Tray recognizing and positioning method for unmanned forklift

Abstract

The invention discloses a pallet recognition and positioning method for an unmanned forklift. The method comprises the following steps: S1, integrating a monocular camera and a single-line laser radar, calibrating the monocular camera and the single-line laser radar, and obtaining an internal parameter matrix and an external parameter matrix of the camera; s2, selecting and completing the trainingand deployment of a neural network system; s3, obtaining a two-dimensional coordinate and an internal reference matrix of the vertex of the tray recognition frame through a neural network, and obtaining connecting lines between the left and right sides of the tray and the optical center of the camera and an included angle between the connecting lines and the optical axis of the camera; s4, projecting the point cloud to a camera coordinate system according to the single-line laser radar ranging information and the external parameter matrix, filtering the point cloud under the camera coordinatesystem according to the included angle, and reserving the point cloud corresponding to the tray; and S5, performing linear detection on the point cloud corresponding to the tray by utilizing Hough transform, and fitting two-dimensional coordinates of the front surface of the tray and the central point of the front surface of the tray and an inclination angle of the front surface of the tray in acamera coordinate system.

Description

technical field [0001] The invention relates to the technical field of intelligent identification and positioning, in particular to a pallet identification and positioning method for unmanned forklifts. Background technique [0002] In the context of the era of intelligence, with the continuous change of robot technology and artificial intelligence technology, the manufacturing industry and warehousing logistics industry are gradually transforming towards intelligence, unmanned, and autonomous. As the above-mentioned industries, intelligent logistics is moving towards intelligence The important foundation of the company has made great progress and development. As the basic implementation form of intelligent logistics, unmanned forklifts are widely used in work scenarios such as material transportation, warehousing, and cargo loading and unloading. They can adapt to different working environments and complete high-intensity tasks. [0003] The essence of an unmanned forklift...

AI Technical Summary

Problems solved by technology

At present, in the research on unmanned forklifts, the identification and positioning of pallets usually adopt binocular vision, laser radar, millimeter wave radar and other depth sensors and monocular vision fusion schemes. Such schemes can realize unmanned forklifts within a certain range. Pallet identification and positioning, but there are still obvious deficiencies in computing resource consumption, object positioning accuracy, effective positioning distance and cost, etc.

Since unmanned forklifts are constrained by issues such as cost, volume, power consumption, and operating efficiency, the computing power of the terminal computing equipment equipped on them is very limited. Therefore, the pallet identification and positioning method using the above scheme is expensive, consumes a lot of computing resources, and has poor real-time performance. , it is difficult to effectively complete pallet identification and positioning under the actual working conditions of unmanned forklifts

Images