A robot to detect and control broad-leaved dock (Rumex obtusifolius L.) in grassland

A Review of Current and Historical Research Contributions to the Development of Ground Autonomous Vehicles for Agriculture

In this study, a comprehensive overview of the available autonomous ground platforms developed by universities and research groups that were specifically designed to handle agricultural tasks was performed. As cost reduction and safety improvements are two of the most critical aspects for farmers, the development of autonomous vehicles can be of major interest, especially for those applications that are lacking in terms of mechanization improvements. This review aimed to provide a literature evaluation of present and historical research contributions toward designing and prototyping agricultural ground unmanned vehicles. The review was motivated by the intent to disseminate to the scientific community the main features of the autonomous tractor named BOPS-1960, which was conceived in the 1960s at the Alma Mater Studiorum University of Bologna (UNIBO). Jointly, the main characteristics of the modern DEDALO unmanned ground vehicle (UGV) for orchard and vineyard operations that was designed recently were evaluated. The basic principles, technology and sensors used in the two UNIBO prototypes are described in detail, together with an analysis of UGVs for agriculture conceived in recent years by research centers all around the world.

Application-Specific Evaluation of a Weed-Detection Algorithm for Plant-Specific Spraying

Robotic plant-specific spraying can reduce herbicide usage in agriculture while minimizing labor costs and maximizing yield. Weed detection is a crucial step in automated weeding. Currently, weed detection algorithms are always evaluated at the image level, using conventional image metrics. However, these metrics do not consider the full pipeline connecting image acquisition to the site-specific operation of the spraying nozzles, which is vital for an accurate evaluation of the system. Therefore, we propose a novel application-specific image-evaluation method, which analyses the weed detections on the plant level and in the light of the spraying decision made by the robot. In this paper, a spraying robot is evaluated on three levels: (1) On image-level, using conventional image metrics, (2) on application-level, using our novel application-specific image-evaluation method, and (3) on field level, in which the weed-detection algorithm is implemented on an autonomous spraying robot and tested in the field. On image level, our detection system achieved a recall of 57% and a precision of 84%, which is a lower performance than detection systems reported in literature. However, integrated on an autonomous volunteer-potato sprayer-system we outperformed the state-of-the-art, effectively controlling 96% of the weeds while terminating only 3% of the crops. Using the application-level evaluation, an accurate indication of the field performance of the weed-detection algorithm prior to the field test was given and the type of errors produced by the spraying system was correctly predicted.

A field-tested robotic harvesting system for iceberg lettuce

Agriculture provides an unique opportunity for the development of robotic systems; robots must be developed which can operate in harsh conditions and in highly uncertain and unknown environments. One particular challenge is performing manipulation for autonomous robotic harvesting. This paper describes recent and current work to automate the harvesting of iceberg lettuce. Unlike many other produce, iceberg is challenging to harvest as the crop is easily damaged by handling and is very hard to detect visually. A platform called Vegebot has been developed to enable the iterative development and field testing of the solution, which comprises of a vision system, custom end effector and software. To address the harvesting challenges posed by iceberg lettuce a bespoke vision and learning system has been developed which uses two integrated convolutional neural networks to achieve classification and localization. A custom end effector has been developed to allow damage free harvesting. To allow this end effector to achieve repeatable and consistent harvesting, a control method using force feedback allows detection of the ground. The system has been tested in the field, with experimental evidence gained which demonstrates the success of the vision system to localize and classify the lettuce, and the full integrated system to harvest lettuce. This study demonstrates how existing state-of-the art vision approaches can be applied to agricultural robotics, and mechanical systems can be developed which leverage the environmental constraints imposed in such environments.

Variation in Phenolic Compounds Content and Antioxidant Activity of Different Plant Organs from Rumex crispus L. and Rumex obtusifolius L. at Different Growth Stages

The study investigated the accumulation of phenolic compounds and the antioxidant activity of extracts of various parts of R. crispus and R. obtusifolius, collected at the flowering stage and the fruiting stage. Half of the collected plants were divided into root, stem, leaves, and reproductive organs (inflorescence). The other half was used to study the vertical distribution of biologically active components and antioxidants throughout the plant. The samples were analyzed for total catechins content, total proanthocyanidins content, total phenolic content, and total antioxidant activity (1,1-diphenyl-2-picrylhydrazyl (DPPH), 2,2'azinobis(3)ethylbenzthiazoline-6-sulfonic acid (ABTS), and ferric reducing antioxidant power (FRAP) assays). All analyses were performed in four replicates. In general, a similar trend was observed in the distribution of phenolic compounds in the studied species. The maximum content of these secondary metabolites was noted in the reproductive organs, both in the flowering and fruiting period. Stems were characterized by a minimum content of the studied classes of substances. The antioxidant activity of the sorrels studied parts can be arranged in the following order: the generative part (flowers, seeds) > leaves > root > stem (for flowering and fruiting stages). It was found that parts of the root closer to the stem differed in higher activity.

A True-Color Sensor and Suitable Evaluation Algorithm for Plant Recognition

Plant-specific herbicide application requires sensor systems for plant recognition and differentiation. A literature review reveals a lack of sensor systems capable of recognizing small weeds in early stages of development (in the two- or four-leaf stage) and crop plants, of making spraying decisions in real time and, in addition, are that are inexpensive and ready for practical use in sprayers. The system described in this work is based on free cascadable and programmable true-color sensors for real-time recognition and identification of individual weed and crop plants. The application of this type of sensor is suitable for municipal areas and farmland with and without crops to perform the site-specific application of herbicides. Initially, databases with reflection properties of plants, natural and artificial backgrounds were created. Crop and weed plants should be recognized by the use of mathematical algorithms and decision models based on these data. They include the characteristic color spectrum, as well as the reflectance characteristics of unvegetated areas and areas with organic material. The CIE-Lab color-space was chosen for color matching because it contains information not only about coloration (a- and b-channel), but also about luminance (L-channel), thus increasing accuracy. Four different decision making algorithms based on different parameters are explained: (i) color similarity (ΔE); (ii) color similarity split in ΔL, Δa and Δb; (iii) a virtual channel 'd' and (iv) statistical distribution of the differences of reflection backgrounds and plants. Afterwards, the detection success of the recognition system is described. Furthermore, the minimum weed/plant coverage of the measuring spot was calculated by a mathematical model. Plants with a size of 1-5% of the spot can be recognized, and weeds in the two-leaf stage can be identified with a measuring spot size of 5 cm. By choosing a decision model previously, the detection quality can be increased. Depending on the characteristics of the background, different models are suitable. Finally, the results of field trials on municipal areas (with models of plants), winter wheat fields (with artificial plants) and grassland (with dock) are shown. In each experimental variant, objects and weeds could be recognized.

Ecologically sustainable weed management: How do we get from proof-of-concept to adoption?

Weed management is a critically important activity on both agricultural and non-agricultural lands, but it is faced with a daunting set of challenges: environmental damage caused by control practices, weed resistance to herbicides, accelerated rates of weed dispersal through global trade, and greater weed impacts due to changes in climate and land use. Broad-scale use of new approaches is needed if weed management is to be successful in the coming era. We examine three approaches likely to prove useful for addressing current and future challenges from weeds: diversifying weed management strategies with multiple complementary tactics, developing crop genotypes for enhanced weed suppression, and tailoring management strategies to better accommodate variability in weed spatial distributions. In all three cases, proof-of-concept has long been demonstrated and considerable scientific innovations have been made, but uptake by farmers and land managers has been extremely limited. Impediments to employing these and other ecologically based approaches include inadequate or inappropriate government policy instruments, a lack of market mechanisms, and a paucity of social infrastructure with which to influence learning, decision-making, and actions by farmers and land managers. We offer examples of how these impediments are being addressed in different parts of the world, but note that there is no clear formula for determining which sets of policies, market mechanisms, and educational activities will be effective in various locations. Implementing new approaches for weed management will require multidisciplinary teams comprised of scientists, engineers, economists, sociologists, educators, farmers, land managers, industry personnel, policy makers, and others willing to focus on weeds within whole farming systems and land management units.

Development and evaluation of a combined cultivator and band sprayer with a row-centering RTK-GPS guidance system

Typically, low-pressure sprayers are used to uniformly apply pre- and post-emergent herbicides to control weeds in crop rows. An innovative machine for weed control in inter-row and intra-row areas, with a unique combination of inter-row cultivation tooling and intra-row band spraying for six rows and an electro-hydraulic side-shift frame controlled by a GPS system, was developed and evaluated. Two weed management strategies were tested in the field trials: broadcast spraying (the conventional method) and band spraying with mechanical weed control using RTK-GPS (the experimental method). This approach enabled the comparison between treatments from the perspective of cost savings and efficacy in weed control for a sugar beet crop. During the 2010–2011 season, the herbicide application rate (112 L ha⁻¹) of the experimental method was approximately 50% of the conventional method, and thus a significant reduction in the operating costs of weed management was achieved. A comparison of the 0.2-trimmed means of weed population post-treatment showed that the treatments achieved similar weed control rates at each weed survey date. Sugar beet yields were similar with both methods (p = 0.92). The use of the experimental equipment is cost-effective on ≥20 ha of crops. These initial results show good potential for reducing herbicide application in the Spanish beet industry.