Abstract
In recent decades, the robotics sector has grown significantly, and the automation of industrial production and daily life has become a shared objective. In recent years, self-driving cars have emerged around the globe, but the majority are still in the research phase and very few are in use in developed regions, not only because of their cost, but also because of their safety and efficiency for path planning and the speed of avoidance in the face of dynamic obstacles, which has been a concern. In this work, multiple path planning algorithms, including the A* method, the dynamic window technique, and the ant colony optimization (ACO) algorithm, will be empirically explored. Initially, the fundamental algorithm will be enhanced, and then the enhanced algorithms will be fused, resulting in a considerable increase in responsiveness and computing efficiency. The study will then attempt to combine the A* algorithm and the ACO algorithm with the dynamic window method and analyse the pros and cons of the two fusion algorithms for path planning in various situations. The A* algorithm fused with the dynamic window method is, on average, more suited for complex situations than the ACO algorithm fused with the dynamic window technique.

This publication has 9 references indexed in Scilit: