The land used for fruit cultivation now exceeds 120 million hectares globally, with an annual yield of nearly 940 million tons. Fruit picking, the most labor-intensive task in agricultural production, is gradually shifting toward automation using intelligent robotic systems. As the component in direct contact with crops, specialized picking end-effectors perform well for certain fruits but lack adaptability to diverse fruit types and canopy structures. This limitation has constrained technological progress and slowed industrial deployment. The diversity of fruit shapes and the wide variation in damage thresholds—2–4 N for strawberries, 15–40 N for apples, and about 180 N for kiwifruit—further highlight the challenge of universal end-effector design. This review examines two major technical pathways: separation mechanisms and grasping strategies. Research has focused on how fruits are detached and how they can be securely held. Recent advances and limitations in both approaches are systematically analyzed. Most prototypes have achieved picking success rates exceeding 80%, with average cycle times reduced to 4–5 s per fruit. However, most designs remain at Technology Readiness Levels (TRLs) 3–5, with only a few reaching TRLs 6–7 in greenhouse trials. A dedicated section also discusses advanced technologies, including tactile sensing, smart materials, and artificial intelligence, which are driving the next generation of picking end-effectors. Finally, challenges and future trends for highly universal agricultural end-effectors are summarized. Humanoid picking hands represent an important direction for the development of universal picking end-effectors. The insights from this review are expected to accelerate the industrialization and large-scale adoption of robotic picking systems.

Strawberry picking relies primarily on manual labor, making it the most labor-intensive stage in strawberry cultivation. Harvesting robots have become essential for strawberry production, and fruit ripeness detection models are critical for picking operations. This study collected strawberry ripeness photographs under various natural environments and enhanced feature expression through diverse image enhancement techniques. Considering practical deployment on harvesting robots, the low-parameter, high-accuracy YOLOv8s was selected as the base model. Leveraging the ease of integration of the Global Attention Mechanism (GAM) within the YOLO model, we incorporated GAM before the SPFF module to enhance the extraction capabilities of both global and local features. Experimental results demonstrate that the improved YOLOv8s achieves excellent performance, with a mAP of 91.5% for three maturity classes and a frame rate of 53 FPS. Compared with other mainstream models, the improved YOLOv8s presented in this paper demonstrates superior detection performance, achieving mAP improvements of 12.1%, 8.0%, 6.1%, 4.6%, and 3.1% over YOLOv3, YOLOv5s, YOLOv7s, YOLOv8s, and CBAM-YOLOv8s, respectively. It also exhibits robust detection capabilities under varying lighting conditions and occlusions, meeting the demands for high precision and rapid performance during harvesting operations.

Intelligent pest detection has become a critical challenge in precision agriculture. Addressing the challenge of distinguishing between aphids, thrips, whiteflies, beet armyworms, spodopetra frugiperda, and spider mites during strawberry growth, this study establishes a small-sample multi-pest dataset for strawberries through field photography, open-source sharing, and web scraping. This study introduces a channel–space parallel attention mechanism (PCSA) into the UNet architecture. This improved UNet model accentuates pest color and morphology through channel-based attention and emphasizes spatial localization with coordinate-based attention, allowing for the comprehensive integration of global and local pixel information. Subsequently, comparative analysis of several color spaces identified HSV as optimal for pest recognition, with the “UNet + PCSA + HSV” approach achieving state-of-the-art results (IoU, 84.8%; recall, 89.9%; precision, 91.8%).

Accurate perception and 3D reconstruction of fruit tree branch structures are fundamental to smart orchard development, with broad applications in intelligent harvesting, crop phenotyping, and precision management. However, the slender and highly branched morphology, multi-scale distribution, weak surface texture, and severe occlusion inherent to fruit tree branches pose substantial challenges to high-fidelity modeling. This paper systematically reviews advances in branch feature extraction and 3D reconstruction for fruit tree canopies. A structured literature search was conducted using the Web of Science, Scopus, and Google Scholar databases, with search terms including “fruit tree branch”, “point cloud reconstruction”, “3D canopy modeling”, “branch feature extraction”, and “agricultural robotics”. Studies published between 2000 and 2025 were considered, with inclusion criteria requiring relevance to branch structure perception, reconstruction accuracy, or orchard application; non-peer-reviewed sources and studies lacking quantitative evaluation were excluded. We trace the evolution of feature extraction from classical 2D image processing and geometric fitting, through point cloud segmentation and skeleton extraction, to modern deep learning approaches and multimodal perception techniques. For 3D reconstruction, we compare active and passive sensing strategies alongside both explicit and implicit scene representation methods, discussing their respective strengths and applicable scenarios. A five-dimensional evaluation framework is also proposed, encompassing geometric accuracy, structural consistency, feature stability, computational efficiency, and generalization capability. Finally, we identify key bottlenecks in fine-grained structure recovery, occlusion handling, and cross-scene generalization, and highlight future directions in structural prior integration, multimodal collaborative modeling, and lightweight neural representations—offering a structured reference for advancing 3D perception research in smart orchards.

The integration of agricultural science, artificial intelligence, and robotics has accelerated the development of robotic arms, significantly enhancing their potential applications across various fields. In light of the unique characteristics of agricultural environments, this paper provides a comprehensive review of variable-stiffness control methods for robotic arms. A robotic arm with rigid–flexible switching capabilities can effectively address collision safety concerns in complex agricultural environments, offering promising research prospects. This paper outlines recent advancements in variable-stiffness control techniques, including passive control methods based on materials and flexible devices, active control methods based on algorithms, and hybrid methods that combine control algorithms with flexible devices. Additionally, it discusses the technical challenges and future opportunities regarding deploying variable-stiffness robotic arms in agricultural environments. The aim of this paper is to provide theoretical and technical insights to support the efficient and versatile development of agricultural robots.