Efficient mobility modeling of autonomous movement planning trajectories using AI algorithms

The path planning plays an important role for autonomous systems. Efficient comprehension of the surrounding environment and the effective generation of an optimal collision-free path are two essential elements to resolve a path planning problem. Artificial intelligence permits solving issues related to path planning, where several algorithms are currently implemented for this purpose. In this work, we will consider analytically and theoretically four AI algorithms, namely: RRT, RRT ^* , Q-Learning and GAN. We will demonstrate the different parameters affecting each algorithm to finally perform a performance analysis for various optimization metrics like execution time through simulation based experiments. Besides implementing each algorithm, we present a reliable contribution of parameters by exploring new environments to give a mobile node fixed trajectories for independent and autonomous mobilities.