Instant training track guiding system and method

Abstract

The invention discloses an instant training track guiding system and method. The instant training track guiding system comprises an image input module, a deep learning training module and a control module. The image input module comprises a plurality of image input units arranged on a self-propelled device. When the self-propelled device is controlled to travel along a tracking line, the image input module obtains a plurality of image data pieces related to the tracking line through the plurality of image input units. The deep learning training module is coupled to the image input module and is used for performing deep learning training according to the plurality of image data pieces to generate a result model. The control module is coupled to the deep learning training module and the self-propelled device respectively, and is used for predicting and controlling the advancing direction of the self-propelled device according to the result model, so that the self-propelled device can automatically advance along the tracking line.

Description

technical field [0001] The present invention is related to trail following, in particular to a real-time training trail guiding system and method. Background technique [0002] Generally speaking, the application of the existing trajectory guidance system can be roughly divided into the following two categories: one is the trajectory guidance applied to the walking aid of the visually impaired, and the other is applied to the factory production line. Trajectory guidance for automatic pallet trucks. Regardless of the above-mentioned applications, most of the known trajectory guidance systems still use traditional computer vision methods for image processing and data calculation. [0003] However, under the above-mentioned processing method, once the light in the environment changes significantly or is in a dynamic environment, for example, the implementation site is in an outdoor environment or in a production line environment with frequent personnel activities, it is likely...

AI Technical Summary

Problems solved by technology

However, once the tracking line is worn or dirty, this magnetic or optical identification method is likely to make a misjudgment and lead to a deviation in the direction of travel of the automatic transport vehicle

Furthermore, if the route needs to be changed, it is relatively difficult to re-arrange the magnetic strip navigation, and the existing optical navigation must be equipped with other equipment, such as radio frequency identification (RFID) to set up multiple routes. It is cumbersome and cost-intensive to determine and deal with intersections

[0005] In addition, for trajectory guidance tasks that require high safety and reliability, such as navigation for the blind, there is still no guidance equipment that can completely replace blind guide bricks

However, the existing guide bricks require relatively high construction and maintenance costs, and may cause inconvenience to users of other barrier-free facilities (such as wheelchair users)

Images