Path Optimization and Obstacle Avoidance using Gradient Method with Potential Fields for Mobile Robot

This research study presents a novel path-planning algorithm for mobile robots to overcome the limitations of existing techniques in terms of obstacle avoidance in mobile robots. Recent advances in the field have introduced a variety of genetic algorithm-based techniques but these systems face unique challenges. These difficulties are accurately accounting for attractive and repulsive forces in the environment, building safe and efficient paths while minimizing path length, and ensuring smooth and collision-free navigation in complex scenarios. Given these constraints, the proposed algorithm combines the Gradient approach and potential fields to address them. The algorithm intelligently guides the robot around obstacles by leveraging attractive and repulsive forces, ensuring a safe and efficient trajectory. The proposed algorithm aims to provide a comprehensive solution that effectively addresses the challenges existing mobile robot navigation systems face. To evaluate the algorithm’s performance, simulations are run on a mobile robot with static obstacles using the MATLAB platform. The results of these simulations show that the algorithm can generate smooth, collision-free paths even in difficult situations. By combining the strengths of potential field and gradient-based methods, the proposed algorithm represents a promising approach for mobile robot navigation in complex environments. This study identifies the difficulties that recent mobile robot path planning techniques have encountered, such as accurately considering forces and ensuring collision-free navigation.