Original scientific paper

https://doi.org/10.21278/TOF.483056623

A Robot Path-Planning Method Based on an Improved Genetic Algorithm

Jixin Liu ; School of Automation, Guangdong University of Petrochemical Technology, Maoming, China
Yanbin Cai ; School of Automation, Guangdong University of Petrochemical Technology, Maoming, China
Yue Cao ; School of Automation, Guangdong University of Petrochemical Technology, Maoming, China *

* Corresponding author.

Abstract

When solving path-planning problems, a traditional genetic algorithm has some drawbacks such as being prone to falling into premature convergence, a relatively slow convergence rate, and generating multiple invalid paths during crossover and mutation operations. It also depends heavily on the initial population and empirical core parameters. In this paper, a robot path-planning method based on an improved genetic algorithm is proposed. The crossover and variation probabilities of the genetic algorithm are given by an adaptive function during the population iterations, and deletion and optimisation operators are proposed to improve the performance of the algorithm. The reference population is introduced for those inferior individuals eliminated by the main population, and the high-quality gene fragments among them are extracted and added to the main population to speed up the search procedure and to avoid missing the optimal solution. The simulation results show that the adaptive function speeds up the convergence of the algorithm and ensures the searching ability. The addition of the deletion and optimisation operators shortens the length of the optimal path. The reference population significantly accelerates the convergence speed of the algorithm and ensures the stability of the population throughout the process.

Keywords

path planning; genetic algorithm; optimisation operator; reference population

Hrčak ID:

319760

URI

https://hrcak.srce.hr/319760

Publication date:

19.6.2024.

Visits: 261 *