Vehicle driving method and device, computer equipment and vehicle

Abstract

The invention relates to a vehicle driving method and device, computer equipment and a vehicle. The method comprises the steps that multiple environment recognition results and multiple pieces of vehicle information are acquired, wherein the plurality of environment recognition results comprise a vehicle environment recognition result obtained by recognizing the surrounding environment informationof the vehicle through deep learning by the vehicle and an environment recognition result obtained by recognizing the surrounding environment information of the vehicle through deep learning by at least one preceding vehicle, and the vehicle information comprises vehicle information and preceding vehicle information of at least one preceding vehicle; and a driving instruction is generated according to the plurality of environment recognition results and the plurality of pieces of vehicle information, and the vehicle is controlled to execute the driving instruction. Both the device and the computer equipment are carriers for implementing the method, and the vehicle comprises the device or the computer equipment. Decision is made by combining the Internet of Vehicles shared information andthe deep learning condition of the Internet of Vehicles, and the proper driving instruction is output, so that the vehicle driving decision accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a vehicle driving method and device thereof, computer equipment, and a vehicle. Background technique [0002] Deep learning is a method based on representational learning of data in machine learning. Its motivation is to establish and simulate a neural network that simulates the human brain for analysis and learning. It imitates the mechanism of the human brain to explain data. In the field of vehicles, deep learning is mainly applicable to the learning of vehicle driving rules and the learning of surrounding environment predictions. For the driver, the source of deep learning consists mainly of pre-trained models as well as models learned in real-world environments. Furthermore, with the development of vehicle technology, a scheme based on the Internet of Vehicles to share vehicle information is proposed. Using the Internet of Vehicles, drivers can obtain relevant inf...

AI Technical Summary

Problems solved by technology

Furthermore, with the development of vehicle technology, a scheme based on the Internet of Vehicles to share vehicle information is proposed. Using the Internet of Vehicles, drivers can obtain relevant information about other vehicles around them, such as the vehicle in front. The relevant information includes whether they can pass through the traffic lights ahead, etc.; In fact, the sharing and transmission of information takes a certain amount of time, and the environment changes in real time. For example, the street light at the intersection ahead is red, and the vehicle in front informs the vehicle behind to stop through the Internet of Vehicles, but when the shared information reaches the vehicle behind, It is possible that the red light turns green, and the vehicles behind can pass slowly

Images