Computers and Electronics in Agriculture最新文献

{"title":"BEGV2-UNet: A method for automatic segmentation and calculation of backfat and eye muscle region in pigs","authors":"Wenzheng Liu ,&nbsp;Tonghai Liu ,&nbsp;Jinghan Cai ,&nbsp;Zhihan Li ,&nbsp;Xue Wang ,&nbsp;Rui Zhang ,&nbsp;Xiaoyue Seng","doi":"10.1016/j.compag.2025.110272","DOIUrl":"10.1016/j.compag.2025.110272","url":null,"abstract":"<div><div>Rapid and accurate measurements of eye muscle area and backfat thickness in breeding pigs is crucial for improving breeding traits. Within reasonable ranges, these traits significantly influence the number of piglets born, their birth weights, and survival rates. Traditional detection methods are time-consuming and heavily reliant on operational expertise. While B-mode ultrasound is widely used as a non-invasive tool for measuring backfat thickness and eye muscle area, its efficiency and precision are limited by dependence on the operator.</div><div>To address these issues, this study introduces the BEGV2-UNet model, an innovative UNet network based on reconstructing down-sampling and up-sampling paths, incorporating GhostModuleV2, and incorporating a large kernel attention mechanism to better capture the boundaries and positions of backfat and eye muscle regions. The model can be used to segment these regions in breeding pigs and improve the loss function for accelerate convergence while remedying the low precision caused by class imbalance. Using a dataset of ultrasound images, the BEGV2-UNet model achieved an MIoU of 96.18 % and MPA of 98.12 %, with model size reduced to 18.69 MB and strong inference accuracy. We calculated the backfat thickness and eye muscle area using the model to achieve R² values of 0.98 and 0.96, respectively.</div><div>This study highlights the significant advantages of BEGV2-UNet in terms of image segmentation accuracy and lightweight design.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110272"},"PeriodicalIF":7.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Agricultural large language model for standardized production of distinctive agricultural products","authors":"Wenlong Yi ,&nbsp;Li Zhang ,&nbsp;Sergey Kuzmin ,&nbsp;Igor Gerasimov ,&nbsp;Muhua Liu","doi":"10.1016/j.compag.2025.110218","DOIUrl":"10.1016/j.compag.2025.110218","url":null,"abstract":"<div><div>To address the diverse nature of specialty agricultural product standardization, its complex and cumbersome development process, and lengthy drafting cycles, while simultaneously tackling challenges such as outdated standardization documents and hallucinations caused by general large language models’ delayed access to agricultural domain information. This study constructs a multi-stage cascaded large language model based on a hybrid retrieval-augmented mechanism. The model comprises three core modules: (1) A multi-source retrieval augmentation module that achieves comprehensive external knowledge acquisition through vector retrieval, keyword retrieval, and knowledge graph retrieval branches; (2) A knowledge fusion module that filters redundant information using inverse ranking fusion and graph structure pruning methods to achieve precise injection of high-quality knowledge; (3) A domain adaptation module that enhances the model’s understanding of agricultural terminology through vertical domain fine-tuning. Experimental results show that in the standardization document summarization task, the model achieves chrF, BERTscore, and Gscore metrics of 34.85, 74.88, and 39.85, respectively, representing improvements of 59.52%, 35.28%, and 72.84% over the BART baseline model, and 58.54%, 24.25%, and 59.54% over the T5 model. This study enriches the theoretical foundation of large language models in agriculture and provides intelligent technical support for specialty agricultural product standardization development.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110218"},"PeriodicalIF":7.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of structure and soil parameters on the detection performance of a contact soil surface height detection device","authors":"Haitao Peng ,&nbsp;Hanping Mao ,&nbsp;Mohamed Farag Taha ,&nbsp;Luhua Han ,&nbsp;Zhiyu Zuo ,&nbsp;Guoxin Ma","doi":"10.1016/j.compag.2025.110242","DOIUrl":"10.1016/j.compag.2025.110242","url":null,"abstract":"<div><div>The complex environment of the soil surface in the field poses severe challenges to contact soil surface height detection devices, as the device's vibration and soil subsidence can introduce detection errors. To address these problems, a contact soil surface height detection device based on an angle sensor was designed in this study. The kinematic and dynamic relationships between the device and the soil during the detection process were analyzed, and a dynamic model of the detection device based on the soil-machine system was established. The dynamic process of ‘soil excitation → device vibration → soil subsidence’ during detection was revealed. The Kelvin model was used to describe the transient subsidence process of the ground wheel, and the model's parameters under different soil moisture contents were experimentally determined with a coefficient of determination (<em>R</em>²) of 0.85 ∼ 0.97. To investigate the influence of soil moisture content and device structural parameters (inertia parameter (<em>J</em>), initial angle (<em>γ</em>₀), prepressure of spring (<em>F_t</em>₀), and spring stiffness coefficient (<em>k</em>)) on the detection results, a simulation model was established using MATLAB/Simulink to simulate the interaction between the detection device and the soil during detection based on the proposed dynamic model, and the simulation results were validated experimentally. The peak overshoot percentage (<em>σ</em>) and steady-state error percentage (<em>Ess</em>) were used as indices. The experimental and simulation indices exhibited a strong linear relationship with a linear regression coefficient of 0.82 ∼ 0.99, confirming the validity of the established model. The results obtained in this study can provide theoretical and technical support for the design, optimization, compensation, and control of contact detection and soil pressure devices with similar structures.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110242"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Next generation crop protection: A systematic review of trends in modelling approaches for disease prediction","authors":"Alison Jensen ,&nbsp;Philip Brown ,&nbsp;Karli Groves ,&nbsp;Ahsan Morshed","doi":"10.1016/j.compag.2025.110245","DOIUrl":"10.1016/j.compag.2025.110245","url":null,"abstract":"<div><div>Digital agriculture tools and advances in modelling approaches have the potential to deliver precise decision support systems for more effective, efficient and sustainable crop disease management. Historically, disease prediction in agriculture has relied on knowledge of the relationships between a few key environmental parameters and crop disease development. The emergence of new sensor technologies is now expanding the range of input data readily accessible for use in modelling. In addition, Artificial Intelligence (such as machine learning and deep learning algorithms) offers the capacity to process the large datasets available from a wider range of input variables relating to the three components of disease development: host, pathogen and environment. This review examined the rate and extent to which machine learning has replaced traditional modelling approaches for disease predictive model development. A systematic protocol was developed to investigate trends in modelling approaches for disease prediction in four major crop types: cereals, grape, potato and citrus. A total of 104 publications, reporting on the development of 146 disease predictive models were evaluated for modelling approach, data inputs and model performance. The results from this review indicate that the application of machine learning for predictive model development has greatly increased over the past two decades. Increased application of machine learning models (including Support Vector Machine and Random Forest) was associated with the development of more high-performance models and incorporation of higher numbers of predictor variables. The potential of deep learning models to deliver more precise and adaptable models for next generation disease management will be determined by applying these methods to large datasets. Further research is needed to investigate multi-model, machine learning approaches for disease prediction and to ensure model design captures important input variables relating to environment, host and pathogen.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110245"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic literature review on the applications of federated learning and enabling technologies for livestock management","authors":"R.J. Garro ,&nbsp;C.S. Wilson ,&nbsp;D.L. Swain ,&nbsp;A.J. Pordomingo ,&nbsp;S. Wibowo","doi":"10.1016/j.compag.2025.110180","DOIUrl":"10.1016/j.compag.2025.110180","url":null,"abstract":"<div><div>This paper conducts a systematic review of the literature on the application and integration of federated learning, blockchain technology, and the Internet of Things (IoT) in livestock management. To achieve this objective, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology was applied, guiding the review process to ensure transparency and comprehensiveness. Extensive searches were carried out from five academic databases, such as ScienceDirect, IEEE Xplore, Springer, Multidisciplinary Digital Publishing Institute (MDPI), and Association for Computing Machinery (ACM). A total of 1,259 articles were reviewed and 20 articles were finally selected for analysis. The study reveals that there is limited research on the integration of federated learning, blockchain technology, and the IoT in the livestock sector. However, these technologies have application in the sector for improving efficiency, optimizing crop and animal management, and promoting environmentally sustainable practices. The study suggested that several key issues need to be considered for using these technologies such as the protection of data privacy, the management of information diversity, and restrictions on connectivity, as well as the need to motivate cooperation and commitment between different stakeholders in the sector. This study provides a reference for researchers on the usefulness of these technologies for increasing efficiency and transparency in livestock management.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110180"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of spectro-temporal remote sensing in vegetation classification: A comprehensive review integrating machine learning and bibliometric analysis","authors":"Arif Ur Rehman ,&nbsp;Abdur Raziq ,&nbsp;Bhaskar Shrestha ,&nbsp;Kim-Anh Nguyen ,&nbsp;Yuei-An Liou","doi":"10.1016/j.compag.2025.110184","DOIUrl":"10.1016/j.compag.2025.110184","url":null,"abstract":"<div><div>Spectro-temporal remote sensing (STRS) is a reliable source for mapping and monitoring earth’s surface dynamics. This review investigates the role of STRS in Vegetation Classification (VC) by analyzing 159 articles from Web of Science Core Collection (WSCC) database, spanning from 1980 to 2023. By integrating machine learning and bibliometric analysis, it provides comprehensive examination of trends, themes and advancements in the application of STRS in VC. The findings indicate significant growth in the use of STRS for VC, highlighted an exponential increase in publications over time. Recently, commonly used classification methods include machine learning, deep learning and spectral matching techniques, with research themes covering crop types, agricultural land, and forests. Notably, the study underscores the dominance of the USA and China in both publication quantity and collaborative efforts, reflecting their leadership in this field. Frequently utilized STRS data sources include MODIS, Landsat and Sentinel-1/2 sensors. Furthermore, the review emphasizes the need for developing flexible frameworks that integrate spectro-temporal data and accuracy evaluation metrics to build robust, intelligent, and transfer-learning classification methods. Overall, this review sheds light on the role of STRS in VC and provides valuable insights for researchers and decision-makers involved in vegetation monitoring and mapping. It emphasizes the potential of STRS to revolutionize VC and outlines directions for further research to address existing challenges and capitalize on emerging opportunities in this rapidly growing field.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110184"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel approach to water stress assessment in plants: New bioimpedance method with PSO-optimized Cole-Cole impedance modeling","authors":"Flórián Kovács ,&nbsp;Ákos Odry ,&nbsp;Zoltán Vizvári ,&nbsp;Sundoss Kabalan ,&nbsp;Enikő Papdi ,&nbsp;Péter Odry ,&nbsp;Katalin Juhos","doi":"10.1016/j.compag.2025.110167","DOIUrl":"10.1016/j.compag.2025.110167","url":null,"abstract":"<div><div>In order to characterize plant water deficiencies, this paper presents a custom-developed bioimpedance (BIS) measurement setup designed for <em>in vivo</em> studies that extracts plant leaf parameters using a novel optimization approach based on the particle swarm optimization (PSO) algorithm. The system performs, four-electrode measurements on plant leaves and employs a custom multi-objective cost function to validate parameters for the Double Shell Cole-Cole model. The experiment consisted of two parts: first, pepper plants (<em>Capsicum annuum</em> L.) as a model plant were exposed to drought stress in a light chamber, and their impedance and physiological parameters were measured. In the second part of the experiment, detached pepper leaves were allowed to dry naturally, and impedance measurements were recorded at hourly and tri-hourly intervals. Impedance spectrum measurements from 230 samples (1 Hz to 100 kHz), collected during both experiments, demonstrated that extracellular fluid resistance increases linearly with water loss. The proposed PSO-optimized Double Shell model showed a stronger correlation between extracellular fluid resistance and water loss compared to the widely used Zfit algorithm, which exhibited higher coefficient of variation in the Cole-Cole parameters. Both algorithms showed a significant negative correlation between relative water content and extracellular fluid resistance, but only the proposed PSO-based model detected a relationship between cell membrane capacity and membrane stability index. Additionally, extracellular fluid resistance correlated with photosynthetic efficiency. The results highlight the effectiveness of impedance measurements for assessing plant water status and support the reliability of proposed PSO-based optimization for bioimpedance analysis.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110167"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time monitoring system for evaluating the operational quality of rice transplanters","authors":"Lei He ,&nbsp;Yongqiang Li ,&nbsp;Xiaofei An ,&nbsp;Hongxun Yao","doi":"10.1016/j.compag.2025.110204","DOIUrl":"10.1016/j.compag.2025.110204","url":null,"abstract":"<div><div>Currently, rice transplanters are extensively employed for the mechanized cultivation of rice seedlings. However, few technologies or systems are available to monitor the operational quality parameters, i.e., the number of missing seedlings, row spacing, plant distance, etc., of rice transplanters. The performance of rice transplanters is directly linked to the growth quality of the seedlings and has a crucial effect on the final yield. Therefore, monitoring the various issues that arise during the operation of rice transplanters in a timely and accurate manner to ensure the quality of the transplanting process is particularly important. To address the above issues, this paper develops a real-time monitoring system for rice transplanters. The system architecture includes embedded devices, an image capture module, and a data upload module. A rice seedling detection model based on an enhanced YOLOv5-Lite neural network is developed, and comparative experimental results demonstrate that the proposed model achieves an [email protected] of 81.9 % for rice seedling detection, which is higher than that of the original YOLOv5-Lite model. We additionally propose a RANSAC-based algorithm to detect rice seeding paths in real time, and the rice seeding path detection results are used to determine the row spacing and plant distance. Specifically, a distance mapping algorithm based on triangular transformations is developed to calculate the row spacing and plant distance in a field. We subsequently calculate the number of missing seedlings between adjacent plants on the basis of the spacing between plants in the same row. Furthermore, a rice seedling tracking and counting algorithm based on an improved ByteTrack algorithm is developed to determine the missing seedling rate, as well as the seeding quantity. We integrate the developed algorithms into a real-time monitoring system and test them at Qixing Farm. The experimental results indicate that the monitoring system achieves an accuracy of 99.2 % for seedling quantity counting and an accuracy of 90.3 % for missing rate counting, with a processing speed of 3.95 frames per second.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110204"},"PeriodicalIF":7.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Path tracking control of crawler tractor based on adaptive adjustment of lookahead distance using sparrow search algorithm","authors":"Yue Song,&nbsp;Jinlin Xue,&nbsp;Tianyu Zhang,&nbsp;Xiaoxu Sun,&nbsp;Han Sun,&nbsp;Weiwei Gao,&nbsp;Qiqi Chen","doi":"10.1016/j.compag.2025.110219","DOIUrl":"10.1016/j.compag.2025.110219","url":null,"abstract":"<div><div>The complex and changeable farmland environment brings great challenges to the path tracking and stable control of autonomous agricultural machinery. To improve the efficiency and stability of path tracking control for autonomous agricultural machinery before entering the path from the headland and after entering the path, a path tracking control method for crawler tractor is proposed which can adjust the lookahead distance adaptively in Pure Pursuit control by using Sparrow Search Algorithm. In the method, the lookahead distance is regarded as sparrow individuals, and then the optimal target point is selected by simulating natural selection. Here, two lookahead area delineation schemes are set in light of the current lateral deviation of the agricultural machinery, and the lookahead area is preprocessed before searching the optimal target point to improve the efficiency and performance of the algorithm. Then, the current position information is substituted into the tracking control model of crawler tractor, and the position at the next moment is predicted under different lookahead distances. The predicted position is compared with the preset path to obtain the axial deviation and the heading deviation at the next moment. Additionally, the fitness function is constructed with the prediction deviation as the variable, and the optimal target point in the lookahead area can be searched by comparing the fitness values. In order to verify the feasibility of the proposed method, the ‘'entry-line and straight-line' tracking test of agricultural machinery under different initial postures and the curve tracking test with time-varying curvature were carried out on the platform of tracked tractor. The test results show that the average value, maximum value and standard deviation of the lateral deviation and the heading deviation after the agricultural machinery reaches the stable tracking state are not more than 0.030 m, 0.106 m, 0.034 m, 0.275 °, 1.528 °, 0.321 ° respectively in the 'entry-line and straight-line' test, and 0.059 m, 0.076 m, 0.175 m, 0.951°, 1.306°, 5.760° respectively in the curve tracking test. These results indicate that the path tracking control algorithm proposed in this paper improves the accuracy and stability of the path tracking of the crawler tractor, and has high adaptability to the curve path with time-varying path curvature, which meets the navigation requirements of the crawler tractor in the field operation.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110219"},"PeriodicalIF":7.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards reliable and damage-less robotic fragile fruit grasping: An enveloping gripper with multimodal strategy inspired by Asian elephant trunk","authors":"Qingyu Wang ,&nbsp;Kaixin Bai ,&nbsp;Lei Zhang ,&nbsp;Zhizhong Sun ,&nbsp;Tianze Jia ,&nbsp;Dong Hu ,&nbsp;Qiang Li ,&nbsp;Jianwei Zhang ,&nbsp;Alois Knoll ,&nbsp;Huanyu Jiang ,&nbsp;Mingchuan Zhou ,&nbsp;Yibin Ying","doi":"10.1016/j.compag.2025.110198","DOIUrl":"10.1016/j.compag.2025.110198","url":null,"abstract":"<div><div>Fruit uploading and packaging are labor-intensive and time-consuming steps in postharvest industry, which involve continuous pick-and-place manipulation. In this case, we aim to replace manual working with robotic grasping. However, for robotic fragile fruit grasping, the main difficulty is to reduce early stage bruise while maintaining the grasping reliability. In this study, we aim to solve this problem and achieve reliable and damage-less robotic fragile fruit grasping. Inspired by the structure of the Asian elephant trunk with its feeding behavior, a bionic and pneumatic soft gripper was designed, and a multimodal grasping strategy was proposed. Similar with Asian elephant trunk, the gripper has two designed trapezoid air chambers to control the two individual parts, including fingertip-like process and enveloping structure. Enveloping grasping behavior was imitated with larger area of contact, less contact force, and larger pull off force. A visuo-tactile multimodal grasping strategy was integrated into the robotic grasping system. The visual modality was developed for positioning and grasp pose estimation. The tactile modality was employed for grasping pose confirmation and closed-loop grasping force control. In the experiment on the enveloping gripper, the maximum contact force and the pull off force reached a good balance and were 0.7083 N and 7.959 N, respectively. With the proposed multimodal grasping strategy, the grasping success rate increased 4.23 % to 96.70 %. As for closed-loop control of the grasping force, the average value for steady-state error and maximum overshoot were 0.0856 N and 26.43 %, respectively. The experiment on Spatial Frequency Domain Imaging (SFDI) demonstrated the effectiveness of our enveloping gripper in reducing the early stage bruise. To some extent, the designed enveloping gripper with the proposed multimodal strategy could achieve reliable and damage-less fragile fruit grasping, which is promising in fruit postharvest industry.</div></div>","PeriodicalId":50627,"journal":{"name":"Computers and Electronics in Agriculture","volume":"234 ","pages":"Article 110198"},"PeriodicalIF":7.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}