Automatic-driving transport vehicle on structured road and control method

Abstract

The invention discloses an automatic-driving transport vehicle on a structured road and a control method. According to the automatic-driving transport vehicle and the control method disclosed by the invention, an image is read through a camera and transmitted to neural networks with different functions for calculation; all the neural networks are subjected to grouping and work division, and automatic driving, sign understanding, risk warning, human-computer interaction and other functions are realized; and inspired by bicycle sharing, a model parameter sharing platform is created to solve the problem that people waste time and energy in training a parameter model for enabling an automatic-driving vehicle to run on a road which is difficult for the neural networks to understand, and the utilization of resources is increased.

Description

technical field [0001] The invention belongs to the technical field of automatic driving, and in particular relates to a structured road automatic driving transport vehicle and a control method. Background technique [0002] Transportation has long been the propeller of social development. In 2016, Tmall Singles Day alone generated 657 million logistics orders. With the increasing volume of logistics and express delivery, the burden on couriers has also greatly increased. Due to the large amount of express delivery every day, it is difficult for the courier to get a rest even at noon. In addition, the courier must keep an eye on the mobile phone order when delivering goods for customers, and the delivery vehicles are prone to accidents. , making many people restless. [0003] Therefore, it is very important to use an express freight system that can reduce the logistics burden. The current solutions mainly include the following: [0004] Chinese invention patent 2016201087...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the above-mentioned deficiencies, and provide a structured road self-driving transport vehicle and a control method, so that the system can be completely unsupervised driving in most cases, and will automatically slow down and feed back information to people in emergency situations, and at the same time Aiming at the diversification of roads in my country and the time-consuming and cost-intensive training of model parameters, a model parameter sharing platform assisted by the automatic driving system was built.

Images