Based on adaptive improved genetic algorithm of optimal path planning

Abstract

Aiming at the problem that simple genetic algorithm is easy to fall into local optimum when solving the path planning of mobile robots, an improved adaptive genetic algorithm is proposed for robot path planning. First, use the discontinuous continuity method to initialize the population, and introduce the elitist replacement strategy, so that the individual has a better gene structure and excellent characteristics, and ensure the global optimization; introduce an adaptive adjustment strategy for the crossover and mutation operators to improve the convergence speed of the algorithm. After the mutation operation, the mutation high-quality operator is proposed to keep the mutated individual always optimal; the smoothness index is added to the fitness function, and the penalty factor is introduced to make the planned path more smooth and efficient. Finally, the algorithm is compared with the traditional genetic algorithm. Experimental results show that the improved algorithm has higher search efficiency and can obtain better path planning results.