Intelligent automobile local path planning method based on improved A * algorithm and Morphin algorithm

Abstract

The invention discloses an intelligent automobile local path planning method based on an improved A * algorithm and a Morphin algorithm. The method comprises the following steps that: a path is planned by using an A * algorithm in a running process of the intelligent automobile; a grid side length variable method is adopted to improve a traditional A * algorithm, when it is monitored that an intelligent vehicle is far away from an obstacle vehicle, the grid side length is set to be larger, the calculation time is shortened, the planning speed and efficiency are improved, and the real-time requirement of the vehicle during high-speed driving can be better met; after an initial path is planned by the improved A * algorithm, smooth optimization is carried out on the initial path planned by the A * algorithm by introducing the Morphin algorithm, so that the initial path meets kinematics constraints of a vehicle, and vehicle tracking is facilitated; rolling planning is carried out by setting a rolling period, whether an obstacle exists on a remaining path of a planned path or not is detected every time the rolling period is passed, and if the obstacle exists, the path is re-planned, sothat the planned path can adapt to a complex and changeable road environment.

Description

technical field [0001] The invention relates to the field of intelligent vehicle control, in particular to a local path planning method for an intelligent vehicle, which is based on an improved A* algorithm and a Morphin algorithm. Background technique [0002] Among the many traffic accidents, traffic accidents caused by human factors account for a large proportion, and unmanned vehicles, as a powerful means to reduce traffic accidents, are attracting the research of many scholars. The execution process of unmanned vehicles includes environmental perception, behavior decision-making, path planning, and trajectory tracking. Path planning is responsible for interpreting the macro-orders of the decision-making layer into a path curve that can be tracked by the vehicle. At the same time, it is necessary to ensure that the planning The path obtained can adapt to the real-time nature of the vehicle's high-speed movement and the complexity of the surrounding road environment, and ...

AI Technical Summary

Problems solved by technology

The advantages and disadvantages of the A* algorithm are obvious. The advantage is that it responds quickly to the environment, the search path is direct, and it can ensure that the searched path is the shortest path. The disadvantage is that the calculation is large, and the search efficiency decreases with the increase of nodes. Good to meet the real-time requirements of the path planning algorithm when the vehicle is moving at high speed

Images