A local path planning method for unmanned vehicles based on improved a-star search

Abstract

The invention discloses an unmanned automobile local path planning method based on improved A-star search. According to the method, direction properties are given to all expanded nodes in an algorithm, and specific mechanical constraint on automobile turning is introduced. Therefore, only the nodes within an advancing direction range of an unmanned vehicle are expanded in the algorithm, and the method better conforms to physical significance; a guide line L is introduced, wherein the guide line L is composed of a series of guide points and is one kind of information expression used for guidingvehicle advancing in the unmanned automobile field; the guide line L is used to modify an evaluation function of the A-star algorithm, so that the evaluation function better conforms to the driving habit of a human driver; and in order to better conform to an obstacle avoidance strategy of the human driver, the concept of key points is introduced, and the key points are used to guide the A-star algorithm to realize an obstacle avoidance process. The method has the advantages that by introducing the guide line to improve the evaluation function, an expected optimal solution can be obtained; and by introducing the key points, the obstacle avoidance strategy is better.

Description

technical field [0001] The invention belongs to a path planning method in the field of automobiles, and in particular relates to a local path planning method for an unmanned vehicle based on improved A-star search. Background technique [0002] With the development of the automobile industry, automobiles have increasingly become an important part of social production and daily life; at the same time, automobile safety issues have gradually become the focus of attention. How to improve vehicle driving safety more effectively has become a A common problem faced by governments and research institutions of all countries. Among them, unmanned vehicles are recognized as the best way to greatly reduce traffic safety accidents, and thus become the frontier and hotspot of research in the field of transportation in the world. [0003] Unmanned vehicles are a composite system that integrates environmental perception, path planning, and motion control. Path planning is the bridge betwe...

AI Technical Summary

Problems solved by technology

[0021] The A-star algorithm is an optimization algorithm, but the algorithm itself cannot guarantee the optimal solution, and in the specific application of driverless cars, the path planned by the A-star algorithm does not meet the driving habits and actual needs of human drivers

Images