A novel whale optimization algorithm of path planning strategy for mobile robots

In the highly complex dynamic environment, the path optimization of the algorithm becomes the key to improve the efficiency of indoor mobile robots. Whale optimization algorithm (WOA) is widely used in the field of path planning of mobile robots due to its simple structure, strong search ability, and easy implementation. The results show that WOA is superior to common meta-heuristic algorithm in solving accuracy and stability. However, WOA and its improved methods still have the problems of slow convergence speed, easy to fall into local optimization, and lack of dynamic obstacle avoidance ability. Therefore, a novel whale optimization algorithm (NWOA) is proposed. NWOA adopts adaptive technology to improve the convergence speed, and sets virtual obstacles to avoid local optimal traps. At the same time, NWOA introduces improved potential field factor to enhance the dynamic obstacle avoidance ability of mobile robots. Comparing NWOA with WOA, genetic algorithm-WOA (GA-WOA) and enhanced global exploration –WOA (EGE-WOA), the experimental results show that the average fitness value obtained by NWOA is reduced by 32.0%, 23.2% and 8.3%, respectively, and the average value of planning time and path length obtained by NWOA is also the smallest. Therefore, NWOA has faster convergence speed and higher dynamic planning effect in mobile robot path planning.