Robot path planning method based on self-adaptive genetic algorithm

Abstract

The invention discloses a robot path planning method based on a self-adaptive genetic algorithm. The method comprises the following steps: constructing a raster map as an environment model of a robot,optimizing an intermediate node by adopting an improved genetic algorithm, and supplementing a path between the nodes by using algorithm for solving shortest path through Dijkstra, wherein the pathsobtained through this way are feasible solutions, and a discrete problem is converted into a continuous problem; setting the shortest distance as a fitness function, proposing a selection method of combining a championship selection method with an optimal saving strategy, an arithmetic crossover way and a random variation strategy, and setting the crossover rate and the variation coefficient by adopting a self-adaptive strategy in the AGA-SNS; and finally simulating and verifying the effectiveness and feasibility of the improved algorithm. Through the planning method disclosed by the invention, the algorithm performance is improved by adopting a way of self-adaptively performing nonlinear conversion on the crossover rate and the variation coefficient between the average fitness and the maximum fitness along with the fitness, and the safest and effective path is found out.

Description

technical field [0001] The invention relates to a robot, in particular to a robot path planning method based on an adaptive genetic algorithm. Background technique [0002] With the rapid development of science and technology, optimization methods have been successfully applied to many fields such as economic management, industrial construction, public management, national defense and military affairs. Because genetic algorithm can effectively deal with NPC combinatorial optimization problems, as well as nonlinear, multi-objective, multi-model function optimization problems, it provides a general framework for solving complex system problems, and thus has received extensive attention from many disciplines. With the in-depth study of genetic algorithm theory, genetic algorithm has been successfully applied to various fields, such as function optimization, production scheduling, combination optimization, path planning, robotics, image processing, automatic control, etc. The ap...

AI Technical Summary

Problems solved by technology

[0003] In the field of robotics, path planning research has been carried out for many years. Researchers have proposed a variety of methods to solve this problem. Different methods have their own advantages and disadvantages, and their scope of application is also different. No path planning method is suitable for All environmental information

Some traditional optimization algorithms are limited in nonlinear and discrete path planning problems, and the optimization effect is not very good. In artificial intelligence methods, genetic algorithms are widely used in path planning due to their strong global optimization capabilities. question

Images