When an octopus grasps something, the rigidity of its tentacle can change greatly, which allowing for unlimited freedom, agility, and precision. Inspired by this, a three-finger flexible bionic robot gripper was designed for apple picking. First, a flexible chamber finger was designed to drive the gripper finger to elongate, shorten, and bend, which works through a process of inflating and deflating. Further, we proposed a three-finger mode to achieve two kinds of motion states: grasping and relaxing, by simulating the movement of an octopus grasping at something. In this paper, we evaluated the bending property of the designed flexible bionic gripper through an apple grasping experiment. The experimental results show that the 100.0 g bionic gripper can load an apple with a weight of 246.5~350.0 g and a diameter of 69.0~99.0 mm, and the grasping success rate is 100%. It has a good grasping performance. Compared to other soft grippers, the proposed bionic flexible gripper has the advantages of being lightweight, and having good cushioning, low driving air pressure, and a strong grasping force.

Insect pest management is one of the main ways to improve the crop yield and quality in agriculture and it can accurately and timely detect insect pests, which is of great significance to agricultural production. In the past, most insect pest detection tasks relied on the experience of agricutural experts, which is time-consuming, laborious and subjective. In rencent years, various intelligent methods have emerged for detection. This paper employs three frontier Deep Convolutional Neural Network (DCNN) models—Faster-RCNN, Mask-RCNN and Yolov5, for efficient insect pest detection. In addition, we made two coco datasets by ourselves on the basis of Baidu AI insect detection dataset and IP102 dataset, and compared these three frontier deep learning models on the two coco datasets. In terms of Baidu AI insect detection dataset whose background is simple, the experimental results strongly recommend Yolov5 for the insect pest detection, because its accuracy reaches above 99% while Faster-RCNN’s and Mask-RCNN’s reach above 98%. Meanwhile, Yolov5 has the faster computational speed than Faster-RCNN and Mask-RCNN. Comparatively speaking, with regard to the IP102 dataset whose background is complex and categories are abundant, Faster-RCNN and Mask-RCNN have the higher accuracy, reaching 99%, than Yolov5 whose accuracy is about 97%.

Nitrogen is a vital ingredient for plant development and growth. It is one of the most crucial indicators of soil fertility and crop growth conditions. For the monitoring of nitrogen loss patterns and the development of crop nitrogen fertilizer application strategies, an accurate determination of soil nitrogen concentration can be a valuable source of information. For the advancement of precision agriculture and the preservation of the natural ecological environment, an accurate, quick, and low-cost determination of soil nitrogen content and its variations is essential. This paper systematically analyzes and summarizes soil nitrogen detection methods by compiling and analyzing the relevant literature, comparing the advantages and disadvantages of various methods, and concluding with a discussion of the most significant challenges and future research trends in this field. This study provides a helpful resource for understanding the current status, application constraints, and future developments of nitrogen-sensing technologies in precision agriculture.

Agriculture is important for ecology. The early detection and treatment of agricultural crop diseases are meaningful and challenging tasks in agriculture. Currently, the identification of plant diseases relies on manual detection, which has the disadvantages of long operation time and low efficiency, ultimately impacting the crop yield and quality. To overcome these disadvantages, we propose a new object detection method named “Plant Leaf Detection transformer with Improved deNoising anchOr boxes (PL-DINO)”. This method incorporates a Convolutional Block Attention Module (CBAM) into the ResNet50 backbone network. With the assistance of the CBAM block, the representative features can be effectively extracted from leaf images. Next, an EQualization Loss (EQL) is employed to address the problem of class imbalance in the relevant datasets. The proposed PL-DINO is evaluated using the publicly available PlantDoc dataset. Experimental results demonstrate the superiority of PL-DINO over the related advanced approaches. Specifically, PL-DINO achieves a mean average precision of 70.3%, surpassing conventional object detection algorithms such as Faster R-CNN and YOLOv7 for leaf disease detection in natural environments. In brief, PL-DINO offers a practical technology for smart agriculture and ecological monitoring.

Picking robot technology plays an important role in the rapid promotion of precision agriculture. The development of a successful robot gripper is critical for the final promotion and industrialization of the tomato picking robot. This paper investigated the cluster tomato picking strategy and the gripper structure design based on this strategy to address the problem of poor adaptability of the existing gripper design in the cluster tomato picking scene. Starting from the research on the behavior of artificially picking cluster tomatoes, the grasping method, finger structure parameters and picking movement pattern of the human hand are analyzed. The evaluation criteria of the gripper are summarized, a simplified mathematical model of the gripper is established, and the picking strategy under the model of the gripper is proposed. Furthermore, according to the simplified gripper model, a rigid-flexible coupling gripper structure is designed, and the gripping simulation analysis is carried out. According to the simulation results, the gripper can smoothly grab medium and large tomatoes with diameter of 65∼95 mm. The peak force and fluctuation force of tomato with different sizes during grasping were less than the tomato’s minimum damage force. The gripper has adaptability and stability characteristics, providing technical support for gripper manufacturing and the construction of a picking system for a tomato picking robot.

Marbling is a crucial indicator that significantly impacts beef quality grading. Currently, Chinese beef processing enterprises rely on professional graders who visually assess marbling using national standard atlases. However, this manual evaluation method is highly subjective and time consuming. This study proposes a beef marbling grading algorithm based on an enhanced YOLOv8x model to address these challenges. The model integrates a convolutional neural network (CNN) augmented with an improved attention mechanism and loss function, along with a Region-of-Interest (ROI) preprocessing algorithm to automate the marbling grading process. A dataset comprising 1300 beef sample images was collected and split into training and test sets at an 8:2 ratio. Comparative experiments were conducted with other deep learning models as well as ablation tests to validate the proposed model’s effectiveness. The experimental results demonstrate that the improved YOLOv8x achieves a validation accuracy of 99.93%, a practical grading accuracy of 97.82%, and a detection time of less than 0.5 s per image. The proposed algorithm enhances grading efficiency and contributes to intelligent agricultural practices and livestock product quality assessment.