Search

Agricultural robotics is a complex, challenging, and exciting research topic nowadays. However, orchard environments present harsh conditions for robotics operability, such as terrain irregularities, illumination, and inaccuracies in GPS signals. To overcome these challenges, reliable landmarks must be extracted from the environment. This study addresses the challenge of accurate, low-cost, and efficient landmark identification in orchards to enable robot row-following. First, deep learning, integrated with depth information, is used for real-time trunk detection and location. The in-house dataset used to train the models includes a total of 2453 manually annotated trunks. The results show that the trunk detection achieves an overall mAP of 81.6%, an inference time of 60 ms, and a location accuracy error of 9 mm at 2.8 m. Secondly, the environmental features obtained in the first step are fed into the DWA. The DWA performs reactive obstacle avoidance while attempting to reach the row-end destination. The final solution considers the limitations of the robot’s kinematics and dynamics, enabling it to maintain the row path and avoid obstacles. Simulations and field tests demonstrated that even with a certain initial deviation, the robot could automatically adjust its position and drive through the rows in the real orchard.

Agricultural robotics is a complex, challenging, and exciting research topic nowadays. However, orchard environments present harsh conditions for robotics operability, such as terrain irregularities, illumination, and inaccuracies in GPS signals. To overcome these challenges, reliable landmarks must be extracted from the environment. This study addresses the challenge of accurate, low-cost, and efficient landmark identification in orchards to enable robot row-following. First, deep learning, integrated with depth information, is used for real-time trunk detection and location. The in-house dataset used to train the models includes a total of 2453 manually annotated trunks. The results show that the trunk detection achieves an overall mAP of 81.6%, an inference time of 60 ms, and a location accuracy error of 9 mm at 2.8 m. Secondly, the environmental features obtained in the first step are fed into the DWA. The DWA performs reactive obstacle avoidance while attempting to reach the row-end destination. The final solution considers the limitations of the robot's kinematics and dynamics, enabling it to maintain the row path and avoid obstacles. Simulations and field tests demonstrated that even with a certain initial deviation, the robot could automatically adjust its position and drive through the rows in the real orchard. [ABSTRACT FROM AUTHOR]

The high tillage resistance of agricultural soil-engaging tools (TASTs) in farmland operations (e.g., tillage, sowing, crop management, and harvesting) increases fuel consumption and harmful gas emissions, which negatively affect the development of sustainable agriculture. Biomimetic methods are promising and effective technologies for reducing the TASTs and have been developed in the past few years. This review comprehensively summarizes the typical agricultural soil-engaging tools (ASETs) and their characteristics and presents existing biomimetic methods for decreasing TASTs. The introduction of TAST reduction was performed on aspects of tillage, sowing, crop management, and harvesting. The internal mechanisms and possible limitations of current biomimetic methods for various ASETs were investigated. The tillage resistance reduction rates of ASETs, as affected by various biomimetic methods, were quantitatively compared under different soil conditions with statistical analyses. Additionally, three future research directions were recommended in the review to further reduce TASTs and encourage the development of sustainable agriculture. [ABSTRACT FROM AUTHOR]

The application of robotics has great implications for future food security, sustainable agricultural development, improving resource efficiency, reducing chemical pesticide use, reducing manual labor, and maximizing field output. Aiming at the problems of high labor intensity and labor shortage in the fields of pesticide application, weeding, and field information collection, a multifunctional and electric field management robot platform is designed, which has four switching steering modes (Ackermann steering, four-wheel steering, crab steering, and zero-radius steering), and its wheel-track can be automatically adjusted. Commonly used spraying booms, weeders, crop information collectors, and other devices can be easily installed on the robot platform. A multi-sensor integrated navigation system including a satellite positioning system, an RGB camera, and a multi-line lidar is designed to realize the unmanned driving of the robot platform in a complex field environment. Field tests have shown that the robot can follow the set route, and tests under simulated conditions have indicated that it can also dynamically correct paths based on crop rows by using a visual system. Results from multiple trials showed that the trajectory tracking accuracy meets the requirements of various field management operations. [ABSTRACT FROM AUTHOR]

This study introduces two methods for crop identification and growth stage determination, focused primarily on enabling mobile robot navigation. These methods include a two-phase approach involving separate models for crop and growth stage identification and a one-phase method employing a single model capable of handling all crops and growth stages. The methods were validated with maize and sugar beet field images, demonstrating the effectiveness of both approaches. The one-phase approach proved to be advantageous for scenarios with a limited variety of crops, allowing, with a single model, to recognize both the type and growth state of the crop and showed an overall Mean Average Precision (mAP) of about 67.50%. Moreover, the two-phase method recognized the crop type first, achieving an overall mAP of about 74.2%, with maize detection performing exceptionally well at 77.6%. However, when it came to identifying the specific maize growth state, the mAP was only able to reach 61.3% due to some difficulties arising when accurately categorizing maize growth stages with six and eight leaves. On the other hand, the two-phase approach has been proven to be more flexible and scalable, making it a better choice for systems accommodating a wide range of crops. [ABSTRACT FROM AUTHOR]

Successive years of straw mulching and returning straw to the fields in Northeast China have made strip-tillage necessary, and reasonable strip-tillage operations can create conditions for crop growth. However, there are limited research studies on the related equipment applicable to this area. In this paper, an automatic control strip-tillage machine is designed. According to the conventional planting pattern of maize in this region, the operative processes of the machine were determined, and a suitable strip seedbed structure could then be constructed under straw mulching conditions. The type of coulters and the structural parameters of the V-type soil-crushing wheel were determined through theoretical analysis. Based on the air spring and electric linear actuator, the plowing depth control system and the straw width control system were developed, respectively, so as to improve the stability of the machine operation. Field tests showed that when the forward speed, tillage depth, and theoretical width were 6–12 km/h, 6–12 cm, and 18–24 cm, respectively, the straw clearing rate, soil crushing rate, and tillage depth and breadth stability were higher than 90%, and the soil flatness was less than 2 cm. All the indexes satisfied the agronomic and technological requirements of corn cultivation. The results of this study can provide equipment and technical support for the further popularization of conservation tillage technology. [ABSTRACT FROM AUTHOR]

To realize autonomous navigation and intelligent management in orchards, vehicles require real-time positioning and globally consistent mapping of surroundings with sufficient information. However, the unstructured and unstable characteristics of orchards present challenges for accurate and stable localization and mapping. This study proposes a framework fusing LiDAR, visual, and inertial data by using the extended Kalman filter (EKF) to achieve real-time localization and colorful LiDAR point-cloud mapping in orchards. First, the multi-sensor data were integrated into a loosely-coupled framework based on the EKF to improve the pose estimation, with the pose estimation from LiDAR and gyroscope acting as the predictions, while that from visual-inertial odometry acting as the observations. Then, the Loam_Livox algorithm was enhanced by incorporating color from the image into the LiDAR point cloud, enabling the real-time construction of a three-dimensional colorful map of the orchard. The method demonstrates a high accuracy for localization in different motion trajectories (average RMSE: 0.3436) and different scenarios (average RMSE: 0.1230) and clear and efficient construction of three-dimensional colorful mapping, taking only 75.01 ms in localization and mapping for a frame of LiDAR point cloud. This indicates the proposed method has a great potential for the autonomous navigation of agricultural vehicles. [ABSTRACT FROM AUTHOR]

Crop row detection is one of the foundational and pivotal technologies of agricultural robots and autonomous vehicles for navigation, guidance, path planning, and automated farming in row crop fields. However, due to a complex and dynamic agricultural environment, crop row detection remains a challenging task. The surrounding background, such as weeds, trees, and stones, can interfere with crop appearance and increase the difficulty of detection. The detection accuracy of crop rows is also impacted by different growth stages, environmental conditions, curves, and occlusion. Therefore, appropriate sensors and multiple adaptable models are required to achieve high-precision crop row detection. This paper presents a comprehensive review of the methods and applications related to crop row detection for agricultural machinery navigation. Particular attention has been paid to the sensors and systems used for crop row detection to improve their perception and detection capabilities. The advantages and disadvantages of current mainstream crop row detection methods, including various traditional methods and deep learning frameworks, are also discussed and summarized. Additionally, the applications for different crop row detection tasks, including irrigation, harvesting, weeding, and spraying, in various agricultural scenarios, such as dryland, the paddy field, orchard, and greenhouse, are reported. [ABSTRACT FROM AUTHOR]

A cost-effective harvesting method and equipment for small-scale farms is essential to ensure the viability and sustainability of their operations. This study aims to retrofit and test a pull-type combine harvester for effective and efficient operations in small grains. A 1960s-era functional combine harvester was retrofitted with a stripper header rotor in place of the sickle bar cutting system to increase the harvesting capacity. Preliminary field testing found that the original header auger and feeder house could not handle the changed crop composition at an increased capacity and did not properly convey the grain from the auger to the feeder house and onto the threshing system. Therefore, redesign modifications were conducted for the auger and feeder house to help increase the efficiency and capacity required to use the stripper header. Various design concepts were proposed, analyzed, and prototyped in this study. The machine performance of the material-conveying efficiency of the wheat-material-other-than-grain mixture was evaluated at various material throughput rates. The results showed that the auger shim and feeder house paddle redesign increased the efficiency from 80.68% to 98.56%, as compared to the original machine configuration. The cost-effective and high-performance pull-type combine harvester proposed in this study has a high potential in solving the bottleneck problem of local production of small grains by small-scale farming operations. [ABSTRACT FROM AUTHOR]

In digital farming, the use of technology to increase agricultural production through automated tasks has recently integrated the development of AgBots for more reliable data collection using autonomous navigation. These AgBots are equipped with various sensors such as GNSS, cameras, and LiDAR, but these sensors can be prone to limitations such as low accuracy for under-canopy navigation with GNSS, sensitivity to outdoor lighting and platform vibration with cameras, and LiDAR occlusion issues. In order to address these limitations and ensure robust autonomous navigation, this paper presents a sensor selection methodology based on the identification of environmental conditions using sensor data. Through the extraction of features from GNSS, images, and point clouds, we are able to determine the feasibility of using each sensor and create a selection vector indicating its viability. Our results demonstrate that the proposed methodology effectively selects between the use of cameras or LiDAR within crops and GNSS outside of crops, at least 87% of the time. The main problem found is that, in the transition from inside to outside and from outside to inside the crop, GNSS features take 20 s to adapt. We compare a variety of classification algorithms in terms of performance and computational cost and the results show that our method has higher performance and lower computational cost. Overall, this methodology allows for the low-cost selection of the most suitable sensor for a given agricultural environment. [ABSTRACT FROM AUTHOR]

Autonomous navigation in greenhouses requires agricultural robots to localize and generate a globally consistent map of surroundings in real-time. However, accurate and robust localization and mapping are still challenging for agricultural robots due to the unstructured, dynamic and GPS-denied environmental conditions. In this study, a state-of-the-art real-time localization and mapping system was presented to achieve precise pose estimation and dense three-dimensional (3D) point cloud mapping in complex greenhouses by utilizing multi-sensor fusion and Visual–IMU–Wheel odometry. In this method, measurements from wheel odometry, an inertial measurement unit (IMU) and a tightly coupled visual–inertial odometry (VIO) are integrated into a loosely coupled framework based on the Extended Kalman Filter (EKF) to obtain a more accurate state estimation of the robot. In the multi-sensor fusion algorithm, the pose estimations from the wheel odometry and IMU are treated as predictions and the localization results from VIO are used as observations to update the state vector. Simultaneously, the dense 3D map of the greenhouse is reconstructed in real-time by employing the modified ORB-SLAM2. The performance of the proposed system was evaluated in modern standard solar greenhouses with harsh environmental conditions. Taking advantage of measurements from individual sensors, our method is robust enough to cope with various challenges, as shown by extensive experiments conducted in the greenhouses and outdoor campus environment. Additionally, the results show that our proposed framework can improve the localization accuracy of the visual–inertial odometry, demonstrating the satisfactory capability of the proposed approach and highlighting its promising applications in autonomous navigation of agricultural robots. [ABSTRACT FROM AUTHOR]

Digital farming approach merges new technologies and sensor data to optimize the quality of crop monitoring in agriculture. The successful fusion of technology and data is highly dependent on the parameter collection, the modeling adoption, and the technology integration being accurately implemented according to the specified needs of the farm. This fusion technique has not yet been widely adopted due to several challenges; however, our study here reviews current methods and applications for fusing technologies and data. First, the study highlights different sensors that can be merged with other systems to develop fusion methods, such as optical, thermal infrared, multispectral, hyperspectral, light detection and ranging and radar. Second, the data fusion using the internet of things is reviewed. Third, the study shows different platforms that can be used as a source for the fusion of technologies, such as ground-based (tractors and robots), space-borne (satellites) and aerial (unmanned aerial vehicles) monitoring platforms. Finally, the study presents data fusion methods for site-specific crop parameter monitoring, such as nitrogen, chlorophyll, leaf area index, and aboveground biomass, and shows how the fusion of technologies and data can improve the monitoring of these parameters. The study further reveals limitations of the previous technologies and provides recommendations on how to improve their fusion with the best available sensors. The study reveals that among different data fusion methods, sensors and technologies, the airborne and terrestrial LiDAR fusion method for crop, canopy, and ground may be considered as a futuristic easy-to-use and low-cost solution to enhance the site-specific monitoring of crop parameters. [ABSTRACT FROM AUTHOR]

One of the main challenges for the implementation of artificial intelligence (AI) in agriculture includes the low replicability and the corresponding difficulty in systematic data gathering, as no two fields are exactly alike. Therefore, the comparison of several pilot experiments in different fields, weather conditions and farming techniques enhances the collective knowledge. Thus, this work provides a summary of the most recent research activities in the form of research projects implemented and validated by the authors in several European countries, with the objective of presenting the already achieved results, the current investigations and the still open technical challenges. As an overall conclusion, it can be mentioned that even though in their primary stages in some cases, AI technologies improve decision support at farm level, monitoring conditions and optimizing production to allow farmers to apply the optimal number of inputs for each crop, thereby boosting yields and reducing water use and greenhouse gas emissions. Future extensions of this work will include new concepts based on autonomous and intelligent robots for plant and soil sample retrieval, and effective livestock management. [ABSTRACT FROM AUTHOR]

Precision agriculture is a crucial way to achieve greater yields by utilizing the natural deposits in a diverse environment. The yield of a crop may vary from year to year depending on the variations in climate, soil parameters and fertilizers used. Automation in the agricultural industry moderates the usage of resources and can increase the quality of food in the post-pandemic world. Agricultural robots have been developed for crop seeding, monitoring, weed control, pest management and harvesting. Physical counting of fruitlets, flowers or fruits at various phases of growth is labour intensive as well as an expensive procedure for crop yield estimation. Remote sensing technologies offer accuracy and reliability in crop yield prediction and estimation. The automation in image analysis with computer vision and deep learning models provides precise field and yield maps. In this review, it has been observed that the application of deep learning techniques has provided a better accuracy for smart farming. The crops taken for the study are fruits such as grapes, apples, citrus, tomatoes and vegetables such as sugarcane, corn, soybean, cucumber, maize, wheat. The research works which are carried out in this research paper are available as products for applications such as robot harvesting, weed detection and pest infestation. The methods which made use of conventional deep learning techniques have provided an average accuracy of 92.51%. This paper elucidates the diverse automation approaches for crop yield detection techniques with virtual analysis and classifier approaches. Technical hitches in the deep learning techniques have progressed with limitations and future investigations are also surveyed. This work highlights the machine vision and deep learning models which need to be explored for improving automated precision farming expressly during this pandemic. [ABSTRACT FROM AUTHOR]

Halophytes are capable of coping with excessive NaCl in their tissues, although some species may differ in their degree of salt tolerance. In addition, it is not clear whether they can tolerate other confounding factors and impurities associated with non-conventional waters. The experiment was performed in a greenhouse with Crithmum maritimum and Atriplex halimus plants, growing on soil and irrigated with two different water types: reclaimed wastewater (RWW) (EC: 0.8–1.2 dS m−1) and reverse osmosis brine (ROB) (EC: 4.7–7.9 dS m−1). Both species showed different physiological and nutritional responses, when they were irrigated with ROB. Atriplex plants reduced leaf water potential and maintained leaf turgor as consequence of an osmotic adjustment process. Atriplex showed higher intrinsic water use efficiency than Crithmum, regardless of the type of water used. In Crithmum, the water status and photosynthetic efficiency were similar in both treatments. Crithmum presented a higher leaf accumulation of B and Ca ions, while Atriplex a higher amount of K, Mg, Na and Zn. Crithmum plants irrigated with ROB presented higher concentrations of 1-aminocyclopropane-1-carboxylic acid and trans-zeatin-glucoside, whereas abscisic acid concentration was lower. Atriplex showed a lower concentration of trans-zeatin-riboside and scopoletin. The characteristics associated to water irrigation did not influence negatively the development of any of these species, which confirms the use of brine as an alternative to irrigate them with conventional waters. [ABSTRACT FROM AUTHOR]

Deep learning and machine learning (ML) technologies have been implemented in various applications, and various agriculture technologies are being developed based on image-based object recognition technology. We propose an orchard environment free space recognition technology suitable for developing small-scale agricultural unmanned ground vehicle (UGV) autonomous mobile equipment using a low-cost lightweight processor. We designed an algorithm to minimize the amount of input data to be processed by the ML algorithm through low-resolution grayscale images and image binarization. In addition, we propose an ML feature extraction method based on binary pixel quantification that can be applied to an ML classifier to detect free space for autonomous movement of UGVs from binary images. Here, the ML feature is extracted by detecting the local-lowest points in segments of a binarized image and by defining 33 variables, including local-lowest points, to detect the bottom of a tree trunk. We trained six ML models to select a suitable ML model for trunk bottom detection among various ML models, and we analyzed and compared the performance of the trained models. The ensemble model demonstrated the best performance, and a test was performed using this ML model to detect apple tree trunks from 100 new images. Experimental results indicate that it is possible to recognize free space in an apple orchard environment by learning using approximately 100 low-resolution grayscale images. [ABSTRACT FROM AUTHOR]

A set of thirty-six wheat cultivars were grown for two consecutive years under low and high nitrogen conditions. The interactions of cultivars with different environmental factors were shown to be highly significant for most of the studied traits, suggesting the presence of wider genetic variability which may be utilized for the genetic improvement of desired trait(s). Three cultivars, i.e., RAJ 4037, DBW 39 and GW 322, were selected based on three selection indices, i.e., tolerance index (TOL), stress susceptibility index (SSI), and yield stability index (YSI), while two cultivars, HD 2967 and MACS 6478, were selected based on all four selection indices which were common in both of the study years. According to Kendall's concordance coefficient, the consistency of geometric mean productivity (GMP) was found to be highest (0.778), followed by YSI (0.556), SSI (0.472), and TOL (0.200). Due to the high consistency of GMP followed by YSI and SSI, the three selection indices could be utilized as a selection tool in the identification of high-yielding genotypes under low nitrogen conditions. The GMP and YSI selection indices had a positive and significant correlation with grain yield, whereas TOL and SSI exhibited a significant but negative correlation with grain yield under both high and low nitrogen conditions in both years. The common tolerant genotypes identified through different selection indices could be utilized as potential donors in active breeding programs to incorporate the low nitrogen tolerant genes to develop high-yielding wheat varieties for low nitrogen conditions. The study also helps in understanding the physiological basis of tolerance in high-yielding wheat genotypes under low nitrogen conditions. [ABSTRACT FROM AUTHOR]

Increasing the rate of genetic gain for dry matter (DM) yield in perennial ryegrass (Lolium perenne L.), which is a key source of nutrition for ruminants in temperate environments, is an important goal for breeders. Genomic selection (GS) is a strategy used to improve genetic gain by using molecular marker information to predict breeding values in selection candidates. An empirical assessment of GS for herbage accumulation (HA; proxy for DM yield) and days-to-heading (DTH) was completed by using existing genomic prediction models to conduct one cycle of divergent GS in four selection populations (Pop I G1 and G3; Pop III G1 and G3), for each trait. G1 populations were the offspring of the training set and G3 populations were two generations further on from that. The HA of the High GEBV selection group (SG) progenies, averaged across all four populations, was 28% higher (p < 0.05) than Low GEBV SGs when assessed in the target environment, while it did not differ significantly in a second environment. Divergence was greater in Pop I (43%–65%) than Pop III (10%–16%) and the selection response was higher in G1 than in G3. Divergent GS for DTH also produced significant (p < 0.05) differences between High and Low GEBV SGs in G1 populations (+6.3 to 9.1 days; 31%–61%) and smaller, non-significant (p > 0.05) responses in G3. This study shows that genomic prediction models, trained from a small, composite reference set, can be used to improve traits with contrasting genetic architectures in perennial ryegrass. The results highlight the importance of target environment selection for training models, as well as the influence of relatedness between the training set and selection populations. [ABSTRACT FROM AUTHOR]

Field weeds identification is challenging for precision spraying, i.e., the automation identification of the weeds from the crops. For rapidly obtaining weed distribution in field, this study developed a weed density detection method based on absolute feature corner point (AFCP) algorithm for the first time. For optimizing the AFCP algorithm, image preprocessing was firstly performed through a sub-module processing capable of segmenting and optimizing the field images. The AFCP algorithm improved Harris corner to extract corners of single crop and weed and then sub-absolute corner classifier as well as absolute corner classifier were proposed for absolute corners detection of crop rows. Then, the AFCP algorithm merged absolute corners to identify crop and weed position information. Meanwhile, the weed distribution was obtained based on two weed density parameters (weed pressure and cluster rate). At last, the AFCP algorithm was validated based on the images that were obtained using one typical digital camera mounted on the tractor in field. The results showed that the proposed weed detection method manifested well given its ability to process an image of 2748 × 576 pixels using 782 ms as well as its accuracy in identifying weeds reaching 90.3%. Such results indicated that the weed detection method based on AFCP algorithm met the requirements of practical weed management in field, including the real-time images computation processing and accuracy, which provided the theoretical base for the precision spraying operations. [ABSTRACT FROM AUTHOR]

Humic substances (HS) are important soil components playing pivotal roles in guaranteeing long-term soil fertility. In this study, the chemical and biological properties of HS extracted from earthworm coprolites collected in soils subjected to different fertilization inputs (no fertilization, NF; fertilization with farmyard manure, FM; mineral input, M; mixed inputs, FMM, half farmyard manure plus half mineral input) were investigated. Results indicated a relationship between fertilization input and composition, molecular complexity and apparent molecular weight distribution of HS produced by earthworms. Coprolites from FM and FMM soils were the most enriched in organic carbon (OC), and HS from coprolites of FM soil were the highest in humic carbon (HC). Also, soil amendment with manure increased carboxylate and aromatic groups in HS, and the fraction with a high degree of polycondensation, thus indicating a positive impact of manure on plant residues' degradation processes. These HS were the only to display hormone-like activity, which likely accounted for their most pronounced positive effects on plant growth and metabolism, including accumulation of chlorophylls, mineral nutrition, and activity of nitrogen assimilation enzymes, in oat (Avena sativa L.) plants growing in a soil-less system. We conclude that manure input favored the turnover of OC towards the humification process that led to the production of high-quality coprolites and HS with superior biological activity, and suggests that OC in coprolites and HC in HS from earthworms might be used as reliable indicators of soil fertility. [ABSTRACT FROM AUTHOR]