Unmanned Ground Weapon Target Assignment based on an Improved Artificial Bee Colony Algorithm

In the context of intricate and perpetually shifting operational landscapes, particularly within high-risk scenarios, the employment of Unmanned Ground Vehicles (UGVs) is pro-gressively revealing its pivotal significance. Nonetheless, the chal-lenge of promptly and precisely dispensing weapon resources in the dynamically evolving theatre of operations to optimize combat efficacy has emerged as a cardinal issue demanding immediate attention. Current methodologies, including approximate solution algorithms like Genetic Algorithms, Particle Swarm Optimization, and the Artificial Bee Colony algorithm, are often limited by inherent constraints. Addressing this shortfall, We propose an enhanced variant of the Artificial bee colony algorithm, synergistically amalgamated with the salient attributes of Genetic Algorithms. The proposed algorithm is designed to refine the decision-making process for weapon-target assignments in UGVs, integrates crossover and mutation mechanisms characteristic of genetic algorithms. Consequently, it mitigates the inherent tendency of the traditional ABC algorithm to stagnate in local optima during the resolution of high-dimensional, nonlinear optimization dilemmas. This augmentation notably amplifies global exploration capabilities, expedites the rate of convergence, and refines solution precision. Experimental results indicate that the proposed algorithm outperforms incumbent techniques across pivotal metrics including convergence velocity, solution fidelity, and adaptive potential when tackling Weapon Target Assignment challenges. These findings unequivocally affirm its operational efficacy and pragmatic utility in authentic settings.