Target recognition and learning method for autonomous driving in vehicle short-range communication network

Abstract

The present invention provides a target recognition and learning method suitable for automatic driving of a vehicle-mounted short-distance communication network. For a specific road section, the roadside node at the starting point is configured with the identification factor of the road section, and the corresponding weak classifier and historical experience weight value will be The configured information is sent to the vehicle driving on the road section. During the driving process of the road section, the vehicle uses the weak classifier to build a strong classifier according to the real-time collected road condition information, and uses the strong classifier to identify each identification factor. The vehicle updates the weight value of the weak classifier according to the recognition result and actual operation, and updates the strong classifier. When the vehicle drives out of the road section, it sends the updated weight value of the weak classifier to the roadside node at the end point, and the roadside node at the end point The node sends the weight value of the weak classifier to the roadside node at the starting point as the historical experience weight value of the weak classifier. In the above process, it continuously learns the driving mode on this road section, and gradually improves the automatic driving that meets the characteristics of this road section. performance.

Description

technical field [0001] The invention relates to a target recognition and learning method suitable for automatic driving of a vehicle-mounted short-distance communication network, and belongs to the technical field of mobile communication. Background technique [0002] Vehicle short-distance communication (Vehicle to X: V2X) network is realized by short-distance communication technologies such as wireless communication, GPS / GIS, and sensors. Communication between the workshop (Vehicle-2-Vehicle), the outside of the vehicle (vehicle-2-Infrastructure), and the vehicle (Vehicle-2-Person). [0003] In a V2X network, device nodes mainly include on-board nodes (OBU: On board Units) and road-side nodes (RSU: Road-Side Units). Roadside nodes are generally not limited in terms of power supply, and the antenna is deployed at a high position, so it has a large coverage area and can communicate with vehicle nodes passing through its coverage area to achieve information interaction. [...

AI Technical Summary

Problems solved by technology

The automatic driving of vehicles is developing from low-level to high-level, but due to the complexity of roads and road conditions, it is difficult to use general-purpose automatic driving algorithms to achieve accurate judgment and safe driving in different road sections and different road conditions

Images