Fast convergence time is crucial for the path tracking control of autonomous agricultural vehicles (AAVs), enabling them to swiftly adapt to complex environments. In this work, we present a novel generalized proportional integral observer (GPIO)-based faster fixed-time control scheme, enhancing the rapid responsiveness of AAVs while effectively compensating for time-varying disturbances. Then, an auxiliary system is developed to mitigate the adverse effects of actuator saturation that may occur due to rapid response. Subsequently, a Lyapunov-based stability analysis is provided to demonstrate the fixed-time convergence of the AAV path tracking system. Finally, comparative experiments validate the superiority of the proposed control scheme.

Precise perception of crops and weeds is crucial for spot-spraying weeding (SSW). However, existing methods rely heavily on manually annotated data and are susceptible to lighting variations in agricultural environments, thereby limiting the robustness, stability, and real-time performance of SSW perception systems. To address these challenges, this study proposed Weedformer, a real-time perception frameworks that integrated crop contour extraction (CCEnet) with the weed index to enable precise segmentation and spraying of early-stage corn and weeds. First, CCEnet combined a lightweight pixel decoder (LPD) with a dual-core transformer decoder (DTD). This design preserved model compactness while substantially improving real-time contour extraction, reducing the model size to 31.5 MB while sustaining 57.2fps. In addition, we designed a Crop Contour Loss (CCL) to improve contour extraction by dynamically predicting key points. Overall, the model achieved an mAP of 98.49% and a recall of 96.32% for crop contour segmentation, outperforming existing models. Second, the proposed Weed Index converted the non-crop regions extracted by CCEnet to the YCrCb color space and incorporated VARI to extract weeds, thereby mitigating the effects of illumination variation on weed segmentation. Even without manual annotations, this method achieved a Dice score of 0.87 and an accuracy of 90.97% for weed segmentation. Experiments demonstrated that Weedformer achieved overall weed accuracy and HIT rates of up to 98.26% and 93.51%, respectively, in practical SSW systems, with pesticide savings reaching 42.44%. The proposed method provided a reliable technical foundation for achieving precise, targeted spot spraying with intelligent application equipment. The code for the proposed methods was open-sourced at: https://github.com/anqilin8/Weedformer.

To address the limitations of seeding quality monitoring methods under the seeding operation mode of cotton hill-drop planter without grain, this paper designed a seeding quality monitoring system that can eschew the traditional reliance on seed conductor. The system realizes real-time monitoring based on the differences in the cotton seeds' absorption of light of different wavelengths, and achieves accurate evaluation of seeding quality by obtaining the seeding quality parameters with multiple types of sensors. Bench tests showed the lowest accuracy of seeding rate monitoring was 97% and the highest accuracy of missed seeding monitoring was 95% while the field tests showed that the highest drop in the accuracy of seeding rate monitoring was 2.03 percentage, but the lowest accuracy of missed seeding monitoring is still above 91%. The system does not require the transformation of the equipment carrier, but has a high degree of equipment adaptability, which can meet the requirements on monitoring of cotton seeding. The monitoring method is effective and feasible, with high accuracy and stability.

The real-time images captured by agricultural machinery on-board monitoring equipment have complex backgrounds and different shooting angles. Especially for straw monitoring tasks, the utilization rate of images is relatively low. This paper presents a novel image classification and effective region segmentation method for straw returning in agriculture, leveraging semantic segmentation to enhance the efficiency of agricultural data analysis. The study addresses the challenges of manual straw cover analysis by proposing an automated approach to select images that meet monitoring standards. The methodology employs an encoder-decoder structure model, enriched with residual units, multi-scale convolution, and attention mechanisms. This model classifies images by calculating the pixel proportions of various scene categories and segments farmland areas to be inspected by incorporating distance information. The model's design is tailored to handle the complex and variable natural environments typical of vehicular monitoring scenarios, where semantic object boundaries can be fuzzy. The experimental results demonstrate that the proposed method achieves an overall sample classification accuracy of 93% for straw returning image classification and an 85.37% accuracy in dividing areas to be inspected. The method outperforms several mainstream semantic segmentation models, providing a more accurate and efficient means of processing agricultural monitoring images. The integration of distance information proves particularly beneficial in distinguishing the farmland areas under inspection, leading to clearer segmentation and more reliable data for agricultural decision-making. In conclusion, the study contributes to the field of agricultural intelligence by offering a robust method for image analysis that can be applied to optimize the use of straw return monitoring data.

To achieve the process of automatic film cutting for cotton and improve the efficiency of cotton precision film hole seeding machine operation, this paper proposes a wireless handle button control method and designs an automatic film and tape cutting system for cotton precision film-laying hole seeder. The system includes electromagnetic integrated valve group, hole opener lifting hydraulic cylinder, membrane pressing hydraulic cylinder, multifunctional hydraulic cylinder for cutting film, strapping support hydraulic cylinder, hydraulic limit sensor, arc-shaped film cutting shovel reset sensor, wireless control handle for film cutting and film cutting controller. The system is based on the VisualTFT platform, equipped with a multi-functional touch screen. By integrating functions such as obtaining the forward distance of the machine, hydraulic control principles, and wireless control models for film cutting and burying, it achieves automatic cutting and burying of ground film and drip tape processes. The experiment verified the working performance of the automatic film cutting and feeding system of the cotton seed precision film mulching hole seeder and the results showed that the average monitoring accuracy of the machine's forward distance was 98.16%; the response time for controlling the film cutting belt and burying film belt was <= 0.78 s, and the execution time was <= 2.68 s; the success rate of cutting film strips was 100.00% and the success rate of burying film strips was above 98.33%, which met the operational requirements of automatic film strip cutting for precise cotton seeding film hole planting machines.

To address the automatic navigation issue of unmanned agricultural tractors affected by unknown disturbances, a path-tracking control scheme is proposed by utilising fixed-time nonsingular terminal sliding mode and adaptive disturbance observer technique. Firstly, a path-tracking kinematic model is established, which considers the unknown disturbances. Secondly, unlike conventional sliding mode controllers, a novel fixed-time terminal sliding mode controller is proposed for the unmanned agricultural tractor, which effectively enhances the dynamic performance and reduce the chattering effect. Furthermore, to reduce the detrimental effects of unknown disturbances, a new adaptive disturbance observer is designed to estimate and compensate these unknown disturbances. Subsequently, a strict Lyapunov analysis is conducted to confirm that the lateral and heading offsets of the unmanned agricultural tractor under the adaptive disturbance observer-based fixed time nonsingular terminal sliding mode control scheme can be stabilised to the arbitrarily small neighbourhood near the origin within a fixed time. Finally, extensive experiments were carried out to verify the effectiveness and advantages of the proposed control scheme.

This article considers the problem of designing path following control for unmanned agricultural tractors (UATs) in the absence of heading information. First, an implementable observer is constructed to observe an unknown state that depends on heading information. Then, combing the constructed observer. an output-feedback path-following controller is designed, which can guarantee finite-time stability of the closed-loop pathfollowing system. The obvious advantage of the proposed control strategy is that it ensures the convergence of the lateral error and heading error to the origin in a finite time without the use of heading information, as verified by a rigorous Lyapunov theory. Finally, comprehensive simulations are presented to emphasize the superior following performance of the proposed strategy.

Aiming at improving the anti-disturbance capability and response speed of permanent magnet synchronous motor (PMSM) system, a novel adaptive gains generalized super- twisting controller (AGSTC) is constructed for speed loop. By introducing adaptive control gains into the generalized super- twisting algorithm (GSTA), the proposed AGSTC eliminates the requirement to determine the upper bound of disturbance. The proposed AGSTC improves the dynamic performance of the PMSM system. Experiments are carried out to present the effectiveness of the proposed AGSTC.

Efficient path tracking control for autonomous agricultural vehicles (AAVs) is the key technology for realizing agriculture 4.0 and precision agriculture, which makes smart farms more sustainable, profitable, and eco-friendly. It is well recognized that model nonlinearity, unknown disturbances, and wheel slipping are common problems in practical AAV systems in operation. To tackle these issues and improve the path tracking performance, a novel fixed-time generalized super-twisting control scheme is proposed for AAVs in this paper. First, a fixed-time integral sliding mode surface is designed for the considered vehicle by fusing the lateral offset and heading offset together. Then, an innovative auxiliary system dynamics is constructed to collaborate with the foregoing sliding mode surface, compensating for the adverse effects of wheel slipping effectively. Subsequently, based on the kinematic offset model of AAVs, a new type of generalized super-twisting controller is designed to achieve superior path tracking with robustness. Unlike existing super-twisting controllers, the generalized super-twisting continuous controller can fully eliminate chattering by replacing the previous discontinuous terms with a nonsmooth term. Further, rigorous theoretical analysis is conducted by raising a fresh Lyapunov function to verify the closed-loop control system stability. Finally, extensive field experiments have been carried out to show that the proposed control scheme significantly outperforms typical comparative control schemes.

To realize real-time monitoring of film laying process of cotton precision planter and improve intelligent level of cotton precision planter, based on advanced morphological filtering method and graphical programming of Labview software, a film laying quality monitoring system of cotton precision planter is designed. Using the Vision Assistant visual assistant, the system uses a color extraction function to convert colors to grayscale images. It uses LOOKup Table function and FFT filter function to perform grayscale transformation, binarization and advanced morphological filtering on it respectively. It then uses basic morphology to acquire various components in the plastic film image. It realizes the monitoring of parameters such as the width of the daylighting surface, the side length or seam length of the mechanical damaged part, and the width of the film edge covering soil. The performance test results of the film laying quality monitoring system showed that the system worked stably and reliably, the average monitoring accuracy of the width of the lighting surface and the width of the film edge covering soil reached more than 95%, and the average monitoring accuracy of the side length or the length of the seam at the mechanical damage part reached more than 88%. It solved the problems of difficulty in recognizing the similarity between the plastic film and the background interferer (soil, etc.) and could accurately detect the quality of the cotton film in real time. It effectively improved the operation quality and working efficiency of the cotton precision planter and met the practical requirements of film laying monitoring.

To improve the accuracy of the parameters used in the discrete element simulation test, this study calibrated the simulation parameters of cotton seeds by combining a physical test and simulation test. Based on the intrinsic parameters used for the physical test of cotton seed, according to the freefall collision method, inclined plane sliding method, and inclined plane rolling method, the contact parameters of cotton seeds and cotton seeds, stainless steel, and nylon were measured, respectively. The physical test of the accumulation angle and angle of repose of the cotton seeds was conducted. It was obtained to process the image of the seed pile with Matrix Laboratory software. The Plackett–Burman test was used to screen the significance of the simulation parameters. The optimal value range of the significant parameters was determined according to the steepest climbing test. The second-order regression model of the significant parameters, the stacking-angle error, and the angle-of-repose error were obtained according to the Box–Behnken design test. Taking the minimum stacking-angle error and angle-of-repose error as the optimization target values, the following optimal parameter combination was obtained: the interspecies collision recovery coefficient was 0.413, the interspecies static friction coefficient was 0.695, and the interspecies rolling friction coefficient was 0.214. Three repetitive simulation experiments were conducted to prove the reliability of the calibration results. The research results can be used for discrete element simulation experiments for cotton precision seed metering.

The implementation of precision agriculture is an important way to realize agricultural modernization, and precision fertilization technology is an important part of precision agriculture. The open-loop fertilization control system based on PID control algorithm improves the response speed of the fertilization motor, but the accuracy of fertilization control needs to be improved. In order to solve the problem of control accuracy of fertilizer application, this paper proposed a closed-loop control system of fertilizer application based on PID control algorithm, set up a fertilizer discharge test bench, compiled software with LabWindows, and took the value monitored by the flow sensor as the output value and negative feedback value, and carried out the closed-loop control experiment of fertilization flow. The test results showed that the response time of the system to achieve the target fertilizer flow rate was less than 4s. This system is more stable than the constant speed system and can significantly improve the control accuracy of the fertilizer rate.

针对渔场养殖投饲机工作时长短、锂电池欠压发现不及时、影响工作效率及降低电池使用寿命等问题,设计了基于LORA的远程投饲机电池管理系统,实现了渔场投饲机供电锂电池组单体电池的电压、温度、电流等实时检测反馈功能,及时根据锂电池状态进行充放电.该系统具有实时、准确、安全、高效等优点,可有效解决投饲机远距离工作充电不及时,影响工作效率等问题.试验数据及结果证明了该投饲机锂电池管理系统的准确性和安全性.

为适应精准农业的发展趋势,提高测产计量系统的精度,开发一套基于IMM-UKF算法的冲量式测产系统.该系统由冲量传感器模块、北斗定位模块、DTU传输模块和上位机等组成.系统通过传感器模块进行信号的采集和处理,采用CAN通信方式将处理后的数据发送至上位机.上位机使用IMM UKF滤波算法对传感器上传的数据进行滤波,最终根据标定曲线得到谷物产量.通过车辆空载试验,采用IMM-UKF算法与KF和UKF算法进行对比验证,结果表明IMM-UKF算法的滤波效果更好,均方差为0.00042 N.通过传感器标定试验,确定传感器的检测值与实际谷物重量的关系.通过大田测产试验,得出每个地块的产量分布图,试验结果表明该测产系统的平均误差达到3.911％.

针对因田间土壤质地不均匀或表面高低不平,无沟铺管机出现行驶偏摆而导致管道铺设弯曲的问题,设计了基于载波相位差分技术的北斗定位系统(Real Time Kinematic-BeiDou Navigation Satellite System,RTK-BDS)的导航控制系统.采用多模态控制策略,通过传感器检测无沟铺管机工作时的左、右行走马达速度,车辆实际平均车速,发动机功率和两侧行走泵的压力等状态参数,并输入到后向反馈(Back Propagation,BP)神经网络,预测铺管机当前状态分类,使用选择器选择模态控制参数,采用自适应比例-积分-微分(Proportion-Integral-Differential,PID)控制算法进行导航控制.经过田间试验,获取铺管机的模态控制参数和BP神经网络训练样本.导航控制系统上线试验结果表明,导航控制横向超调量为4.58 cm,最大横向误差在±4 cm范围内,平均横向误差在±1.5 cm范围内,能够满足铺管机直线性作业要求.