Research on the application of a model combining improved optimization algorithms and neural networks in trajectory tracking of robotic arms

Abstract

This study presents an enhancement to the Mountain Gazelle Optimizer (MGO) and proposes a new optimization algorithm—Mapping Mountain Gazelle Optimizer (MMGO). Through systematic experiments, we have validated the performance of the MMGO in addressing complex optimization problems. To further enhance optimization effectiveness, we integrated the new algorithm MMGO with Radial Basis Function (RBF) neural networks, resulting in the development of two optimization algorithm models: RBF_MMGO and RBF_MGO. In the practical application of robotic arm trajectory tracking control, we conducted a comprehensive performance evaluation and comparison of these two optimization algorithm models. Experimental results indicate that RBF_MMGO significantly outperforms RBF_MGO in terms of tracking accuracy and stability. This finding not only validates the effectiveness of MMGO in optimization problems but also demonstrates the application potential of optimization algorithm models in robotic arm control. Through comparative analysis, we discovered that the RBF_MMGO model exhibits greater adaptability in dynamic environments, enabling it to better cope with the challenges posed by trajectory changes. This model has shown higher accuracy and lower tracking errors when handling complex nonlinear systems. These advantages suggest that the MMGO has broader applicability and higher reliability in practical applications. This research provides theoretical insights into the MMGO's application and lays the foundation for advancements in robotic arm trajectory tracking control. It illustrates the feasibility of combining optimization algorithms with neural networks, offering innovative approaches for future research.