Intelligent vehicle path planning method for improving artificial potential field algorithm

Abstract

The invention discloses an intelligent vehicle path planning method based on an improved artificial potential field algorithm, and the method comprises the steps: collecting the position parameters ofa starting point, a target point and an obstacle, constructing a gravitational potential field function and a repulsion potential field function, and obtaining the resultant force of an intelligent vehicle at a current position point through calculation according to the gravitational potential field function and the repulsion potential field function; dragging the intelligent vehicle to advance towards the target point according to the resultant force to generate a corresponding path; and a step of escaping from the local minimum point: taking a random point from a circle taking the current point or the obtained motion point as the center of the circle and the radius as the step length, judging whether the random point is set as the next motion point or not by utilizing the constructed probability function, judging whether the random point escapes from the local minimum point or not according to the size of the potential field, and finally limiting the number of iterations, namely thestep number through a potential energy threshold; and finally, selecting an escape track with the best smoothness in the limited step number. The step length and the track of moving out of the influence area are automatically adjusted according to the size of the local minimum value point influence area, the track smoothness, the moving step number and the calculated amount are difficult to balance, and the problems in the prior art are solved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to an intelligent vehicle path planning method for improving an artificial potential field algorithm. Background technique [0002] The path planning method is to plan a collision-free path from the initial state (position, attitude) to the target state according to certain evaluation criteria in the obstacle environment, mainly considering the geometric relationship between the local moving subject and the obstacle, and finding A path without collisions. A path is a static geometric trajectory that does not contain the concept of time, and usually represents the position and attitude relationship of an intelligent vehicle in Cartesian coordinates. [0003] Because the artificial potential field method is simple and practical, has good real-time performance, simple structure, and is convenient for real-time control of the bottom layer, it has been widely used in real-t...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a smart car path planning method that improves the artificial potential field algorithm, so as to solve the problem that the prior art cannot automatically adjust the step size and track of moving out of the affected area according to the size of the affected area of ​​the local minimum point, and the smoothness of the track. Technical issues that are difficult to balance with the number of moving steps and the amount of calculation

Images