Path planning method based on improved A* algorithm in off-road environment

Abstract

The invention discloses a path planning method based on an improved A * algorithm in an off-road environment, which belongs to the technical field of path planning, and comprises the following steps: dividing a working space of a vehicle into identical grids, and storing environment information by adopting a numerical matrix, an obstacle model, a threat model and a road model are established and fused to obtain a final cross-country environment model, the position relation between child nodes and obstacles is analyzed, and a selection area of the child nodes is established; a direction change penalty rule is introduced into the selected area, and an evaluation function in the off-road environment is established by quantifying information of a local area; and path optimization is realized by setting an anti-collision safety distance D. According to the method provided by the invention, a safe, feasible and efficient driving path can be quickly and effectively planned under the cross-country environment condition under the joint coupling action of obstacles, environmental threats and road conditions, the inflection point number of the planned path is reduced by 4 times compared with that of a traditional A * algorithm, and the efficiency is improved by 30%.

Description

technical field [0001] The invention belongs to the technical field of path planning, and in particular relates to a path planning method based on an improved A* algorithm in an off-road environment. Background technique [0002] Path planning technology can be roughly divided into the following: intelligent search method based on optimal algorithm, classic ant colony algorithm, particle swarm algorithm, genetic algorithm, probabilistic roadmap and rapid exploration random tree algorithm. The path planning method based on geometric model, its classic planning algorithms include Dijkstra algorithm, A* algorithm, D* algorithm, Field D* algorithm, etc. Among them, Hybrid A* algorithm has a very good performance in intelligent vehicle path planning in unstructured road environment. Effect. There are also algorithms for local obstacle avoidance, including artificial potential field methods and dynamic window methods. However, the performance of traditional path planning algorit...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to provide a path planning method based on the improved A* algorithm in an off-road environment, which is used to solve the traditional algorithm used in path planning in the prior art. There are too many inflection points in the path, and it is easy to fall into local The problem of the best point, the low efficiency of the algorithm, etc.

Images