Self-learning-based vehicle autonomous driving method and system, and electronic equipment

Abstract

The embodiment of the invention relates to a self-learning-based vehicle autonomous driving method and system, and electronic equipment. The method comprises the steps of: on the basis of road relateddata acquired for a route to be learned, performing road environment learning, and constructing a virtual road scene; planning the target trajectory and the target speed of a vehicle in the virtual road scene; on the basis of the virtual road scene, the target trajectory and the target speed, generating an autonomous driving control model to be trained; and, training and verifying the autonomousdriving control model, so that whether the route to be learned is suitable for autonomous driving or not is determined. According to the learning type autonomous driving scheme provided in the embodiment of the invention, whether the route supports application of a vehicle autonomous driving system or not can be analyzed in a short time; therefore, a road section capable of supporting autonomous driving is rapidly extracted; and the application range, the use flexibility and the real-time performance of the autonomous driving system are improved.

Description

technical field [0001] The present invention generally relates to the field of data processing, and in particular to a self-learning-based vehicle automatic driving method, system and electronic equipment. Background technique [0002] Fully automated driving, such as the current Society of Automotive Engineers (SAE, Society of Automotive Engineers) Level 5 (SAE Level 5) unmanned driving system can support vehicles to perform unmanned driving in any road environment. Self-driving vehicles below this level can often only achieve automatic driving under certain conditions and specific road environments, that is, there is a certain scope of design (ODD, Operational Design Domain). After the ODD design of the autonomous vehicle is completed, it is impossible to expand and update the ODD in a short period of time, and the automatic driving system cannot expand the scope of the ODD by learning the characteristics of the road section, so this type of automatic driving system is cal...

AI Technical Summary

Problems solved by technology

[0003] The non-learning automatic driving system realizes automatic driving in a fixed area, and its automatic driving road section is completely fixed. Even if the system supports OTA (Over-the-Air Technology) upgrade, it can only be expanded to a limited extent after the upgrade. Areas where autonomous driving is possible

At the same time, the designed ODD may not be the automatic driving range that the driver expects to use frequently, and in this case the driver cannot make appropriate changes to the designed ODD

In addition, after the maintenance or upgrade of the regional road section that originally supported automatic driving, the road section in this area may not continue to support automatic driving. At this time, if the driver continues to turn on the automatic driving system on this road section, it will bring potential driving risks.

Images