South China Robotics Innovative Research Institute

Robotic pollination represents a pivotal component of smart agriculture, with foundational architectures for target recognition, path planning, and motion control having been progressively established. However, developing an efficient and robust pollination system that integrates perception, decision-making, and execution within real-world scenarios remains confronted with complex challenges. This study systematically reviews recent advancements in the field and distills the core technical issues of greenhouse robotic pollination into three primary domains: target detection and pose estimation, end-effector design, and pollination strategies combined with motion control. Focusing on the visual perception of flowers, actuator architecture, and operational tactics, this review synthesizes existing academic findings to evaluate the state-of-the-art in flower detection and pose estimation, characterize diverse end-effector designs, and analyze the evolutionary trajectory of motion control techniques. Specifically, the analysis encompasses the impact of detection algorithms on recognition accuracy and robustness, the structural classification and performance attributes of pollination mechanisms, and the optimization of control strategies. Furthermore, the study categorizes global research backgrounds, technical methodologies, and paradigmatic system cases, offering a critical evaluation of experiences in constructing automated pollination systems. Despite these advances, current robotic pollination technologies for peppers (chili) face significant bottlenecks characterized by immature methods for precise flower detection and pose estimation, the need for optimized specialized end-effector designs, and insufficient robustness in decision-making systems under dynamic environmental conditions. To address these issues, future development should prioritize constructing diverse, large-scale flower image and pose datasets while developing detection algorithms adaptable to complex environments to achieve high-precision identification. Additionally, implementing this system requires a hierarchical architecture where perception drives adaptive actuation. Deep learning models must localize flower targets and assess maturity in real-time, feeding coordinates to path planners that generate collision-free trajectories through foliage. These trajectories are executed via multimodal motion control, synchronizing the rigid manipulator with soft end-effectors. By embedding tactile feedback into the machine learning loop, the system creates a unified sensorimotor framework. This enables dynamic force modulation based on physical resistance, ensuring precise, non-destructive pollination tailored to chili plants.

Rice leaf diseases pose a significant and escalating threat to global food security. Timely and accurate detection, particularly in the critical early stages characterized by subtle lesions, is paramount for effective disease management. However, existing solutions often struggle with the complexities of real-world field environments (e.g., variable lighting, occlusions, complex backgrounds), computational constraints on edge devices, and limited generalizability across diverse disease types and plant species. To address these challenges, this study proposes a novel lightweight deep learning framework specifically designed for robust rice leaf disease detection. Our key innovations include: (1) A Multi-branch Large-kernel Fusion Depthwise (MLFD) module enhancing multi-scale contextual feature extraction critical for identifying subtle early lesions; (2) A Multi-scale Dilated Transformer Attention (MDTA) module integrating spatial and channel attention mechanisms to improve feature representation under complex conditions; (3) A Lightweight Detection Head (Lo-Head) optimized with grouped and depthwise convolutions, drastically reducing model complexity without sacrificing accuracy. Crucially, extensive experiments demonstrate the framework's superior performance. On a dedicated rice leaf disease dataset, it achieves a mean Average Precision mAP@0.5:0.95 of 62.62%, outperforming state-of-the-art lightweight detectors including YOLOv5n (56.73%), YOLOv8n (57.41%), YOLOv10n (56.14%), and the baseline YOLOv11n (60.85%), while maintaining low computational demands (6.3 GFLOPs, 2.66M parameters). Significantly, rigorous generalization experiments validate the model's exceptional transferability. Evaluated on independent datasets encompassing potato and tomato leaf diseases, the proposed framework consistently surpasses comparable models in mAP@0.5:0.95, demonstrating its robust capability to detect diseases across different plant species. This combination of high accuracy, computational efficiency, and remarkable cross-crop generalizability positions our framework as a highly promising tool for practical deployment on resource-limited edge devices (e.g., drones, field sensors) in smart agriculture systems, enabling proactive disease surveillance and precision control strategies across diverse crops.

When picking strawberries outdoors, due to factors such as light changes, obstacle occlusion, and small target detection objects, the phenomena of poor strawberry recognition accuracy and low recognition rate are caused. An improved YOLOv5n strawberry high-precision recognition algorithm is proposed. The algorithm uses FasterNet to replace the original YOLOv5n backbone network and improves the detection rate. The MobileViT attention mechanism module is added to improve the feature extraction ability of small target objects so that the model has higher detection accuracy and smaller module sizes. The CBAM hybrid attention module and C2f module are introduced to improve the feature expression ability of the neural network, enrich the gradient flow information, and improve the performance and accuracy of the model. The SPPELAN module is added as well to improve the model’s detection efficiency for small objects. The experimental results show that the detection accuracy of the improved model is 98.94%, the recall rate is 99.12%, the model volume is 53.22 MB, and the mAP value is 99.43%. Compared with the original YOLOv5n, the detection accuracy increased by 14.68%, and the recall rate increased by 11.37%. This technology has effectively accomplished the accurate detection and identification of strawberries under complex outdoor conditions and provided a theoretical basis for accurate outdoor identification and precise picking technology.

Selecting an appropriate calibration configuration set is crucial for industrial robot kinematic calibration, as it can mitigate the effects of unmodeled parameters and measurement noise. Existing approaches either rely on laser measurement of a large number of configurations followed by offline selection of an optimal subset—an inherently time-consuming process—or generate optimal configurations solely from joint-space constraints, which are easily affected by the robot’s workspace and the laser tracker’s line-of-sight limitations. In this study, we propose a novel optimization framework that, on the basis of joint-space constraints, incorporates both Cartesian-space constraints and laser-tracker line-of-sight constraints to formulate an optimization model for generating an optimal calibration configuration set. A hybrid WPSO-SQP algorithm—combining the global search capability of inertia-weighted particle swarm optimization (WPSO) with the strong convergence properties of sequential quadratic programming (SQP) for nonlinear constrained problems—is then employed to identify the optimal configuration set. To ensure uninterrupted line-of-sight during measurement, a simulated annealing algorithm is used to optimize the measurement sequence of the selected calibration configuration set. Experimental validation on a six-degree-of-freedom industrial robot demonstrates that the proposed method substantially improves both the efficiency and the accuracy of kinematic calibration.

Berries are nutritious and valuable, but their thin skin, soft flesh, and fragility make harvesting and picking challenging. Manual and traditional mechanical harvesting methods are commonly used, but they are costly in labor and can damage the fruit. To overcome these challenges, it may be worth exploring alternative harvesting methods. Using berry fruit-picking robots with perception technology is a viable option to improve the efficiency of berry harvesting. This review presents an overview of the mechanisms of berry fruit-picking robots, encompassing their underlying principles, the mechanics of picking and grasping, and an examination of their structural design. The importance of perception technology during the picking process is highlighted. Then, several perception techniques commonly used by berry fruit-picking robots are described, including visual perception, tactile perception, distance measurement, and switching sensors. The methods of these four perceptual techniques used by berry-picking robots are described, and their advantages and disadvantages are analyzed. In addition, the technical characteristics of perception technologies in practical applications are analyzed and summarized, and several advanced applications of berry fruit-picking robots are presented. Finally, the challenges that perception technologies need to overcome and the prospects for overcoming these challenges are discussed.

Establishing a novel design and accurate analytical models for XY nanopositioning stages based on voice coil motor (VCM) actuators is critical to achieving an optimal working performance. To overcome the existing design challenges of 2-degree-of-freedom guiding mechanisms, a four-layer structure composed of L-shaped spatial double parallelogram flexure mechanisms was proposed for the magnetic stage, which exhibits light weight and inhibits parasitic and decoupled motions. The guiding mechanisms were modeled by the compliance matrix method. Thereafter, by combining an electromagnetic model for the VCMs with the equivalent magnetic network method, an electromagnetic-mechanical coupling optimization method with multiple constraints was proposed for the stage to achieve a millimeter-range motion with a maximized natural frequency. The mechanical and electromagnetic performances were then verified by finite element analysis software. The optimized prototype was tested with a stroke of ±3.41 and ±3.08mm for X axis and Y axis, respectively, a closed-loop resolution of 100nm for X axis and 150nm for Y axis, and a resonant frequency of 11.75Hz for both axes. The tracking of a 0.1Hz spiral of Archimedes achieved a maximum tracking error of 2.9%.

Abstract Micro‐arc oxidation (MAO) is a surface treatment technology that enhances the surface properties of valves by creating a ceramic oxide layer on the metal surface. The goal of this study is to investigate the influence of current density on the properties of aluminum coatings during preparation and to improve the tribological properties of MAO/PTFE self‐lubricating films on the coating surface. The characterization of the coating was performed using X‐ray photoelectron spectroscopy, X‐ray diffraction, Raman spectra, and energy dispersive spectroscopy. The roughness, hardness, and elastic modulus of the coatings were tested using atomic force microscopy and nanoindentation. Tribological experiments were conducted to evaluate the tribological properties of the coatings. The experimental results show that the friction coefficient (COF), roughness, hardness, and elastic modulus of the MAO coating increase with the increase of current density. Additionally, the friction coefficient of the MAO composite coating significantly decreases after the addition of polytetrafluoroethylene (PTFE), improving the service life and application range of the metal coating. These findings are expected to promote the development of valve metal in various application fields.