Method of path planning based on improved ant colony algorithm

Abstract

The invention discloses a method for path planning based on an improved ant colony algorithm. Compared with the classical ant colony algorithm, the method has the following improvements: (1) a constant pheromone evaporation coefficient is adjusted to be an adaptive pheromone evaporation coefficient, and the size of the coefficient is changed adaptively along with increase in number of iterations of an ant colony method; a local optimum path is preferentially selected by adopting a rule that the number of inflection points is small on the basis that different paths are identical in length; (3) a path simplifying rule is adopted for the local optimum path, whether each passing node in the path and the starting node are neighboring nodes or not is judged, and redundant nodes on the path are eliminated; and (4) a pre-sorting rule is adopted when pheromone updating is performed on the path passing by an ant colony before, and only the top 1 / 3 of paths in path length sorting are updated. According to the above improvements, the method can effectively reduce the algorithm convergence time of the ant colony algorithm and improve the operating efficiency.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a path planning method based on an ant colony algorithm. Background technique [0002] Path planning is one of the current research hotspots. A path refers to a sequence of points or curves connecting the starting point and the end point. The strategy for forming a path is called path planning. The purpose of path planning is to enable mobile subjects (such as smart cars, mobile robots, drones, etc.) Avoid obstacles on the road with many obstacles, so as to choose an optimal path from the starting point to the end point. [0003] The research on path planning mainly focuses on the following three aspects: first, whether the moving subject can reach the end point smoothly from the starting point; second, whether the moving subject can automatically avoid obstacles along the way during driving; third, On the basis of completing the above two indicators, whether the mobile s...

AI Technical Summary

Problems solved by technology

However, in the classical ant colony algorithm, the pheromone volatilization coefficient is a constant, and the newly searched optimal path follows the same pheromone volatilization criterion as the path searched in the previous round, but this criterion cannot maximize the promotion of the ant colony. The positive feedback effect of the swarm algorithm causes the convergence speed of the classic ant colony algorithm to be too slow, and it will be accompanied by some unstable optimal solutions

Images