Research on Intelligent Logistics Sorting Robot Control Based on Machine Vision

As the information era advances, robotic intelligent sorting is being applied more and more in the logistics sector. As such, studying vision-based autonomous identification, localization, grasping, and sorting mobile sorting robot systems is crucial. In order to accomplish the function of motion ranging and positioning, this paper uses a camera mounted at the end of an industrial robot to continuously shoot single-point images of various locations within the world coordinate system. The parameters obtained are similar to those of binocular vision ranging. The vision library (OpenCV for Python) is used to process the image data for an automatic sorting operation of cylindrical workpieces that is currently in place. The point-by-point sampling calculation is carried out within the robot’s running trajectory. According to the experimental results, the monocular motion vision ranging and localization system performs well, with an average localization error of less than 4%. The ranging method can also meet accuracy requirements under some conditions, which is useful in lowering the automatic sorting system’s upgrade costs.