Smart agriculture development mainly depends on the intelligence and reliability of autonomous agricultural machinery. Automatic navigation systems (ANSs) play a key role in intelligent agricultural machinery design, as they not only reduce farmers’ workloads but also improve their land utilization rates. In this paper, a tractor ANS based on dynamic path search and a fuzzy Stanley model (FSM) was designed, and its capability for whole-field path tracking was tested. First, the tracking performance of the steering control module was validated after the automatic reconstruction of the tractor platform. Then, a navigation decision system was established based on a unified reference waypoint search framework, where the path generation for whole-field coverage was presented. Finally, the gain coefficient of the Stanley model (SM) was adjusted adaptively according to the tracking error by utilizing the fuzzy logic controller. Subsequently, the developed tractor ANS was tested in the field. The experiment’s results indicate that the FSM outperformed the SM in straight path tracking and whole-field path tracking. When the tractor traveled at a speed of 1 m/s, the maximum lateral tracking error for the straight path was 10 cm, and the average lateral tracking error was 5.2 cm, showing improvements of 16.7% and 10.3% compared to the SM. Whole-field autonomous navigation showed that the maximum lateral tracking error was improved from 34 cm for the SM to 27 cm for the FSM, a reduction of approximately 20.6%, illustrating the superiority of the FSM in the application of whole-field path tracking. As the maximum tracking error of whole-field autonomous navigation appears in the turning stage, where tractors often stop working, the designed ANS satisfies the requirements of a self-driving system for unmanned tractors.

Flower thinning for fruit trees in time is an important operation to keep a suitable quantity of fruits and guarantee the quality of fruits. Accurate detection of flower density is the premise of precise flower thinning, and machine vision provides an effective approach to achieving the accurate identification of flower density. To detect the flower density on the proximal side of Y-shaped densely planted peach trees accurately, this study proposed a method based on an RGBD camera and a convolutional neural network that incorporated an attention mechanism and multi-scale feature fusion. Firstly, image acquisition and preprocessing were performed with the RGBD camera, and the complex background and distal flowers were filtered out through depth information. Then, a convolutional neural network for flower density detection based on an attention mechanism and multi-scale feature fusion, named the flower counting network (FC-Net), was constructed and tested. Results showed that the coefficient of determination (R²) between the estimated number of flowers by the FC-Net and the real values reached 0.95, the mean absolute error (MAE) was 4.3, the root mean square error (RMSE) was 5.65, the counting error rate (Er) was 0.02%, and the processing time of one image was 0.12 s. The proposed FC-Net can provide visual support for intelligent mechanical flower thinning operations.

Aiming at solving the problems of inaccurate tillage depth detection and unstable tillage depth control, this study proposes a tillage depth detection and control method based on attitude estimation and online calibration of model parameters. First, a tillage depth detection model based on the attitude measurement of the plow is established. The attitude estimation method is designed to measure the horizontal attitude of the plow. An adaptive Kalman filter is utilized to perform an online calibration of the model parameters between the rotation angle of the lifting arm and the pitch angle of the plow. The dynamic and accurate detection of tillage depth is achieved using the tillage depth detection model. Second, a tillage depth control device using an STM32 microcontroller is developed in this study. The PID controller controls the tractor’s suspension system to adjust the plow through the solenoid valve, thus achieving stable control of the tillage depth. Finally, the experimental results obtained from simulation and field tests show that the tillage depth can be stably controlled within the set target interval during the tractor plowing operation, proving the effectiveness and feasibility of the proposed tillage depth detection and control method.

Rapeseed is one of the primary oil crops; yet, it faces significant threats from weeds. The ideal method for applying herbicides would be selective variable spraying, but the primary challenge lies in automatically identifying weeds. To address the issues of dense weed identification, frequent occlusion, and varying weed sizes in rapeseed fields, this paper introduces a STBNA-YOLOv5 weed detection model and proposes three enhanced algorithms: incorporating a Swin Transformer encoder block to bolster feature extraction capabilities, utilizing a BiFPN structure coupled with a NAM attention mechanism module to efficiently harness feature information, and incorporating an adaptive spatial fusion module to enhance recognition sensitivity. Additionally, the random occlusion technique and weed category image data augmentation method are employed to diversify the dataset. Experimental results demonstrate that the STBNA-YOLOv5 model outperforms detection models such as SDD, Faster-RCNN, YOLOv3, DETR, and EfficientDet in terms of Precision, F1-score, and mAP@0.5, achieving scores of 0.644, 0.825, and 0.908, respectively. For multi-target weed detection, the study presents detection results under various field conditions, including sunny, cloudy, unobstructed, and obstructed. The results indicate that the weed detection model can accurately identify both rapeseed and weed species, demonstrating high stability.

Current methods to control the spraying quantity present several disadvantages, such as poor precision, a long adjustment time, and serious environmental pollution. In this paper, the flow control valve and the linear active disturbance controller (LADRC) were used to control the spraying quantity. Due to the disturbance characteristics in the spraying pipeline during the actual operation, the total disturbance was observed by a linear extended state observer (LESO). A 12 m commercial boom sprayer was used to carry out practical field operation tests after relevant intelligent transformation. The experimental results showed that the LADRC controller adopted in this paper can significantly suppress the disturbance in practical operation under three different operating speeds. Compared with the traditional proportional–integral–differential controller (PID) and an improved PID controller, the response speed of the proposed controller improved by approximately 3~5 s, and the steady-state error accuracy improved by approximately 2~9%.

Autonomous driving solutions for agricultural machinery have advanced rapidly; however, large-wheeled harvesters present unique challenges compared to traditional vehicles. Specifically, the 5.4 m cutting width, 9.2 m minimum turning diameter, and rear-wheel–steered configuration demand specialized path tracking and steering methods. To address these challenges, this study developed an integrated system combining feedforward PID and Look-Ahead Ackermann (LAA) algorithms with sensors, actuators, and an embedded control platform. Field experiments indicated that the system maintained an average lateral deviation of approximately 5 cm on straight-line paths, with slightly larger errors observed only during turning or alignment maneuvers. Additionally, a “three-cut” steering method was implemented, which enhanced path tracking accuracy and prevented crop damage at headland turns. Successful field tests confirmed the robustness of the developed system, highlighting its practical potential for production-level autonomous harvesting.