasiva, para caracterizar y monitorizar de forma fiable el estado hídrico del viñedo y poder ayudar a la toma de decisiones de riego en viticultura., Este trabajo ha recibido financiación de la Comisión Europea, a través del proyecto VineRobot (grant nº: 610953)., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

VineRobot: A new robot for vineyard monitoring using non-invasive sensing technologies

  • Tardáguila, Javier
  • Blasco, Julián
  • Diago, Maria P.
Trabajo presentado en el International Cool Climate Wine Symposium (ICCWS), celebrado en Brighton del 26 al 28 de mayo de 2016.-- Tardáguila, Javier et al., The VineRobot project has received funding from the European Union’s Seventh Programme for research, technological development and demonstra?on under Grant Agreement No 610953., Peer Reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Future opportunities of proximal near infrared spectroscopy approaches to determine the variability of vineyard water status

  • Diago, Maria P.
  • Bellincontro, A.
  • Scheidweiler, M.
  • Tardáguila, Javier
  • Tittmann, S.
  • Stoll, Manfred
[Background and Aims] Non‐destructive, reliable, fast and automated plant‐based methods for the assessment of the water status of a grapevine are necessary to design irrigation strategies. The goal of this work was to test the capability of near infrared (NIR) spectroscopy using a vehicle‐mounted and remote NIR sensor without plant contact (contactless) to assess the water status of grapevines in the vineyard. [Methods and Results] An NIR spectrometer (1100–2100 nm) mounted on an all‐terrain vehicle was used to acquire spectra (contactless, in stop‐and‐go mode) from leaves of water‐stressed and non‐stressed vines of Riesling at two timings during the season. Calibration and cross‐validation models yielded R2c = 0.95 and R2cv = 0.88 for the estimation of the stomatal conductance measured in the same grapevines. [Conclusions] The study demonstrates that NIR spectroscopy may become a potential tool for on‐the‐go assessment of proximal plant water status, although further research will be required for full confirmation. [Significance of the Study] The NIR technology tested, capable of being installed on vineyard machinery, paves the way to collect data on plant water status at high spatial and temporal resolution to assist in irrigation scheduling., The work leading to these results has received funding from the European Union under grant agreement no. 610953 (VINEROBOT project). Dr Maria P. Diago was funded by the Spanish Ministry of Economy, Industry and Competitiveness (MINECO) with a Ramon y Cajal grant RYC‐2015‐18429., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

In field quantification and discrimination of different vineyard water regimes by on-the-go NIR spectroscopy

  • Fernández-Novales, Juan
  • Tardáguila, Javier
  • Gutiérrez, Salvador
  • Marañón Grandes, Miguel
  • Diago, Maria P.
Precise and rapid methods to assess plant water status are needed in agriculture. The goal of this work was to evaluate the capability of a new plant-based method based on proximal near-infrared (NIR) spectroscopy acquired on-the-go from a moving vehicle to quantify and discriminate different water regimes in a commercial vineyard. Proximal on-the-go NIR spectroscopy (1100–2100 nm) was acquired at solar noon on five days from veraison (onset of ripening) to harvest 2015 in a commercial Tempranillo vineyard. Spectral measurements were taken at ∼0.30 m from the canopy, on both canopy sides, from a vehicle moving at 5 km h−1. Measurements of midday stem water potential (Ψs) and leaf stomatal conductance (gs) were simultaneously acquired to be used as reference indicators of plant water status. Partial least squares (PLS) was used to build calibration, cross validation and predictive models for Ψs and gs. The determination coefficients of prediction (R2p) were above 0.86 for Ψs and above 0.66 for gs, while the root mean square errors of prediction (RMSEP) were less than 0.18 MPa and 93.7 mmol [H2O] m−2 s−1, respectively. PLS-Discriminant Analysis (PLS-DA) was applied to classify the data into three different water regimes, according to Ψs or gs. The average correctly classified percentage was greater than 72% for Ψs and gs. This discriminant capability, together with the large number of measurements that the on-the-go NIR spectroscopy can provide, enables the quantification and mapping of the variability of a vineyard water status and may help to define precise irrigation strategies in viticulture., his work has received funding from the Spanish Ministry of Economy and Competitiveness (MINECO) under the INNGRAPE project (RTC-2014-3058-2). The work leading to these results has received funding from the European Union under grant agreement n°610953 (VINEROBOT project). Salvador Gutiérrez would like to acknowledge the research founding FPI grant 299/2016 by Universidad de La Rioja, Gobierno de La Rioja. Maria P. Diago is funded by the Spanish Ministry of Economy, Industry and Competitiveness (MINECO) with a Ramon y Cajal grant RYC-2015-18429., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Automated early yield prediction in vineyards from on-the-go image acquisition

  • Aquino, Arturo
  • Millán Prior, Borja
  • Diago, Maria P.
  • Tardáguila, Javier
Early grapevine yield assessment provides information to viticulturists to help taking management decisions to achieve the desired grape quality and yield amount. In previous works, image analysis has been explored to this effect, but with systems performing either manually, on a single variety or close to harvest-time, when there are few rectifiable agronomic aspects. This study presents a solution based on image analysis for the non-invasive and in-field yield prediction in vines of several varieties, at phenological stages previous to veraison, around 100 days from harvest. To this end, an all-terrain vehicle (ATV) was modified with equipment to autonomously capture images of 30 vine segments of five different varieties at night-time. The images were analysed with a new image analysis algorithm based on mathematical morphology and pixel classification, which yielded overall average Recall and Precision values of 0.8764 and 0.9582, respectively. Finally, a model was calibrated to produce yield predictions from the number of detected berries in images with a Root-Mean-Square-Error per vine of 0.16 kg. This accuracy makes the proposed methodology ideal for early yield prediction as a very helpful tool for the grape and wine industry., The authors want to acknowledge the European Union for funding the VineRobot project within the Seventh Programme for research, technological development and demonstration (Grant Agreement No 610953). Thanks also to the Agencia de Desarrollo Económico de La Rioja (ADER) for funding the VINETICS project (2012-I-IDD-0009). Borja Millán would especially like to acknowledge the research founding FPI grant 536/2014 by the University of La Rioja. Dr. Maria P. Diago is funded by the Spanish Ministry of Economy and Competitiveness (MINECO) with a Ramon y Cajal grant RYC-2015-18429., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Assessment of amino acids and total soluble solids in intact grape berries using contactless Vis and NIR spectroscopy during ripening

  • Fernández-Novales, Juan
  • Garde-Cerdán, Teresa
  • Tardáguila, Javier
  • Gutiérrez-Gamboa, Gastón
  • Pérez-Álvarez, Eva Pilar
The amino acid concentration assessment along grape ripening would provide valuable information regarding harvest scheduling, wine aroma potential and must nitrogen supplement addition. In this work the use of Visible (Vis) and near-infrared (NIR) spectroscopy to estimate the grape amino acid content along maturation on intact berries was investigated. Spectral data on two ranges (570–1000 and 1100–2100 nm) were acquired contactless from intact Grenache berries. A total of 22 free amino acids in 128 grape clusters were quantified by HPLC. Partial least squares was used to build calibration, cross validation and prediction models. The best performances (R2P ~ 0.60) were found for asparagine (SEP: 0.45 mg N/l), tyrosine (SEP: 0.33 mg N/l) and proline (SEP: 17.5 mg N/l) in the 570–1000 nm range, and for lysine (SEP: 0.44 mg N/l), tyrosine (SEP: 0.26 mg N/l), and proline (SEP: 15.54 mg N/l) in the 1100–2100 nm range. Remarkable models (R2P~0.90, SEP~1.60 ºBrix, and RPD~3.79) were built for total soluble solids in both spectral ranges. Contactless, non-destructive spectroscopy could be an alternative to provide information about grape amino acids composition., This work has received funding from the Spanish Ministry of Economy and Competitiveness (MINECO) under the INNGRAPE project (RTC-2014-3058-2). The work leading to these results has received funding from the European Union under grant agreement no 610953 (VINEROBOT project)., Peer reviewed