Weeds are among the major factors that could harm crop yield. Site-specific weed management has become an effective tool to control weed and machine vision combined with image processing is an effective approach for weed detection. In this work, an encoder-decoder deep learning network was investigated for pixel-wise semantic segmentation of crop and weed. Different input representations including different color space transformations and color indices were compared to optimize the input of the network. Three image enhancement methods were investigated to improve model robustness against different lighting conditions. The results show that for images without enhancement, color space transformation and vegetation indices without NIR (Near Infrared) information did not improve the segmentation results, while inclusion of NIR information significantly improved the segmentation accuracy, indicating the effectiveness of NIR information for precise segmentation under weak lighting condition. Image enhancement improved the image quality and consequently the robustness of segmentation models against different lighting conditions. The best MIoU value for pixel-wise segmentation was 88.91% and the best mean accuracy of object-wise segmentation was 96.12%. The deep network and image enhancement methods applied in this work provided promising segmentation results for weed detection and did not need large amount of data for model training, which is suitable for site-specific weed management.

To decrease the impact of uncertainty disturbance such as sideslip from the field environment on the path tracking control accuracy of an unmanned rice transplanter, a path tracking method for an autonomous rice transplanter based on an adaptive sliding mode variable structure control was proposed. A radial basis function (RBF) neural network, which can precisely approximate arbitrary nonlinear function, was used for parameter auto-tuning on-line. The sliding surface was built by a combination of parameter auto-tuning and the power approach law, and thereafter an adaptive sliding controller was designed. Based on theoretical and simulation analysis, the performance of the proposed method was evaluated by field tests. After the appropriate hardware modification, the high-speed transplanter FLW 2ZG-6DM was adapted as a test platform in this study. The contribution of this study is providing an adaptive sliding mode path tracking control strategy in the face of the uncertainty influenced by the changeable slippery paddy soil environment in the actual operation process of the unmanned transplanter. The experimental results demonstrated that: compared to traditional sliding control methods, the maximum lateral deviation was degraded from 17.5 cm to 9.3 cm and the average of absolute lateral deviation was degraded from 9.1 cm to 3.2 cm. The maximum heading deviation was dropped from 46.7° to 3.1°, and the average absolute heading deviation from 10.7° to 1.3°. The proposed control method not only alleviated the system chattering caused by uncertain terms and environmental interference but also improved the path tracking performance of the autonomous rice transplanter. The results show that the designed control system provided good stability and reliability under the actual rice field conditions.

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.

The sampling-based Kalman filters have been widely used for GNSS/INS of land vehicle navigation. Although many nonlinear filters are proposed by employing different approximate algorithms, most of the filters update sigma points utilize the moments match and Bayesian filter update framework. In this paper, cubature Kalman filters (CKFs) based on a class of novel sigma-point update framework (NSUF) are developed and compared in terms of accuracy and convergence rate. In order to enhance the reliability of GNSS/INS, an improved CKF, named as ArtCKF is proposed by merging the moments generated by different NSUFs, which not only addresses the problem of observation missing but also improves the efficiency of Bayesian filter update. Numerical simulation based on field test data is employed to verify the superiority of ArtCKF in land vehicle navigation. Our results indicate that the ArtCKF improves the heading of land vehicle by 71.3% compared with CKF, and makes a tradeoff between direct observable and non-direct observable state estimation under GNSS-challenged environment.

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.