The aging of the world’s population is causing older farmers familiar with agricultural practices to retire, resulting in a growing shortage of related labor. The ever-increasing labor shortage in traditional agriculture has reduced the manual sorting of agricultural products during processing and packaging. Delicate products such as cherry tomatoes pose a severe problem. This study proposes an artificial intelligence of things (AIoT) intelligent production line that leverages deep learning technology, the internet of things, and data analytics for fully automated and efficient 360-degree visual defect detection and classification of cherry tomatoes. By integrating image recognition and AIoT technology, the system can prevent the occurrence of defects during packaging, ensure consistent product quality during grading, and improve the reputation of agricultural producers. We achieved an outstanding mean average precision of 97.4% in the AIoT intelligent production line actual application in defect detection. The results showed that AIoT and intelligent screening plate mechanisms were advantageous for the detection of cherry tomatoes and help promote the development of delicate agricultural products. This study contributed to the development of intelligent agriculture by reducing labor and time costs, quickly detecting defects, effectively controlling sorting quality, and improving crop management through data analysis.

This research develops an amphibious transformable robot, Claw-Wheel IV, which could move on flat ground, uneven terrain, and aquatic environment. Compared to the previous version, Claw-Wheel III, the new generation has waterproof enclosure to adapt to watery environments and paddles are installed to produce underwater propulsion force, while the transformable idea and claw locomotion mechanism design are retained. Different kinds of gaits are designed and compared to reduce the vertical fluctuation of COM of the robot and run more smoothly. Advancing in aquatic environments relies on the paddles driven along with the rotating claws while steering is achieved with velocity differential between claws on both sides. Velocities of individual claws are computed and regulated based on gyration radius and angular velocity parameters obtained in experiments, in order to follow ideal trajectories.