Next-Generation Smart Farming: The Role of Agricultural Large Models and Intelligent Machinery

A Special Issue of AgriEngineering (ISSN 2624-7402) belonging to the section "Computer Applications and Artificial Intelligence in Agriculture".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 1029

Editor

College of Engineering, Nanjing Agriculture University, Nanjing 210031, China
Interests: digital twin; large language model; human-robot collaboration; intelligent decision-making and optimization; agricultural carbon intelligence

Special Issue Information

Dear Colleagues,

The global agricultural sector is on the brink of a profound transformation, driven by the convergence of artificial intelligence, big data, and advanced robotics. This Special Issue is dedicated to exploring this pivotal shift from data-driven farming toward a new era of cognitive and autonomous agriculture. Central to this revolution is the synergistic integration of two disruptive technologies: Agricultural Large Models (AgLMs) and next-generation intelligent machinery.

Agricultural Large Models (AgLMs), trained on vast multimodal datasets, including satellite imagery, weather history, soil science, plant physiology, and real-time sensor data, are emerging as the “digital brain” of the farm. These foundational models can perform complex tasks such as predictive yield modeling, precise disease and pest identification, hyper-localized resource recommendation, and generation of optimal management strategies under climate uncertainty. They move beyond simple analytics to offer generative, prescriptive insights, effectively understanding the intricate language of agronomy.

These digital insights must be physically actuated, which is the role of intelligent machinery. The field is evolving from automation to full autonomy, with smart tractors, robotic harvesters, drones, and swarms of mini-robots that can perceive their environment, make real-time decisions, and perform delicate operations with minimal human intervention. Empowered by edge computing and advanced sensors, these machines become the “hands and feet” of AgLMs, closing the loop between data-driven decision-making and physical action. This enables tasks like millimeter-accurate weeding, plant-by-plant treatment, and selective harvesting at scale, fundamentally redefining precision agriculture.

This Special Issue will serve as a platform for cutting-edge research that bridges this digital–physical divide. We invite contributions on the development and application of AgLMs, advanced perception and control algorithms for intelligent machinery, human–robot interaction in agricultural settings, and scalable cloud–edge architectures for farm-wide intelligence. Furthermore, we welcome discussions on critical socio-economic dimensions, including technology adoption barriers, data ownership, and the ethical implications of autonomous systems. By fostering interdisciplinary dialogue, this collection aims to chart the course toward a more resilient, productive, and sustainable agricultural future, powered by cognitive machines.

Dr. Gang Yuan
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AgriEngineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • agricultural large models
  • multimodal embodied perception
  • generative AI decision-making
  • digital twin virtual simulation
  • embodied intelligence of robots
  • electric intelligent power equipment
  • immersive virtual reality
  • agricultural carbon intelligence

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

43 pages, 68208 KB  
Article
Improved YOLO11n-OBB for Rotated Watermelon Detection in Complex Field Environments Toward Agricultural Large-Model Applications
by Xinyang Li, Jinghao Shi, Chuang Wang, Xin Yue, Weiqi Sun, Zonghui Zhuo, Jinge Wang and Kezhu Tan
AgriEngineering 2026, 8(6), 214; https://doi.org/10.3390/agriengineering8060214 - 28 May 2026
Viewed by 677
Abstract
Intelligent perception of watermelon targets in complex field environments is a key prerequisite for automated harvesting and future collaborative decision-making with agricultural large models. To address severe leaf occlusion, large pose variation, dense adhesion among adjacent fruits, and the inability of conventional horizontal [...] Read more.
Intelligent perception of watermelon targets in complex field environments is a key prerequisite for automated harvesting and future collaborative decision-making with agricultural large models. To address severe leaf occlusion, large pose variation, dense adhesion among adjacent fruits, and the inability of conventional horizontal bounding boxes to accurately represent target orientation under natural cultivation conditions, this paper proposes an improved YOLO11n-OBB-based method for rotated watermelon detection. During data preparation, a semi-automatic annotation strategy combining segmentation-mask assistance with circumscribed rectangle fitting was adopted to efficiently construct a watermelon OBB dataset that closely matches the true physical boundaries of the fruits. On this basis, three structural improvements were introduced to the YOLO11n-OBB baseline: an LSK module was selectively embedded into the middle and later stages of the backbone to enhance adaptive receptive-field modeling and occlusion reasoning in complex bac kgrounds; the original neck structure was replaced with a lightweight BiFPN to strengthen bidirectional feature fusion for targets with large-scale variation in field scenes; and KFIoU Loss was incorporated into the rotated box regression branch to alleviate angle sensitivity and boundary discontinuity, thereby improving the convergence stability of orientation parameter learning. On the constructed watermelon OBB test set, the improved model raised mAP@0.5 (OBB) from 0.871 to 0.931, mAP@0.5:0.95 (OBB) from 0.670 to 0.736, Precision from 0.885 to 0.931, and Recall from 0.849 to 0.908 relative to the YOLO11n-OBB baseline (relative gains of 6.89%, 9.85%, 5.20%, and 6.95%, respectively), while keeping the inference speed at 100 FPS and the parameter count at only 2.71 M. While maintaining a compact model size and high real-time performance, the proposed method significantly improved rotated detection accuracy in crowded and overlapping scenes. In addition, the detection results were encapsulated into a structured JSON perception interface, preliminarily demonstrating the integration pathway of this lightweight front-end for task planning and human–machine collaborative operations with agricultural large models, and indicating its potential for future intelligent agricultural decision-making. Full article
Show Figures

Figure 1

Back to TopTop