Vehicle-road collaborative driving system and method combining vehicle correlation degree and game theory

Abstract

The invention provides a vehicle-road collaborative driving system and method combining a vehicle correlation degree and a game theory, and belongs to the field of intelligent network connection vehicles and the Internet of Vehicles. The system mainly comprises a vehicle-road collaborative driving behavior decision subsystem which is mainly used for calculating the traffic capacity of a lane in a V2X visual range through a vehicle BSM message and a roadside CIM message, and deciding driving behaviors to change lanes or follow up in combination with the driving expectation of a driver and traffic rules, a vehicle driving behavior association subsystem which is mainly used for calculating vehicles with a high association degree with the vehicle driving behavior, screening out the vehicles with the high association degree, and preventing other irrelevant vehicles from participating in collaborative driving calculation to increase the calculation complexity, and a vehicle-vehicle repeated dynamic game collaborative driving subsystem. The speed and safety benefits among vehicles are maximized mainly through a multi-vehicle game method. According to the invention, the lane-level road traffic efficiency is improved by taking safety as a reference from the vehicle-road and vehicle-vehicle collaborative directions.

Description

technical field [0001] The invention belongs to the field of intelligent networked vehicles and the Internet of Vehicles, and relates to a vehicle-road collaborative driving model that combines vehicle correlation and game theory. Background technique [0002] With the increasing number of private vehicles, the traffic congestion rate and the number of safety accidents are also increasing year by year. The traffic safety problem in our country is always a problem that needs to be solved urgently. At present, vehicle manufacturers use more bicycle smart solutions to increase vehicle driving safety. Bicycle intelligence mainly relies on the vehicle's own vision, millimeter-wave radar and lidar sensors for environmental perception, and completes the detection and positioning of the surrounding environment. On the one hand, calculation and decision-making analyzes and processes sensor data to realize target recognition; on the other hand, it performs behavior prediction, global ...

AI Technical Summary

Problems solved by technology

[0004] At present, there is no vehicle-road collaborative driving method that combines vehicle correlation and game theory. This method combines vehicle-road coordination to make vehicle driving behavior decisions by calculating lane capacity, driver's driving expectations, and traffic restrictions, and further screens the correlation based on the decision results. For vehicles with high speed, the self-vehicle and the selected vehicles perform repeated dynamic games, and the game results of car-following or lane-changing driving behaviors are reflected in speed

Images