A lane-changing decision-making assistance method and system based on a high-precision map

Abstract

The invention relates to a high-precision map-based auxiliary method and system for lane-changing decision-making, which uses prior road environment information contained in the high-precision map to calculate a lane-changing position threshold in advance with a certain direction angle. If the vehicle position exceeds this threshold, it will not be able to change lanes at the set angle, and it can be considered that the best lane-changing space is lost. According to the set lane-changing angle, the present invention can provide the optimal lane-changing point position threshold for lane-changing decisions in automatic driving, beyond which the lane-changing at the set angle will not be possible. Based on the position threshold and the current vehicle state such as position and speed, the self-driving car can make speed control and direction control decisions in advance.

Description

technical field [0001] The invention relates to the technical field of automatic driving and high-precision maps, in particular to a lane-changing decision-making assistance method and system based on high-precision maps. Background technique [0002] Lane changing is a very common behavior in driving, and it is also a difficult point in decision-making and control in autonomous driving. The main reason is that it is affected by the surrounding vehicles, so it is necessary to have a reasonable space for lane changing and find the right time to complete the lane change. If the traffic flow is large, it becomes very difficult to grasp the space and timing, and it is easy to miss the section where traffic rules allow lane changes, and the route has to be re-adjusted. If the lane is changed forcibly, it may lead to violation of traffic rules and even cause traffic accidents . [0003] In complex scenarios where the number of road lanes or connection patterns change (such as att...

AI Technical Summary

Problems solved by technology

If the traffic flow is large, it becomes very difficult to grasp the space and timing, and it is easy to miss the section where traffic rules allow lane changes, and the route has to be re-adjusted. If the lane is changed forcibly, it may lead to violation of traffic rules and even cause traffic accidents

[0003] In complex scenarios where the number of road lanes or connection patterns change (such as attached figure 1 As shown), self-driving cars may have perception blind spots and cannot provide perception basis for lane-changing decisions in advance. At higher driving speeds, self-driving cars will not be able to grasp the appropriate lane-changing space and timing

Secondly, the driving behavior of continuously changing lanes across multiple lanes has great potential safety hazards and should be avoided

Finally, when the angle of the vehicle changing lanes is too large, it may make people in the car feel uncomfortable when the speed is fast, so the angle of lane changing needs to be predicted in advance

Images