Analysis of Cargo Sorting Robot Based on Multiple Photoelectric Sensors

Abstract

With the rise of e-commerce, dangerous goods such as flammable and explosives carried in logistics goods have a negative impact on the development of the logistics industry and seriously threaten staff safety. Infrared is widely used in the logistics cargo security inspection system, which can detect the goods’ shape and internal temperature and analyze the type of goods through spectra. These characteristics help to determine whether it is a hazardous material. In this research, a photoelectric intelligent sorting robot based on an infrared sensor and a Charge Coupled Device (CCD) sensor is designed. The robot’s hardware system is first developed, and then its important components’ model selection is made. The cargo loading module is designed according to the size of the cargo to be sorted. The cargo information collection module comprises multi-infrared sensors and CCD sensors, and the robot’s hardware is logically connected. In the sorting process, the cargo information is required for model training, the SSD_inception network model is used for training, and the Sort_target data structure is defined to label different cargo information. In the test, the design-based robot, with the increase of measurement distance, the relative distance error of detecting cargo shows an increasing trend, but the error is within 5%. The cargo ID can be determined through the information received by multiple photoelectric level sensors, and they are placed in the designated area, thus successfully achieving the sorting of cargo.