Xiaomin Yao

The accuracy and speed of tomato detection were increased to facilitate fully automated harvesting by improving the Real-Time Detection Transformer (RTDETR) to develop a new lightweight tomato detection model called LiteTom-RTDETR. This model employed RepViT as a lightweight backbone network instead of the original RTDETR backbone, considerably reducing both the number of parameters in and computational complexity of the model. Furthermore, a context guide fusion module was designed to enhance multiscale feature extraction efficiency, and an adaptive sliding weight mechanism was integrated into the loss function to mitigate class-imbalance issues. The proposed LiteTom-RTDETR model was shown to balance high tomato identification accuracy (88.2%) with an excellent real-time inference speed (52.2 frames per second) and computational efficiency (36.3 GFLOPs). Notably, the average detection accuracy of LiteTom-RTDETR was 0.6% higher, its detection speed was 15.5% faster, and its computational load and model size were 36.2% and 31.6% smaller, respectively, than those of the original RTDETR model. Therefore, the proposed model provides a practical approach for realizing visual recognition tasks in resource-constrained mobile automated tomato harvesting equipment.

The functionality of unmanned aerial vehicles (UAVs) in agricultural applications was improved by optimizing the parameters of the vector bracket in a vertical takeoff and landing UAV to maximize thrust and lift-to-drag ratio. First, the results of computational fluid dynamics simulations were compared with wind tunnel data to ensure an accurate model of the considered UAV, indicating a thrust coefficient error of less than 3% and a UAV lift-to-drag ratio error of less than 8%. Next, this model was applied to simulate the propeller thrust and UAV lift-to-drag ratio for 25 sample points selected using a central composite experimental design by varying the four structural parameters of the vector bracket. A kriging algorithm was subsequently applied to construct response surface models based on the results. Finally, a Multi-Objective Genetic Algorithm was employed to determine the optimal parameter values maximizing the two coefficients. The optimal structural parameters for the UAV vector bracket were determined to comprise a vector bracket height of 51 mm, fixed bracket length of 168 mm, fixed bracket width of 69 mm, and ball socket outer diameter of 31 mm. These values provided a 19% larger propeller thrust coefficient than those of the original UAV.

This study designed a vertical take-off and landing tailsitter unmanned aerial vehicle (UAV) with a long endurance time. Nine parameters of the tailsitter UAV were investigated. Using a 2^k full factorial test, 512 experiments on the nine parameters were conducted at their maximum and minimum values. The time coefficient and air resistance were calculated using the computational fluid dynamics (CFD) method under different parameter combinations. The analysis of variance determined that the specific factors influencing the time coefficient and air resistance were the root chord, wingtip chord, wingspan, and sweep angle. By carrying out a central composite design (CCD) test, 25 sample points of the four particular factors were constructed. The time coefficient and air resistance were simulated under different structural parameter combinations using the CFD method. CFD simulation was verified by carrying out a wind tunnel test, and the results revealed that the aerodynamic coefficient error was less than 5%, while the air resistance error was less than 6%. The response surface methodology (RSM) for the time coefficient and air resistance was established using a genetic aggregation method. A multi-objective genetic algorithm (MOGA) was used to optimize the parameters with regard to the maximum time coefficient and minimum air resistance. The optimal structural parameters were wing root chord length at 315 mm, wingtip chord length at 182 mm, wingspan length at 1198 mm, and sweep angle at 16°. Compared with the original layout and size, the time coefficient of the new design of the tailsitter UAV improved by 19.5%, while the air resistance reduced by 34.78%. The results obtained by this study are significant for the design of tailsitter UAVs.

We developed and tested an unmanned aerial vehicle-based gas sampling system (UGSS) for collecting gases and atmospheric particulate matter (PM). The system applies an alternative way of collecting both vertical and horizontal transects of trace gases in order to analyze them in the laboratory. To identify the best position of the UGSS intake port, aerodynamic flow simulations and experimental verifications of propeller airflow were conducted with an unmanned aerial vehicle (UAV) in hover mode. The UGSS will automatically replace the original gas in the system with gas from a target location to avoid the original gas being stored in the air bags. Experimental results show that the UGSS needs 5 s to replace the system’s own original gas using its pump. CO₂ and PM2.5/10 above the corn field are used as the test species to validate the accuracy of the CO₂ gas and PM concentrations collected by UGSS. Deming regression analyses showed good agreement between the measurements from the UGSS and the ground sampling station (y = 1.027x – 11.239, Pearson’s correlation coefficient of 0.98 for CO₂; y = 0.992x + 0.704, Pearson’s correlation coefficient of 0.99 for PM).The UGSS provides a measuring method that actively collects gases and PM for manual analyses in the laboratory.

An unmanned aerial vehicle (UAV) particulate-matter (PM) monitoring system was developed that can perform three-dimensional stereoscopic observation of PM2.5 and PM10 in the atmosphere. The UAV monitoring system was mainly integrated by modules of data acquisition and processing, wireless data transmission, and global positioning system (GPS). Particularly, in this study, a ground measurement-control subsystem was added that can display and store collected data in real time and set up measurement scenarios, data-storage modes, and system sampling frequency as needed. The UAV PM monitoring system was calibrated via comparison with a national air-quality monitoring station; the data of both systems were highly correlated. Since rotation of the UAV propeller affects measured PM concentration, this study specifically tested this effect by setting up another identical monitoring system fixed at a tower as reference. The UAV systems worked simultaneously to collect data for comparison. A correction method for the propeller disturbance was proposed. Averaged relative errors for the PM2.5 and PM10 concentrations measured by the two systems were 6.2% and 6.6%, respectively, implying that the UAV system could be used for monitoring PM in an atmosphere environment.