Intelligent vehicle local path planning method in structured environment

Abstract

The invention provides an intelligent vehicle local path planning method in a structured environment. The method comprises the following steps of positioning and map loading, obstacle information processing, coordinate system conversion and analysis, decision and replanning method, speed planning and local planning updating. Firstly, a corresponding local reference path is loaded by using a high-precision map and self-vehicle positioning information, then obstacle information is detected, coordinate system conversion is performed on the local reference path and the obstacle information, whether replanning is required is judged, and a local optimal path is obtained through a decision and replanning method. And finally, safe and stable driving is realized through speed planning and updatingof a local planning result. According to the invention, path planning, lane changing decision and speed planning are integrated, and the time performance of the intelligent vehicle local path planningmethod in the structured environment can be improved while the unmanned driving safety is guaranteed.

Description

technical field [0001] The invention belongs to the field of automation and computer technology, in particular to the field of path planning technology for intelligent vehicles, and specifically relates to a local path planning method in a structured environment. Background technique [0002] Because of its potential to improve traffic safety, reduce energy consumption, and improve travel convenience, smart vehicles are considered to be the main direction of future automotive development. Generally speaking, the automatic driving system can be divided into: environmental perception module, decision-making planning module and control execution module, among which the decision-making planning module is a very important part of automatic driving technology, which plays a link between environmental perception and motion control. Urban roads with clear lane lines and structured environments such as expressways are the main road scenes that vehicles drive. Therefore, local path pl...

AI Technical Summary

Problems solved by technology

[0003] Chinese patent application: Unmanned vehicle local path motion planning method and device (application number: CN107992050A) discloses a driverless vehicle local path motion planning method, the method obtains local target point clusters by sampling, and uses Bezier curves Fit the target points to generate trajectory clusters and calculate the minimum cost to obtain the optimal trajectory. This method only considers the optimal trajectory obtained by the vehicle in front, and does not involve lane change analysis and decision-making. If there is a lane change in the optimal trajectory, it may occur Collision, less safety

This method calculates the speed limit for multiple scenarios, but does not involve path planning and selection indicators related to obstacle avoidance, and does not involve lane change analysis and decision-making in urban roads, which has poor adaptability and low planning efficiency.

Images