Path planning method based on improved ant colony algorithm

Abstract

The invention relates to a path planning method based on an improved ant colony algorithm. According to the algorithm, an improved artificial potential field (APF) algorithm and an ant colony algorithm are combined, and the improved APF algorithm is adopted to carry out initial map planning, so that the blindness of initial planning of the ant colony algorithm is reduced. According to the algorithm, a heuristic function is improved by utilizing an evaluation function of an A * algorithm and a path turning angle, and a heuristic information incremental function is introduced, so that the convergence rate is ensured while local optimization is avoided. The state transition rule is improved, and the threshold of the state transition function is adaptively adjusted, so that the operation efficiency of the algorithm can be improved, and the diversity of solutions can be improved. The pheromone updating mechanism and the path evaluation function of the algorithm are improved, the global optimality of the algorithm is improved, and the obtained path better meets the actual requirement.

Description

technical field [0001] The invention relates to a path planning method based on an improved ant colony algorithm, which belongs to the field of path planning of intelligent robots. Background technique [0002] Robot path planning is the most important link in robot navigation technology. It refers to placing the mobile robot in a working environment with obstacles, and setting the initial point and target point of the robot in this workspace to make the robot The process of finding a path from an initial point to a goal point. In this process, by using a certain path planning method, the robot can find a satisfactory path. At present, researchers at home and abroad have proposed many algorithms for path planning, including A* algorithm, artificial potential field and other traditional algorithms. And a series of intelligent optimization algorithms, such as ant colony algorithm, genetic algorithm, particle swarm algorithm, etc. Each algorithm has different advantages and ...

AI Technical Summary

Problems solved by technology

In addition, the ant colony algorithm has the advantages of strong adaptability and better solution ability, but at the same time, the ant colony algorithm also has the following disadvantages: ① The ant colony search is blind in the early stage of path planning, the algorithm convergence speed is slow, and the search ② The traditional ant colony algorithm uses the Euclidean distance between the ant’s current position and the next position as the heuristic information function, which makes the ants prone to stagnation and fall into the local optimal solution during the search process; ③ In addition, the ant colony algorithm also There are disadvantages such as large amount of calculation and low operation efficiency

Images