Vision-based forklift AGV high-precision positioning system and method

Abstract

The invention discloses a vision-based forklift AGV high-precision positioning system which is used for solving the problems that in the prior art, the cost for identifying the forklift position is high, and the system error is large. The system comprises a forklift, a plurality of light sources, an imaging system and a plurality of image sensors, the light sources, the imaging system and the multiple image sensors are arranged at the bottom of the forklift; the multiple light sources are used for emitting light with the wavelength within the preset range; the imaging system is used for imaging a working road surface of a forklift AGV and generating corresponding image information; and the multiple image sensors are used for conducting preset vision feature extraction on the image information according to the preset sampling time interval according to a preset feature extraction algorithm, preset vision features are calculated according to a preset displacement algorithm, and displacement information of the current forklift AGV is obtained. The system is low in cost; the manner of obtaining positioning information based on images is in a non-contact type, and the reliability of thesystem can be increased; and based on the manual sign assistance, work in a great working space can be achieved, and convenience is brought to design of an AGV path.

Description

technical field [0001] The invention relates to the field of image processing and sensor technology, in particular to a vision-based system and method for high-precision positioning of forklift AGVs. Background technique [0002] AGV (Automated Guided Vehicle) refers to a transport vehicle equipped with automatic guidance devices such as electromagnetic or optical, capable of driving along a prescribed guiding path, with safety protection and various transfer functions, and does not require a driver's handling in industrial applications Cars generally use batteries as their power source. In order to achieve the goal of automatic guidance, AGV needs to detect its own position in real time and send it to the host computer or server. At present, the positioning methods that can be applied on AGV are based on several typical methods such as magnetic strips, lasers, and images. [0003] The method based on the magnetic strip guides the AGV by laying strips containing magnetic m...

AI Technical Summary

Problems solved by technology

All of these methods require large changes to the ground. When the business needs change, it will cost a certain amount of money to modify the layout. In addition, the patterns laid on the ground are prone to stains after a period of use, making identification difficult. This is the method of this type. inherent flaws

Images