Extended Artificial Potential Field Applied for Soccer Robot Players Path Planning

Abstract

Mobile robots have recently attracted the attention of researchers due to their various potential in civilian applications. The essential technology needed for mobile robots is their navigation and path-planning. The aim of this paper is to carry out a comprehensive study on the Artificial Potential Field (APF) algorithm. This paper presents a straightforward and reliable path planning method for general mobile robots, focusing on Omni-directional soccer robot players. The (APF) method has been widely applied in static real-time path planning. In this study, we present the Extended APF (EAPF) method to solve some inherent shortcomings, such as the latency and inertia of the robots, local minima, and the non-reachability of the target (GNRON problem). We also propose a novel approach to use APF in highly dynamic environments. We added gaussian noise to the simulation’s data to further resemble the real-world environment, and then we proposed a simple filter to mitigate the incoming noise as well as estimating other necessary information from the environment’s raw data. Simulation results show that the proposed method has promising feasibility and efficiency in real-time path planning and can effectively avoid obstacles.