Improved Particle Swarm Optimization (IPSO) Based Mobile Robot Navigation for Path Planning

Abstract

This research delves into the advancement of mobile robot path planning within indoor environments, leveraging the Particle Swarm Optimization (PSO) algorithm. The significance of mobile robots spans diverse applications, ranging from surveillance and exploration to rescue operations and industrial automation. The objective of this study is to formulate a resilient and efficient path planning methodology tailored for mobile robots navigating through unknown and dynamic environments. Integration of the PSO algorithm with renowned path planning algorithms like A* and Dijkstra is undertaken to optimize navigation by refining obstacle avoidance, minimizing path length, and enhancing overall efficiency within real-time constraints. The investigation encompasses a comprehensive exploration of mobile robot navigation principles, an in-depth analysis of obstacle avoidance efficacy, and the development of an algorithm adept at navigating with reduced turns. The implementation utilizes the Python programming language to craft path planning and navigation algorithms. Ultimately, this research aims to contribute a dependable and optimized solution for path planning, fostering autonomous navigation proficiency in intricate indoor settings.