Automatic driving overtaking trajectory planning method based on acceptable risk

Abstract

The invention relates to an automatic driving overtaking trajectory planning method based on an acceptable risk. The method comprises the following steps of obtaining driving original data; constructing a road coordinate system according to the driving original data, obtaining quantitative road element risks and traffic operation risks, and performing quantitative superposition to form integrated road traffic risks; calibrating the maximum acceptable risk of overtaking of the autonomous vehicle; according to the road coordinate system, introducing integrated road traffic risks, according to risk distribution in the actual driving environment, evaluating the risk cost of the overtaking track, and completing sampling and screening of the overtaking track of the automatic driving vehicle. Compared with the prior art, the method has the advantages that overtaking track planning is safer, and the method is more matched with the actual road environment.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to an acceptable risk-based overtaking trajectory planning method for automatic driving. Background technique [0002] Commonly used autonomous driving overtaking trajectory planning models use polynomials for fitting, such as quintic polynomials, to calculate safe and comfortable trajectories for unmanned vehicles to complete predetermined driving tasks. Another method is a trajectory planning method based on deep learning, which imitates human driving behavior to complete trajectory planning by training human driving trajectories. These methods generally consider factors such as vehicle clearance, vehicle speed, or set a series of safety rules to prevent collisions with dynamic vehicles. However, there is a lack of consideration of road conditions, such as curving road linearity, ramp acceleration lane length and other road constraints; on the other hand, the influence of traffic...

AI Technical Summary

Problems solved by technology

However, there is a lack of consideration of road conditions, such as curving road linearity, ramp acceleration lane length and other road constraints; on the other hand, the influence of traffic rules, such as right of way, lane speed limit and intersection signals, etc. These trajectory planning algorithms lack applicability to complex road environments

[0003] Although the existing research on overtaking trajectory planning for autonomous driving considers the risk of interactive vehicles, it lacks a comprehensive description of the complex road environment and ignores the impact of real-time risks of the road environment on vehicle driving.

Images