Unmanned vehicle guiding method, system and device based on limb movement instruction

Abstract

The invention provides an unmanned vehicle guiding device based on a limb movement instruction, and the device comprises the steps: guiding a person to give a limb movement representing a preset instruction to an unmanned vehicle nearby the unmanned vehicle to be guided; acquiring an image containing the limb movement in real time, and extracting the limb movement instruction; analyzing and matching an actual instruction represented by the limb action through an action instruction matching system, wherein the instruction is used as a control instruction of the unmanned vehicle; and enabling the unmanned vehicle to perform a corresponding automatic driving action according to the actual instruction. The invention further provides an unmanned vehicle guiding system and device based on the limb movement instruction, driverless persons can be allowed to guide the driverless vehicles only through the simple limb movement instruction, the formation efficiency of the driverless vehicles is greatly improved, and meanwhile the labor cost is reduced.

Description

technical field [0001] The present invention relates to the technical field of unmanned driving, and in particular, relates to an unmanned vehicle guidance method, system and device based on body movement instructions. Background technique [0002] With the rapid development of unmanned driving technology, fleet driving is a solution to reduce completely unmanned driving. In traditional fleet driving, the driver follows the car into the formation, which leads to high labor costs and low formation efficiency. Aiming at the traditional multi-vehicle formation method that requires the formation personnel to manually drive each vehicle into the formation before being towed by the lead vehicle, a method of realizing unmanned vehicle guidance by other means without relying on the driver is proposed. [0003] After searching, it is found that the application number is 201711240940.8, and the application date is 2017-11-30. The Chinese patent application "UAV-based guidance system ...

AI Technical Summary

Problems solved by technology

Although this application can effectively recognize traffic police gestures, because it uses a deep learning network model for training, the replaceability of gesture commands is low, and the cost of replacement is relatively high. In terms of direction control, multiple gesture command interactions are required. Boot efficiency is low

In addition, the vehicle-mounted workstation is not easy to disassemble, the replaceability is poor, and the transfer of the device is also inconvenient, and the price is not competitive to a certain extent.

[0005] The above-mentioned patent solutions have limitations in the applicable environment. Although they can achieve the purpose of guiding the vehicle through the interaction between the human / drone and the vehicle, no matter in terms of the guidance efficiency of the unmanned vehicle or the cost of the system and hardware None are competitive enough and not universal

[0006] At present, there is no description or report of the similar technology of the present invention, and no similar data at home and abroad have been collected yet.

Images