Unmanned Lane Keeping Method and Device, Computer Device, and Storage Medium

The present disclosure relates to an unmanned lane keeping method and device, a computer device, and a storage medium. The method includes that: a vehicle road image collected by a data collector of the vehicle is received; the vehicle road image is transmitted to a preset DNN model of the vehicle for processing to obtain a steering wheel angle corresponding to the vehicle road image, wherein the DNN model of the vehicle is established by deep learning, and is used for characterizing a correspondence between the vehicle road image and the steering wheel angle; and the vehicle is controlled to keep driving in a corresponding lane according to the steering wheel angle.