Advanced Control Strategies for Mobile Robots Using Artificial Intelligence

Abstract

Optimizing mobile robot control is a key challenge in robotics, particularly for trajectory tracking and system stability. Traditional tuning methods, like Ziegler-Nichols, often struggle in dynamic environments. To address this, metaheuristic algorithms have emerged as effective solutions for PID parameter optimization. This study compares three recent metaheuristic algorithms: Hunger Games Search (HGS), Slime Mould Algorithm (SMA), and Educational Competition Optimizer (ECO), applied to the PID control of a differential mobile robot. The goal is to identify the most accurate, stable, and robust algorithm. Simulation results show that SMA achieves the best accuracy and stability, minimizing trajectory errors. HGS offers a balanced trade-off between robustness and precision, while ECO exhibits higher oscillations, indicating weaker performance. ITAE minimization and optimized PID parameters further confirm SMA’s superiority, with HGS as a strong alternative and ECO showing more erratic responses. Overall, SMA proves to be the most effective algorithm for PID control in mobile robots, ensuring accurate tracking and enhanced stability. This study high lights the advantages of metaheuristic approaches in robot control and their potential for real world applications.