Path planning is a fundamental challenge in robotics and autonomous systems, where safety, efficiency, and adaptability must be jointly optimized in dynamic environments. Existing approaches, including classical search and evolutionary algorithms, often suffer from slow convergence, premature stagnation, or poor handling of conflicting objectives, limiting their applicability in real-world scenarios. To address these shortcomings, this study proposes an Adaptive Particle Swarm Optimization (APSO) framework that integrates dynamic inertia adjustment, multi-objective dominance ranking, and adaptive constraint handling into a unified optimization process. Extensive experiments across 2D, 3D, and dynamic obstacle environments demonstrate that APSO achieves up to 17.8% shorter paths, 22.5% lower energy consumption, and significantly faster convergence compared with state-of-the-art baselines, while maintaining superior Pareto diversity and feasibility. Real-world deployment on a mobile robot further validates its robustness and practicality. These findings advance the methodological frontier of swarm-based optimization and provide a scalable, adaptive solution for autonomous navigation in complex environments, with potential applications in robotics, intelligent transportation, and UAV systems.
Zhao et al. (Sun,) studied this question.