To analyze the droplet deposition under the influence of the flow field of an unmanned aerial vehicle (UAV), a hand-held three-dimensional (3D) laser scanner was used to scan 3D images of the UAV. Fluent software was used to simulate the motion characteristics of droplets and flow fields under the conditions of a flight speed of 3 m/s and an altitude of 1.5 m. The results indicated that the ground deposition concentration in the nonrotor flow field was high, the spray field width was 2.6 m, and the droplet deposition concentration was 50 to 200 ug/cm². Under the influence of the rotor flow field, the widest deposition range of droplets reached 12.8 m. Notably, the droplet deposition uniformity worsened, and the concentration range of the droplet deposition was 0 to 500 ug/cm². With the downward development of the downwash flow field, the overall velocity of the flow field gradually decreased, and the influence interval of the flow field gradually expanded. In this article, the droplet concentration was verified under simulated working conditions by a field experiment, thereby demonstrating the reliability of the numerical simulation results. This research could provide a basis for determining optimal UAV operating parameters, reducing the drift of droplets and increasing the utilization rate of pesticides. Keywords: Unmanned aerial vehicle (UAV), Aerial application, Downwash flow field, Droplet deposition, Simulation analysis.

The application of autonomous navigation in intelligent agriculture is becoming more and more extensive. Traditional navigation schemes in greenhouses, orchards, and other agricultural environments often have problems such as the inability to deal with an uneven illumination distribution, complex layout, highly repetitive and similar structures, and difficulty in receiving GNSS (Global Navigation Satellite System) signals. In order to solve this problem, this paper proposes a new tightly coupled LiDAR (Light Detection and Ranging) inertial odometry SLAM (LIO-SAM) framework named April-LIO-SAM. The framework innovatively uses Apriltag, a two-dimensional bar code widely used for precise positioning, pose estimation, and scene recognition of objects as a global positioning beacon to replace GNSS to provide absolute pose observation. The system uses three-dimensional LiDAR (VLP-16) and IMU (inertial measurement unit) to collect environmental data and uses Apriltag as absolute coordinates instead of GNSS to solve the problem of unreliable GNSS signal reception in greenhouses, orchards, and other agricultural environments. The SLAM trajectories and navigation performance were validated in a carefully built greenhouse and orchard environment. The experimental results show that the navigation map developed by the April-LIO-SAM yields a root mean square error of 0.057 m. The average positioning errors are 0.041 m, 0.049 m, 0.056 m, and 0.070 m, respectively, when the density of Apriltag is 3 m, 5 m, and 7 m. The navigation experimental results indicate that, at speeds of 0.4, 0.3, and 0.2 m/s, the average lateral deviation is less than 0.053 m, with a standard deviation below 0.034 m. The average heading deviation is less than 2.3°, with a standard deviation below 1.6°. The positioning stability experiments under interference conditions such as illumination and occlusion were carried out. It was verified that the system maintained a good stability under complex external conditions, and the positioning error fluctuation was within 3.0 mm. The results confirm that the robot positioning and navigation accuracy of mobile robots satisfy the continuity in the facility.

The vision-based recognition and localization system plays a crucial role in the unmanned harvesting of aquatic vegetables. After field investigation, factors such as illumination, shading, and computational cost have become the main difficulties restricting the identification and positioning of Brasenia schreberi. Therefore, this paper proposes a new lightweight detection method, YOLO-GS, which integrates feature information from both RGB and depth images for recognition and localization tasks. YOLO-GS employs the Ghost convolution module as a replacement for traditional convolution and innovatively introduces the C3-GS, a cross-stage module, to effectively reduce parameters and computational costs. With the redesigned detection head structure, its feature extraction capability in complex environments has been significantly enhanced. Moreover, the model utilizes Focal EIoU as the regression loss function to mitigate the adverse effects of low-quality samples on gradients. We have developed a data set of Brasenia schreberi that covers various complex scenarios, comprising a total of 1500 images. The YOLO-GS model, trained on this dataset, achieves an average accuracy of 95.7%. The model size is 7.95 MB, with 3.75 M parameters and a 9.5 GFLOPS computational cost. Compared to the original YOLOv5s model, YOLO-GS improves recognition accuracy by 2.8%, reduces the model size and parameter number by 43.6% and 46.5%, and offers a 39.9% reduction in computational requirements. Furthermore, the positioning errors of picking points are less than 5.01 mm in the X direction, 3.65 mm in the Y direction, and 1.79 mm in the Z direction. As a result, YOLO-GS not only excels with high recognition accuracy but also exhibits low computational demands, enabling precise target identification and localization in complex environments so as to meet the requirements of real-time harvesting tasks.

The flow path design problem is one of the most important issues of an automated guided vehicle (AGV) system design and control. A revised electromagnetism-like mechanism is proposed to solve the flow path design problem of unidirectional AGV systems under a reconfigurable manufacturing system environment in this paper. First, the formal model considering both loaded and empty travels is given. Then the preprocessing procedure for the guidepath network is proposed to improve the feasibility of solution and to reduce the computational complexity. In the revised electromagnetism-like mechanism, particles are encoded discretely, and Hamming distance based reduced variable neighbourhood search is adopted in the local search procedure. To reduce computation, only the best particle is searched in the local search procedure. In the moving procedure, each element of a particle is moved according to the ordering probability strategy. To verify the efficiency of the proposed algorithm, several computational experiments are carried out. The computational results show that the proposed algorithm is efficient, which is able to obtain optimal solutions to small scale problems and near optimal ones to large scale problems within reasonable computation time.