Mobile Robot Path Planning Based on Improved Localized Particle Swarm Optimization

• DOI: 10.1109/jsen.2020.3039275
• Publication Date: 2020-11-20T04:23:31Z
• Authors: Lin Zhang; Yingjie Zhang; Yangfan Li
• Keywords: Premature convergence; Smoothing; Local optimum; Parallel metaheuristic

Mobile robot path planning is a key technology and challenge in automation field. For long time, particle swarm optimization has been used planning, while the well-known shortcomings such as local minimum, premature low efficiency have prevented its extensive application. In this article, an improved localized algorithm proposed to address these problems. Firstly, improvements inertia weights, acceleration factors, localization prevent falling into minimum value increase convergence speed of algorithm. Then, fitness variance measure diversity particles, increasing can help overcome shortcoming premature. Particle's increased by defined extended Gaussian distribution. Finally, smoothing principle applied planning. process simulation experiments real-world validations, our method compared with basic A-star four scenarios maps, comparative study show that outperforms well algorithms terms length, running optimal degree, stability. related results demonstrate more effective, robust feasible for mobile