In this paper, we review, compare, and analyze previous studies on agricultural machinery automatic navigation and path planning technologies. First, the paper introduces the fundamental components of agricultural machinery autonomous driving, including automatic navigation, path planning, control systems, and communication modules. Generally, the methods for automatic navigation technology can be divided into three categories: Global Navigation Satellite System (GNSS), Machine Vision, and Laser Radar. The structures, advantages, and disadvantages of different methods and the technical difficulties of current research are summarized and compared. At present, the more successful way is to use GNSS combined with machine vision to provide guarantee for agricultural machinery to avoid obstacles and generate the optimal path. Then the path planning methods are described, including four path planning algorithms based on graph search, sampling, optimization, and learning. This paper proposes 22 available algorithms according to different application scenarios and summarizes the challenges and difficulties that have not been completely solved in the current research. Finally, some suggestions on the difficulties arising in these studies are proposed for further research.

Tree roots are vital for tree ecosystems; accurate root detection helps analyze the health of trees and supports the effective management of resources such as fertilizers, water and pesticides. In this paper, a deep learning-based ground-penetrating radar (GPR) inversion method is proposed to simultaneously image the spatial distribution of permittivity for subsurface tree roots and layered heterogeneous soils in real time. Additionally, a GPR simulation data set and a measured data set are built in this study, which were used to train inversion models and validate the effectiveness of GPR inversion methods.The introduced GPR inversion model is a pyramid convolutional network with vision transformer and edge inversion auxiliary task (PyViTENet), which combines pyramidal convolution and vision transformer to improve the diversity and accuracy of data feature extraction. Furthermore, by adding the task of edge inversion of the permittivity distribution of underground materials, the model focuses more on the details of heterogeneous structures. The experimental results show that, for the case of buried scatterers in layered heterogeneous soil, the PyViTENet performs better than other deep learning methods on the simulation data set. It can more accurately invert the permittivity of scatterers and the soil stratification. The most notable advantage of PyViTENet is that it can accurately capture the heterogeneous structural details of the soil within the layer since the soil around the tree roots in the real scene is layered soil and each layer of soil is also heterogeneous due to factors such as humidity, proportion of different soil particles, etc.In order to further verify the effectiveness of the proposed inversion method, this study applied the PyViTENet to GPR measured data through transfer learning for reconstructing the permittivity, shape, and position information of scatterers in the actual scene. The proposed model shows good generalization ability and accuracy, and provides a basis for non-destructive detection of underground scatterers and their surrounding medium.

To address the problems of low recognition accuracy and slow processing speed when identifying harvest-stage cabbage heads in complex environments, this study proposes a lightweight harvesting period cabbage head recognition algorithm that improves upon YOLOv8n. We propose a YOLOv8n-Cabbage model, integrating an enhanced backbone network, the DyHead (Dynamic Head) module insertion, loss function optimization, and model light-weighting. To assess the proposed method, a comparison with extant mainstream object detection models is conducted. The experimental results indicate that the improved cabbage head recognition model proposed in this study can adapt cabbage head recognition under different lighting conditions and complex backgrounds. With a compact size of 4.8 MB, this model achieves 91% precision, 87.2% recall, and a mAP@50 of 94.5%—the model volume has been reduced while the evaluation metrics have all been improved over the baseline model. The results demonstrate that this model can be applied to the real-time recognition of harvest-stage cabbage heads under complex field environments.

Semantic segmentation of rural roads presents unique challenges due to the unstructured nature of these environments, including irregular road boundaries, mixed surfaces, and diverse obstacles. In this study, we propose an enhanced PP-LiteSeg model specifically designed for rural road segmentation, incorporating a novel Strip Pooling Simple Pyramid Module (SP-SPPM) and a Bottleneck Unified Attention Fusion Module (B-UAFM). These modules improve the model’s ability to capture both global and local features, addressing the complexity of rural roads. To validate the effectiveness of our model, we constructed the Rural Roads Dataset (RRD), which includes a diverse set of rural scenes from different regions and environmental conditions. Experimental results demonstrate that our model significantly outperforms baseline models such as UNet, BiSeNetv1, and BiSeNetv2, achieving higher accuracy in terms of mean intersection over union (MIoU), Kappa coefficient, and Dice coefficient. Our approach enhances segmentation performance in complex rural road environments, providing practical applications for autonomous navigation, infrastructure maintenance, and smart agriculture.

Reducing damage and missed harvest rates is essential for improving efficiency in unmanned cabbage harvesting. Accurate real-time segmentation of cabbage heads can significantly alleviate these issues and enhance overall harvesting performance. However, the complexity of the growing environment and the morphological variability of field-grown cabbage present major challenges to achieving precise segmentation. This study proposes an improved YOLOv8n-seg network to address these challenges effectively. Key improvements include modifying the baseline model’s final C2f module and integrating deformable attention with dynamic sampling points to enhance segmentation performance. Additionally, an ADown module minimizes detail loss from excessive downsampling by using depthwise separable convolutions to reduce parameter count and computational load. To improve the detection of small cabbage heads, a Small Object Enhance Pyramid based on the PAFPN architecture is introduced, significantly boosting performance for small targets. The experimental results show that the proposed model achieves a Mask Precision of 92.2%, Mask Recall of 87.2%, and Mask mAP50 of 95.1%, while maintaining a compact model size of only 6.46 MB. These metrics indicate superior accuracy and efficiency over mainstream instance segmentation models, facilitating real-time, precise cabbage harvesting in complex environments.