A Hybrid Search Behavior-Based Adaptive Grey Wolf Optimizer for Cooperative Path Planning for Multiple UAVs.

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Optimization Algorithms

Background:

• Cooperative path planning for multiple unmanned aerial vehicles (UAVs) is crucial for enhancing mission efficiency and safety.
• The complexity of multi-UAV systems introduces significant challenges due to multiple constraints, complicating path planning design.

Purpose of the Study:

• To propose a novel hybrid search behavior-based adaptive grey wolf optimizer (HSB-GWO) to address the challenges in multi-UAV cooperative path planning.
• To improve the efficiency, safety, and quality of multi-UAV trajectories in complex operational scenarios.

Main Methods:

• Developed HSB-GWO incorporating a dimension learning-based hunting (DLH) strategy for enhanced population diversity.
• Integrated Aquila exploration with expanded exploration and Lévy flight-based narrowed exploration to enrich search behaviors and avoid local optima.
• Implemented an adaptive weight adjustment mechanism for leader wolves to dynamically tune their contribution to offspring generation based on fitness.

Main Results:

• HSB-GWO demonstrated superior performance on benchmark functions from IEEE CEC 2017 and 2019, outperforming seven other algorithms.
• Statistical analysis using the Friedman test confirmed HSB-GWO's top overall rank (Rank 1) among the tested algorithms.
• Cooperative path planning simulations showed that HSB-GWO generates high-quality multi-UAV trajectories, ensuring safe and smooth navigation with minimal cost.

Conclusions:

• The proposed HSB-GWO effectively addresses multi-constraint cooperative path planning challenges for multiple UAVs.
• HSB-GWO significantly improves search performance and solution quality compared to existing algorithms.
• The method successfully generates optimal trajectories for safe, efficient, and smooth multi-UAV operations.