Automatic driving vehicle driving method with backup path

Abstract

The invention discloses an automatic driving vehicle driving method with a backup path. The automatic driving vehicle driving method comprises the following steps of pre-storing the backup path of a vehicle traveling under specific road scenes in an automatic driving control system of the vehicle; whether the vehicle travels under the specific road scenes or not is judged in real time; if yes, combining a path planned through sensing by the control system with the backup path for driving; and if not, performing driving according to the path planned through sensing by the control system. The specific road scenes refer to a shunting turnout and a ramp. By means of the automatic driving vehicle driving method with the backup path, under specific rod scenes such as the shunting turnout, the pre-stored backup path can be used to instruct vehicle driving, so that the driving of an autonomous vehicle conforms to human driving habit, and meanwhile, the safety of automatic driving is improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving vehicles, in particular to a driving method for an automatic driving vehicle with a backup route. Background technique [0002] Autonomous driving vehicles use perception technology to plan driving routes during driving. Perception can mainly identify pedestrians, signs, lane lines and obstacles on the road, and then plan the vehicle's driving trajectory based on the obtained road information. However, , perception can only recognize the existence of real people or objects visible to the naked eye, so it cannot guide the vehicle to drive in a way that conforms to human driving habits. At the same time, perception is often prone to failure when encountering complex road environments, such as: When the driving lane changes from two lanes to three lanes or from three lanes to two lanes, according to the habit of manual driving, the vehicle is often used to driving on the side close to the t...

AI Technical Summary

Problems solved by technology

[0002] Autonomous driving vehicles use perception technology to plan driving routes during driving. Perception can mainly identify pedestrians, signs, lane lines and obstacles on the road, and then plan the vehicle's driving trajectory based on the obtained road information. However, , perception can only recognize the existence of real people or objects visible to the naked eye, so it cannot guide the vehicle to drive in a way that conforms to human driving habits. At the same time, perception is often prone to failure when encountering complex road environments, such as: When the driving lane changes from two lanes to three lanes or from three lanes to two lanes, according to the habit of manual driving, the vehicle is often used to driving on the side close to the target lane before changing lanes, rather than always Driving in the middle of the original lane, at this time, the use of perception technology cannot make the vehicle drive according to manual driving habits. Another example: when encountering a branch intersection, the display of the lane line is obviously different from the conventional continuous lane line. In this case, the fitted lane lines after perception are often very inaccurate. What’s more, the vehicle’s control system cannot perform lane line fitting based on the obtained lane line images. At this time, the vehicle cannot perform normal automatic driving. This makes autonomous driving a safety risk