Dynamic Weighted Multi-Objective Optimization Framework for Target Search Path Planning Based on an Improved Genetic Algorithm

Computer-based optimization for target search path planning in dynamic and uncertain environments has become a critical area of research in autonomous robotics, unmanned aerial vehicles (UAVs), and disaster response systems. These scenarios require balancing multiple conflicting objectives, such as minimizing travel distance, reducing energy consumption, and avoiding risks, while ensuring high search efficiency. Traditional static weighting strategies and conventional genetic algorithms (GAs) often fail to adapt to rapid environmental changes, resulting in suboptimal solutions. To address these challenges, this paper presents a dynamic weighted multi-objective optimization framework that integrates an improved genetic algorithm (IGA) with an adaptive weighting mechanism. The proposed method dynamically adjusts the priority of objectives in real time based on environmental feedback, enabling efficient optimization in complex scenarios. The enhanced genetic algorithm incorporates adaptive crossover, mutation, and selection strategies to improve convergence speed and solution quality. Experimental results in simulated dynamic environments demonstrate that the proposed framework outperforms baseline methods in terms of path efficiency, energy consumption, and computational efficiency. The findings highlight the effectiveness of dynamic weighting in achieving robust and adaptive performance, making this framework a promising solution for real-time multiobjective optimization and complex path planning tasks.