In this article, the formation control problem of multi-agent systems in complex environments is addressed, aiming to improve convergence efficiency, robustness, and adaptability. Based on the mean-shift self-organizing clustering algorithm, a genetic algorithm is introduced to optimize key control parameters. The proposed method integrates a multi-stage search strategy, adaptive mutation, and guided mutation mechanisms, forming a control framework that includes fitness function construction, customized genetic operations, and parameter tuning. Simulation results confirm that the optimized system achieves better formation accuracy, faster convergence, and enhanced stability, demonstrating the effectiveness of the proposed approach.
Paper
Full text
Research on mean-shift-based multiagent formation control optimized by genetic algorithm
OpenAlex · Metaheuristic Optimization Algorithms Research · 2026
Abstract
In this article, the formation control problem of multi-agent systems in complex environments is addressed, aiming to improve convergence efficiency, robustness, and adaptability. Based on the mean-shift self-organizing clustering algorithm, a genetic algorithm is introduced to optimize key control parameters. The proposed method integrates a multi-stage search strategy, adaptive mutation, and guided mutation mechanisms, forming a control framework that includes fitness function construction, customized genetic operations, and parameter tuning. Simulation results confirm that the optimized system achieves better formation accuracy, faster convergence, and enhanced stability, demonstrating the effectiveness of the proposed approach.