An intelligent traffic management method, device, computer and readable storage medium

Abstract

The embodiment of the present application discloses an intelligent traffic management method, device, computer and readable storage medium. It relates to automatic driving technology. The method includes: obtaining the running lane area of ​​the first vehicle, Establish a road coordinate system to obtain the predicted trajectory of the second vehicle; map the predicted trajectory to the road coordinate system, establish a local coordinate system corresponding to the second vehicle according to the mapping result, and obtain the predicted trajectory in the running lane area according to the local coordinate system The trajectory crossing probability; the guiding vehicle is determined from the second vehicle according to the trajectory crossing probability; the guiding vehicle refers to the vehicle that guides the driving route of the first vehicle. By adopting the present application, the decision-making fault tolerance for selecting and guiding vehicles for the current vehicle is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an intelligent traffic management method, device, computer and readable storage medium. Background technique [0002] Self-driving vehicles, also known as unmanned vehicles or computer-driven vehicles, are intelligent vehicles that realize unmanned driving through computer systems. Human driving is generally divided into Level 0 (Level 0, L0) to Level 5 (Level 5, L5), that is, from no automation to full automation. Among them, the existing self-driving vehicle technology is generally based on Cadillac's CT6 autopilot system or Tesla's (Tesla) autopilot (Autopilot) system. For example, Autopilot systems rely on complex sensor configurations to obtain the positional relationship of obstacles to lane lines. At present, companies and institutions that are committed to developing L3 and above unmanned driving technology generally invest more in sensor configuration, that...

AI Technical Summary

Problems solved by technology

At present, companies and institutions that are committed to developing L3 and above unmanned driving technology generally invest more in sensor configuration, that is, the sensor configuration is more comprehensive, and the use of lidar makes the development cost of this unmanned driving technology often very high. Difficult to achieve mass production

However, if a lower sensor configuration scheme is used, the state estimation accuracy of obstacles will be lower and the uncertainty will be greater, that is, the decision-making error tolerance of the current vehicle's guiding vehicle will be lower.

Images