Search

The segmentation and extraction of oilseed rape crop rows are crucial steps in visual navigation line extraction. Agricultural autonomous navigation robots face challenges in path recognition in field environments due to factors such as complex crop backgrounds and varying light intensities, resulting in poor segmentation and slow detection of navigation lines in oilseed rape crops. Therefore, this paper proposes VC-UNet, a lightweight semantic segmentation model that enhances the U-Net model. Specifically, VGG16 replaces the original backbone feature extraction network of U-Net, Convolutional Block Attention Module (CBAM) are integrated at the upsampling stage to enhance focus on segmentation targets. Furthermore, channel pruning of network convolution layers is employed to optimize and accelerate the model. The crop row trapezoidal ROI regions are delineated using end-to-end vertical projection methods with serialized region thresholds. Then, the centerline of oilseed rape crop rows is fitted using the least squares method. Experimental results demonstrate an average accuracy of 94.11% for the model and an image processing speed of 24.47 fps/s. After transfer learning for soybean and maize crop rows, the average accuracy reaches 91.57%, indicating strong model robustness. The average yaw angle deviation of navigation line extraction is 3.76°, with a pixel average offset of 6.13 pixels. Single image transmission time is 0.009 s, ensuring real-time detection of navigation lines. This study provides upper-level technical support for the deployment of agricultural robots in field trials. [ABSTRACT FROM AUTHOR]

The application of robotics has great implications for future food security, sustainable agricultural development, improving resource efficiency, reducing chemical pesticide use, reducing manual labor, and maximizing field output. Aiming at the problems of high labor intensity and labor shortage in the fields of pesticide application, weeding, and field information collection, a multifunctional and electric field management robot platform is designed, which has four switching steering modes (Ackermann steering, four-wheel steering, crab steering, and zero-radius steering), and its wheel-track can be automatically adjusted. Commonly used spraying booms, weeders, crop information collectors, and other devices can be easily installed on the robot platform. A multi-sensor integrated navigation system including a satellite positioning system, an RGB camera, and a multi-line lidar is designed to realize the unmanned driving of the robot platform in a complex field environment. Field tests have shown that the robot can follow the set route, and tests under simulated conditions have indicated that it can also dynamically correct paths based on crop rows by using a visual system. Results from multiple trials showed that the trajectory tracking accuracy meets the requirements of various field management operations. [ABSTRACT FROM AUTHOR]

Aiming at the time-consuming, laborious, and inefficient process of removing abnormal rape plants during breeding, combined with the agronomic requirements for planting rapeseed, a clamping manipulator was designed. This manipulator is mainly composed of hollow splints, grip-force sensors, connecting rods, cylinders and other components. Additionally, a removing test platform was built. Single-factor and Box-Behnken experiments were conducted. Taking the output air pressure, pulling angle and pulling speed as the test factors, the rape uprooted removal rate, rape removal breakage rate and pulling force were the test indicators. Mathematical models for multiple regression were established separately for each evaluation index, and analysis of variance was conducted. Objective optimization was performed using the Numerical component to obtain the optimal combination of operating parameters: output air pressure of 0.47 MPa, pulling angle of 68.8° and extraction speed of 8 cm/s. The field validation test showed that the uprooted removal rate was 83.33%, the removal breakage rate was 6.67% and the pulling force was 84.9 N at the output air pressure of 0.5 MPa, pulling angle of 70° and pulling speed of 8 cm/s. The validation test values are in good agreement with the parameter optimization values, indicating that the parameter optimization model is reasonable. [ABSTRACT FROM AUTHOR]

When the boom sprayer works in the field, the boom must be parallel to the undulating ground or crop canopy. Aiming at the problem of low control accuracy and poor stability caused by parameter uncertainties and time-varying disturbances in the electro-hydraulic active boom suspension system, this paper proposes an adaptive robust precision control algorithm based on disturbance estimation. Firstly, the dynamic analysis modeling method is adopted to establish the nonlinear dynamic model and mechanism geometric equation of the pendulum active and passive suspension. Then, the controller was designed based on the nonlinear model of the suspension system. The proposed controller uses the backstepping design method to integrate the disturbance observer into the adaptive robust controller, which can effectively deal with the parameter uncertainties and time-varying disturbances in the suspension system model. Finally, a large number of experiments were carried out by taking a 28 m large boom active suspension driven by a single-rod hydraulic pressure as an example. Using an established rapid control prototype of a large boom suspension, a variety of control algorithm comparison experiments were carried out, and a 6-DOF motion platform was used to simulate the motion coupling interference of the sprayer chassis. The experiment results illustrate the high-performance characteristics of the proposed controller and improve the tracking performance of the active pendulum suspension system under various parameter uncertainties and time-varying disturbances. [ABSTRACT FROM AUTHOR]