Search Results (1,052)

In precision agriculture, fruit segmentation serves as a fundamental visual prerequisite for orchard robotic operations, including precision management, automated harvesting and yield estimation. For unripe passion fruits, complex scene interference, high fruit–leaf similarity and foliage occlusion in practical orchard scenes easily cause missed detection and over-segmentation in existing models. To address these challenges, we build a multi-scene unripe-passion-fruit dataset named ZKMPF. Based on the UNet architecture, we propose Environment-Adaptive and Prompt-Fusion UNet (EAPF-UNet). First, EAPF-UNet embeds an Environmental Adapter into the encoder, which adjusts feature parameters to mitigate complex scenes interference. Then, it incorporates a Localization Multi-Scale Fusion Module (LMSM) and Refinement Multi-Scale Fusion Module (LMFM) to achieve accurate localization and refinement of unripe passion fruits and address scale variations. Finally, it designs the Multi-Dimensional Prompt Fusion module that integrates color, geometry and texture priors to improve the feature discriminability between unripe passion fruits and background. We conduct experiments on our self-built dataset, comparing EAPF-UNet with eight other segmentation models. Evaluated against eight segmentation models, EAPF-UNet obtains mDice of 85.51% and mIoU of 77.16% across six metrics and achieves competitive segmentation results within this dataset’s test scenes. Full article

The integration of robotics into agriculture addresses challenges such as labour shortages and sustainable production. Handling delicate and irregular natural products remains difficult for conventional grippers. This paper presents a baromorphic end-effector as a proof-of-concept platform for validating a perception-sensing TCP realignment pipeline rather than as a field-ready agricultural product. The square-to-hexagonal layout choice was made iteratively through prototyping, whereas a finite-element analysis was used in prior work to optimise and characterise the hexagonal cushion unit . The materials, actuation, and robotic platforms serve as the experimental testbeds for the integrated control concept. The system uses a modular array of pneumatically actuated hexagonal cells with sparse embedded pressure sensing, vision-based object detection, a discrete heuristic visual servoing controller to bypass kinematic singularities during the approach, and a closed-loop TCP dynamic realignment algorithm. Under controlled laboratory conditions, the prototype achieved 12/12 successful linear grasps and 9/11 successful angular grasps (82%) on irregular produce, whereas a conventional rigid parallel-jaw gripper failed all attempted baseline trials under the same protocol. Full article

Robots are being developed to perform the day-to-day operational tasks of animal agriculture, affecting the way in which humans and farm animals interact. There is the prospect of automation increasing to the point where humans would hardly set foot on farms, which, aside from the consumption of animal-based products, could entirely disconnect humans and farmed animals from each other. Yet the literature on public attitudes towards the introduction of agricultural robots into the human–animal relationship is sparse. Here, we consider the public acceptability of introducing robots into the human–animal relationship in agriculture. Between 2023 and 2025, we conducted 12 dialogue groups and two community juries with members of the Australian public on the social and ethical impacts of automation in agriculture. We draw on insights from these empirical studies to highlight the underlying values that inform different attitudes towards robots taking on tasks previously performed by humans in animal farming. Across our empirical work, we consistently found three key factors influencing the willingness of members of the public to accept agricultural robots into the human–animal relationship: moral responsibility for farm animals; human intuition and empathy; and a natural life as a condition of animal welfare. Our data suggested that the removal of humans from all contact with farmed animals by adopting highly roboticized farming will likely be rejected by the Australian public as “a step too far”, largely due to its moral and social implications. We identify a set of conditions that are likely to be important to public acceptability of the use of robots in animal agriculture. Full article

In open-field agriculture, timely human activity recognition (HAR) is critical for anticipating worker actions and enabling proactive human–robot collaboration. This study developed an offline early HAR framework based on pre-segmented activity sequences. Long Short-Term Memory (LSTM) networks were used in conjunction with wearable inertial sensors mounted on the chest, cervical region, lumbar region, and right and left wrists. Accelerometer, gyroscope, and magnetometer signals were collected from 20 participants during an outdoor agricultural material-handling task, with a mobile ground robot serving as the receiving platform for the crate. Each activity was represented by cumulative prefixes from 30% to 100% of its duration. At the 30% observation ratio, the model achieved a macro-F1 score of 0.9314, compared with 0.9481 for the full sequence, corresponding to an absolute difference of 0.0167. Shapley Additive Explanations (SHAP) were also used to identify the body locations, sensor modalities, and signal channels that contributed most. The early decisions were mainly supported by sensors placed on the trunk, with wrist sensors providing complementary information, particularly for standing classification. Multimodal inertial information was also important. The most influential inputs were mainly gyroscope and magnetometer channels from the chest, cervical region, and lumbar region. In conclusion, the high performance at early observation ratios highlights the potential to support more adaptive and better-coordinated robot-assistance strategies. Full article

Accurate and smooth path tracking is important for autonomous tracked agricultural robots operating in greenhouse-like environments. Existing adaptive look-ahead pure-pursuit methods mainly adjust the look-ahead distance according to vehicle speed or path geometry, while the influence of time-varying localization reliability has not been sufficiently considered. This study proposes a noise-aware adaptive pure-pursuit controller that combines Extended Kalman Filter (EKF) estimation with causal Savitzky–Golay (SG) endpoint smoothing. A bounded look-ahead law is designed by jointly considering normalized vehicle speed, lateral error, path curvature, and an innovation-derived localization-noise indicator. Numerical simulations were conducted on straight, circular, S-shaped, and U-shaped reference paths under prescribed localization disturbances. Under the 0.5 m positional-noise condition, the proposed method achieved an root mean square error (RMSE) of 0.087 m and an angular-velocity root mean square (RMS) of 0.28 rad/s, compared with 0.112 m and 0.36 rad/s, respectively, for conventional fixed-look-ahead pure pursuit. Compared with proportional-integral-derivative (PID), Stanley, model predictive control (MPC), and conventional pure-pursuit controllers, the proposed method provides a favorable balance between tracking accuracy and control smoothness. It also has better computational efficiency than MPC while retaining the low-computational-burden advantage of geometric control. In the sensitivity analysis, the relative RMSE increase from 0.1 to 0.8 m was 36.5% for the proposed method and 103.4% for conventional pure pursuit. These results indicate that the proposed lightweight noise-aware control strategy can improve tracking accuracy, control smoothness, and tolerance to localization disturbances under the specified numerical conditions, providing a practical design reference for low-speed greenhouse agricultural robots. Full article

Digital agriculture (sensors, Internet of Things, machine learning, robotics, digital twins) has for fifteen years been sustained by massive investment promising more productive, precise, and sustainable agriculture, yet adoption remains heterogeneous and systemic impact limited despite intense scientific output. The dominant explanation treats this as a diffusion deficit and calls for more farmer training, advisory support, and subsidy; this reading leaves the structure of research itself unexamined and does not, on its own, explain why the gap between announced and delivered performance persists across technology generations. We argue that, alongside diffusion-side and demand-side factors, the paradox has a further, under-recognised upstream component: research design oriented towards technological artefacts rather than guaranteed functions. We develop the case for this complementary reading using Stahel’s performance economy framework and the Product-Service Systems literature. Four contributions follow: a tripartite typology of function (service-, specification-, and process-function) articulated hierarchically explains why research centred on specification-function alone cannot guarantee a service-function; current research is characterised, on the reading developed here, by three cumulative biases and three blind spots, including data governance and the under-representation of the social sciences; a four-axis reorientation agenda is proposed; and the framework is distinguished from Agricultural Innovation Systems, Responsible Research and Innovation, and mission-oriented research by specifying the functional level these leave indeterminate. Full article

The harvesting of fruit and vegetable crops has long been plagued by prominent issues such as high labor costs, low harvesting efficiency, and high fruit damage rates. The application of object recognition technology has enabled harvesting robots to identify, detect, and locate crops in certain agricultural scenarios, achieving a degree of automated harvesting. However, these systems still suffer from shortcomings such as poor robustness in complex environments, insufficient generalization ability, and high model deployment costs, which significantly limit their large-scale application in agricultural harvesting equipment. This paper comprehensively reviews recent literature in the field of fruit and vegetable target recognition. It summarizes how current research focuses on the implementation principles and directions for the improvement of mainstream methods—including digital image processing, traditional machine learning, and deep learning—while also identifying the remaining issues and challenges facing current technology in terms of algorithmic model real-time performance, robustness, and generalization ability. In the future, target recognition technology is expected to achieve breakthroughs through approaches such as multimodal feature fusion, large-scale models, and semi-supervised learning, evolving toward higher accuracy, faster processing speeds, and easier deployment, thereby providing technical support for the large-scale implementation of smart agriculture. Full article

Variable-rate pesticide spraying and fertilizer application require coordinated operation of heterogeneous agricultural machines, particularly in irregular fields where task demands, vehicle mobility, payload capacity, energy consumption, and resupply requirements vary spatially. However, most existing studies optimize aerial spraying or ground fertilization separately and do not jointly consider prescription-map demands, air–ground synchronization, pesticide-drift risk, and agricultural vehicle constraints. This study formulates collaborative UAV spraying and UGV fertilization as a multi-objective mixed-integer nonlinear programming problem with three objectives: minimizing system makespan, weighted energy consumption, and pesticide-drift penalty. A prescription-map-guided bi-level planning framework is proposed. At the upper level, the problem-specific TNSAOO solver determines UAV and UGV task sequences and collaborative resupply-point activation. At the lower level, adaptive Theta* and row-constrained Hybrid A* generate UAV spraying and UGV fertilization trajectories, respectively, while prescription-dependent application commands are assigned along active operation segments and a time-window mechanism detects and corrects residual air–ground conflicts. The framework was evaluated using 30 real farmland boundaries and 90 randomized prescription scenarios. Mean geometric coverage rates reached 98.82% for UAV spraying and 98.95% for UGV fertilization, while the mean prescription-compliance errors were 6.21% and 2.13%, respectively. In addition, 96.7% of the batch runs contained no more than one detected air–ground conflict, with a mean corrective waiting time of 1.07 s. Compared with traditional independent operation, collaborative planning reduced mean system makespan by 9.32%, weighted energy consumption by 7.21%, modeled drift penalty by 3.62%, and total path length by 5.79%. In the multi-objective comparison, TNSAOO obtained a mean hypervolume of 0.597 and a mean inverted generational distance of 0.375, showing competitive Pareto-search performance relative to established comparison algorithms, particularly NSGA-II. Additional terrain and drift sensitivity analyses produced systematic changes in energy, completion time, and modeled drift risk under controlled parameter perturbations. These findings demonstrate the simulation-based feasibility of jointly planning heterogeneous variable-rate spraying and fertilization under a shared prescription map. Physical field experiments remain necessary to validate spray deposition, fertilizer-distribution uniformity, terrain effects, and model calibration under environmental uncertainty. Full article

Agricultural multi-robot systems in narrow and dynamic environments require global coordination, semantic event interpretation, and responsive trajectory execution. This study presents an end–edge–cloud fast–slow semantic planning framework. The cloud maintains a farm topology and generates fleet-level dispatch policies; the edge hosts an asynchronous agentic vision–language planner and a fast trajectory planner; and the robot performs sensing, LiDAR odometry, low-level control, and execution. The fast planner reuses the latest valid semantic condition until an event-triggered update becomes available. The fast branch is pretrained on nuScenes and adapted using the training and validation subsets of a 3780-sample agricultural dataset comprising synchronized front- and rear-view images, robot states, motion histories, and future trajectories, with an independent 630-sample test set reserved for final evaluation. On an edge-side RTX 4080 SUPER, the complete planner achieves an average L₂ error of 0.67 m, a fast-step latency of 96.3 ms, and a throughput of 10.4 Hz. In the four-robot topology experiment, the framework achieves a 100.0% success rate under the representative single-blockage condition and maintains an 86.7% success rate under the dual-blockage condition. During an approximately 30 min operation at a nominal semantic update rate of 2 Hz, the cloud and robot communication round-trip times average 24.43 and 3.85 ms, respectively, with no robot deadline misses, while the mean trigger-to-updated-trajectory latency of the full event-driven pipeline is 2357.37 ms. These results demonstrate the feasibility of assigning global coordination to the cloud, semantic reasoning and trajectory inference to the edge, and sensing and execution to the robot. Full article

Image segmentation is a fundamental step in computer vision and a cornerstone of robotic perception, serving as the foundation for interpreting data acquired from vision sensors, enabling robots to analyze complex visual environments, identify and localize objects, and support intelligent decision-making and autonomous control. It plays a critical role in applications such as autonomous navigation, robotic manipulation, medical robotics, agricultural robotics, autonomous vehicles, and human–robot interaction. Image segmentation has evolved from classical methods, which relied on handcrafted rules and mathematical models, to deep learning approaches that learn complex visual patterns directly from data. This evolution reflects advances in algorithms, computational power, and the theoretical foundations of mathematics and data science. Modern deep learning methods rely heavily on large, well-annotated datasets to train sophisticated neural networks. Yet, classical techniques remain valuable in certain scenarios, offering faster, reliable results without extensive computational requirements. Understanding the strengths and limitations of both approaches is key to selecting the right method. This paper surveys image segmentation techniques, comparing them in terms of accuracy, computational cost, and processing speed to guide informed method selection. Full article

Agentic, autonomous and explainable AI (XAI) is growing in smart agriculture, but its design, evaluation and integration have not been systematically mapped. Following PRISMA 2020, we searched Web of Science Core Collection, Scopus and IEEE Xplore through 14 June 2026 for English-language peer-reviewed articles and conference papers (2016–2026) implementing agentic/autonomous AI and/or XAI in agricultural systems using sensor, robotic or computer-vision data and reporting an evaluation. Two reviewers independently screened, extracted data and appraised methodological quality using a six-item CASP-style rubric. Results were synthesised descriptively using counts, percentages, cross-tabulations and thematic mapping; meta-analysis was inappropriate because tasks, datasets and metrics were heterogeneous. Of 2255 records, 322 studies were included. XAI dominated (69.6%), whereas autonomous (14.0%) and agentic (12.1%) designs were less common; only 4.3% combined autonomy with explainability. Disease detection was the leading application (33.5%). Most systems remained at the perception/decision-support level (78.9%); 17.4% were field-validated and 4.3% validated explanations agronomically. The evidence reveals an explainability-autonomy divide and substantial field-validation and reproducibility gaps. Explainable-by-design agentic systems require agronomic validation and shared evaluation standards. The review received no external grant funding and was not registered. Full article

Reliable joint detection of mango fruits and stems is an essential upstream perception task for robotic harvesting, but remains challenging because stems are small, slender, frequently occluded, and visually degraded by illumination variation. This study proposes MangoNET, a YOLOv11n-based framework for joint mango fruit and stem detection in complex orchard environments. A P2 high-resolution detection head preserves fine spatial information for small targets, while SPPF-ELAN aggregates local and contextual features for partially visible objects. SENet recalibrates channel responses under illumination variation, and WIoU v3 regulates bounding-box samples with different localization qualities. A dataset containing 1782 original images of Tainong and Jinhuang mangoes was collected from two orchards and data augmentation was applied only to the training set, increasing its size from 1172 to 2886 images through rotation, contrast adjustment, and Gaussian noise addition. MangoNET achieved fruit and stem F1-scores of 0.920 and 0.916, respectively, with mAP50 and mAP50–95 values of 0.941 and 0.690. Compared with YOLOv11n, mAP50 and mAP50–95 increased by 1.6 and 2.9 percentage points, respectively, while stem recall increased from 0.877 to 0.906. Source-image-independent five-fold cross-validation yielded mean mAP50 and mAP50–95 values of 0.944 and 0.711, respectively. Pilot evaluations using images acquired by a UAV and an RGB-D camera in a geographically distinct orchard suggested that MangoNET could maintain detection performance in a different orchard environment. MangoNET supplies fruit and stem candidate regions for subsequent association, harvesting-point localization, and robotic manipulation. Full article

Driven by the escalating global agricultural workforce shortage and the urgent need to meet the “Zero Hunger” mandate, the automation of harvest–transport workflows has emerged as a cornerstone of Agriculture 4.0. This paper highlights the latest research progress in multi-robot collaborative logistics scheduling across highly unstructured farming environments, underpinned by cutting-edge spatial perception and digital twin frameworks. Initially, we summarize the technological leap from conventional 2D geometric mapping to multi-modal semantic 3D reconstruction—fusing light detection and ranging (LiDAR), unmanned aerial vehicle (UAV) imagery, and spatial data—to enable high-fidelity forward-looking predictions. The discussion then transitions to algorithmic advancements, emphasizing the shift from traditional centralized operations research to decentralized, data-driven approaches such as Multi-Agent Reinforcement Learning (MARL). We also explore micro-kinematic predictive control mechanisms and the growing integration of ecological sustainability metrics into routing models. To demonstrate practical engineering progress, multi-agent implementations are analyzed across three typical spatial settings: high-throughput continuous relays in open fields, global navigation satellite system (GNSS)-denied discrete routing in dense orchards, and close-proximity human–robot collaboration (HRC) in smart greenhouses. Finally, we identify the remaining barriers to the large-scale commercialization of Agricultural Cyber-Physical Systems (ACPS), such as the “Sim-to-Real” gap restricted by edge-computing capacities, unclosed economic loops, and HRC ethical dilemmas, offering a forward-looking roadmap for next-generation resilient agricultural networks. Full article

Agricultural operations such as pepper harvesting, fruit counting, and field phenotyping rely on accurate visual recognition and instance segmentation algorithms. However, pepper fruits in complex field environments often exhibit slender and curved shapes, partial occlusion, ambiguous boundaries, and adhesion between adjacent instances. Existing object detection and instance segmentation methods therefore struggle to obtain complete fruit masks, which adversely affects subsequent fruit counting, contour measurement, and picking-point localization. To improve the instance segmentation accuracy of occluded peppers in complex field scenes, this study proposes OccPepSeg-YOLO, an improved model based on YOLO11n-seg. First, a P2FreqFusion module is introduced to fuse shallow, high-resolution detail features with deep semantic features, thereby enhancing the representation of fruit edges and tip regions. Second, an ASC module is designed to model the directional and scale-related morphological characteristics of pepper fruits, while a BoundaryGate module strengthens responses at occlusion interfaces and boundaries between adjacent instances. Finally, an OccPepSegment multi-scale prototype segmentation head is constructed, and a BDoU loss function is introduced to improve the boundary consistency of instance masks. Experiments on a self-constructed field-pepper instance segmentation dataset showed that OccPepSeg-YOLO achieved M-P, M-R, M-mAP50, and M-mAP50–95 values of 93.87%, 92.09%, 97.17%, and 82.31%, respectively, representing improvements of 5.59, 3.18, 3.83, and 9.52 percentage points over YOLO11n-seg. Further comparisons with representative YOLO-based instance segmentation models, including YOLOv8n-seg, YOLOv9c-seg, YOLO12n-seg, and YOLOv26n-seg, demonstrated that OccPepSeg-YOLO achieved the best overall segmentation performance. In particular, its M-mAP50–95 exceeded the best competing result obtained by YOLOv9c-seg by 8.35 percentage points. Under a unified repeated-inference protocol on an RTX 3090 GPU using FP32 precision, a batch size of 1, and 640 × 640 inputs, OccPepSeg-YOLO achieved a mean inference latency of 15.801 ± 1.238 ms, a P95 latency of 17.323 ms, and a throughput of 63.29 FPS. These results demonstrate that the proposed model can produce more complete pepper instance masks under leaf occlusion, fruit overlap, and complex background conditions, providing technical support for field-pepper recognition, fruit counting, and visual perception by agricultural robots. Full article

Global labour shortages in the agricultural sector, combined with diminishing arable land and a growing population, are driving investment in autonomous agricultural machinery. Autonomous systems that can navigate crop environments and perform planting, treatment, and harvesting alongside humans are required, but the gap between published research and commercially deployed systems remains wide across most operational scenarios. Why are agricultural robots still not widely deployed in real farms despite decades of research in autonomous navigation and path planning, and what is preventing full farm autonomy? This paper reviews the principal enabling technologies for autonomous agricultural integration, with a specific focus on path planning as the differentiator between research-stage and deployed systems. Current research in human–robot integration, open-field navigation, row identification and following, crop sensing, and power efficiency is synthesised and evaluated against a deployability criterion. A Deployability Assessment Framework is introduced, comprising structured tables that assign Technology Readiness Levels to twelve path-planning families and benchmark eleven commercial and research platforms against field-validated accuracy data. The analysis shows that point-to-point GNSS navigation has reached TRL 9 with over one million commercial units deployed, vision-based crop row following is at TRL 5–7 depending on crop and season, and whole-farm autonomy with dynamic re-planning is at TRL 3–5. The primary barriers are the absence of standardised evaluation benchmarks, the failure of perception models to generalise across seasons and crop types, and the decoupling of terrain and slip feedback from global path planners. Our review reveals that open-field GNSS navigation is commercially mature, but true whole-farm agricultural autonomy remains unsolved because current systems are not robust enough across seasons, terrain, sensing conditions, and operational transitions. Full article