3D UAV path optimization using a task-allocation and archive-guided mutation particle swarm optimization algorithm.

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Aerospace Engineering

Background:

• Unmanned aerial vehicles (UAVs) face complex 3D flight-path planning challenges with conflicting objectives like minimizing distance, energy, and maximizing safety.
• Existing algorithms struggle to balance multiple objectives and adapt to dynamic, constrained environments.

Purpose of the Study:

• To present an enhanced Task Allocation and Archive-Guided Mutation Particle Swarm Optimization (TAMOPSO) algorithm for multi-objective 3D UAV path planning.
• To improve efficiency, safety, and maneuverability of UAV trajectories in complex mission environments.

Main Methods:

• Encoding candidate paths as discrete 3D waypoints.
• Implementing dynamic task allocation with role-specific subpopulations (global explorers, local refiners, altitude managers).
• Utilizing an external archive and adaptive Lévy-flight mutations for Pareto-front diversity and guided optimization.

Main Results:

• Achieved up to 60% reduction in total flight distance compared to baseline algorithms.
• Demonstrated 47% faster convergence on average.
• Produced smoother trajectories and more uniformly distributed Pareto fronts across complex terrains.

Conclusions:

• The TAMOPSO framework effectively addresses multi-objective 3D UAV path planning challenges.
• Role-based task allocation and adaptive mutation enhance optimization performance and robustness.
• The proposed approach is computationally efficient, scalable, and suitable for real-time applications.