Heterogeneous Autonomous Robotic System in Viticulture and Mariculture: Vehicles Development and Systems Integration

Kapetanović, Nadir; Goričanec, Jurica; Vatavuk, Ivo; Hrabar, Ivan; Stuhne, Dario; Vasiljević, Goran; Kovačić, Zdenko; Mišković, Nikola; Antolović, Nenad; Anić, Marina; Kozina, Bernard

doi:10.3390/s22082961

Cited by 10 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, viticulture is a major actor in the Greek production plan, aligning with the EU policies for quality over quantity products. The introduction of autonomous robots has demonstrated promising potential [59], and Greek viticulture is moving in this direction. The assimilation of knowledge and innovative technologies should formulate the cornerstone of autonomous multipurpose robotic operations in viticulture [60]; therefore, the economic performance of an innovative system as such is a novelty presented by the current study.…”

Section: Discussionmentioning

confidence: 99%

Assessing the Economic Performance of Multipurpose Collaborative Robots toward Skillful and Sustainable Viticultural Practices

et al. 2023

View full text Add to dashboard Cite

The increased cost of labor in modern viticulture stemming from the nature of operations that require physical strength and precision, coupled with labor shortages, poses a significant constraint in facilitating and scheduling seasonal activities. Therefore, autonomous collaborative robots present a potential solution for achieving sustainable development objectives and decreasing operational expenditures in agricultural operations. The current paper presents an economic assessment of collaborative robots (or cobots for short) in comparison to conventional labor for four different cultivars in Greece in a lifecycle costing methodological framework. The selected cultivars are Asyrtiko, Cabernet Sauvignon, Merlot and Tempranillo, which are cultivated by two private wineries in the area of interest. All the relevant expenses of their annual production were distributed to agricultural operations, and eight scenarios were developed to compare conventional and cobot practices. The results indicate the great potential of cobots regarding specific viticultural operations such as weed control, pruning, herbiciding and topping. The adoption of cobots in these operations has the potential to contribute to sustainable agriculture by reducing labor costs and addressing labor shortages, while also increasing the efficiency and precision of these tasks. Nevertheless, the defoliation and tying operations appeared to be inefficient in most cases in comparison to conventional labor practices. Overall, the annual equivalent costs could be reduced by up to 11.53% using cobots, even though the projected lifetime of the cobots plays a significant role in the cost-effectiveness of autonomous robotic labor in viticulture. In conclusion, cobots could be instrumental in the Greek viticulture, integrating innovation and high-quality products toward sustainable agricultural development.

show abstract

Section: Discussionmentioning

confidence: 99%

Assessing the Economic Performance of Multipurpose Collaborative Robots toward Skillful and Sustainable Viticultural Practices

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A custom-made aluminum catamaran named Korkyra was developed to function as a versatile remote-controlled or autonomous surface vehicle, as shown in Figure 2. Detailed information concerning the development of the catamaran can be found in [7,12]. This specially designed catamaran boasts several key features, one of which is a landing platform dedicated to accommodating a lightweight drone for aerial operations [13].…”

Section: Asv Korkyramentioning

confidence: 99%

Autonomous Visual Fish Pen Inspections for Estimating the State of Biofouling Buildup Using ROV

Fabijanić,

Kapetanović,

Mišković

2023

JMSE

Self Cite

View full text Add to dashboard Cite

The process of fish cage inspections, which is a necessary maintenance task at any fish farm, be it small-scale or industrial, is a task that has the potential to be fully automated. Replacing trained divers who perform regular inspections with autonomous marine vehicles would lower the costs of manpower and remove the risks associated with humans performing underwater inspections. Achieving such a level of autonomy implies developing an image processing algorithm that is capable of estimating the state of biofouling buildup. The aim of this work is to propose a complete solution for automating the said inspection process; from developing an autonomous control algorithm for an ROV, to automatically segmenting images of fish cages, and accurately estimating the state of biofouling. The first part is achieved by modifying a commercially available ROV with an acoustic SBL positioning system and developing a closed-loop control system. The second part is realized by implementing a proposed biofouling estimation framework, which relies on AI to perform image segmentation, and by processing images using established computer vision methods to obtain a rough estimate of the distance of the ROV from the fish cage. This also involved developing a labeling tool in order to create a dataset of images for the neural network performing the semantic segmentation to be trained on. The experimental results show the viability of using an ROV fitted with an acoustic transponder for autonomous missions, and demonstrate the biofouling estimation framework’s ability to provide accurate assessments, alongside satisfactory distance estimation capabilities. In conclusion, the achieved biofouling estimation accuracy showcases clear potential for use in the aquaculture industry.

show abstract

“…[1] aims to develop an autonomous robot for the care of vineyards, equipped with tools that allow it to perform activities such as suckering, spraying, and monitoring. This robot is designed to make work easier in small and medium-sized vineyards in order to solve the problem of tedious and often dangerous manual labor [2]. Extensive work has already been carried out in the field of object detection in the vineyard for robot localization, autonomous task execution [3], and navigation [4].…”

Section: Introductionmentioning

confidence: 99%

Generating a Dataset for Semantic Segmentation of Vine Trunks in Vineyards Using Semi-Supervised Learning and Object Detection

Slaviček,

Hrabar,

Kovačić

2024

Robotics

Self Cite

View full text Add to dashboard Cite

This article describes an experimentally tested approach using semi-supervised learning for generating new datasets for semantic segmentation of vine trunks with very little human-annotated data, resulting in significant savings in time and resources. The creation of such datasets is a crucial step towards the development of autonomous robots for vineyard maintenance. In order for a mobile robot platform to perform a vineyard maintenance task, such as suckering, a semantically segmented view of the vine trunks is required. The robot must recognize the shape and position of the vine trunks and adapt its movements and actions accordingly. Starting with vine trunk recognition and ending with semi-supervised training for semantic segmentation, we have shown that the need for human annotation, which is usually a time-consuming and expensive process, can be significantly reduced if a dataset for object (vine trunk) detection is available. In this study, we generated about 35,000 images with semantic segmentation of vine trunks using only 300 images annotated by a human. This method eliminates about 99% of the time that would be required to manually annotate the entire dataset. Based on the evaluated dataset, we compared different semantic segmentation model architectures to determine the most suitable one for applications with mobile robots. A balance between accuracy, speed, and memory requirements was determined. The model with the best balance achieved a validation accuracy of 81% and a processing time of only 5 ms. The results of this work, obtained during experiments in a vineyard on karst, show the potential of intelligent annotation of data, reducing the time required for labeling and thus paving the way for further innovations in machine learning.

show abstract

Heterogeneous Autonomous Robotic System in Viticulture and Mariculture: Vehicles Development and Systems Integration

Cited by 10 publications

References 43 publications

Assessing the Economic Performance of Multipurpose Collaborative Robots toward Skillful and Sustainable Viticultural Practices

Assessing the Economic Performance of Multipurpose Collaborative Robots toward Skillful and Sustainable Viticultural Practices

Autonomous Visual Fish Pen Inspections for Estimating the State of Biofouling Buildup Using ROV

Generating a Dataset for Semantic Segmentation of Vine Trunks in Vineyards Using Semi-Supervised Learning and Object Detection

Contact Info

Product

Resources

About