Multi-Strategy Improved Pelican Optimization Algorithm for Engineering Optimization Problems and 3D UAV Path Planning

Area of Science:

• Artificial Intelligence
• Robotics
• Optimization Algorithms

Background:

• Unmanned aerial vehicles (UAVs) face significant path-planning challenges in complex, dynamic environments.
• Existing optimization algorithms often struggle with efficiency and accuracy in these scenarios.

Purpose of the Study:

• To develop an enhanced pelican optimization algorithm (MIPOA) for improved UAV path planning.
• To address limitations in population diversity, exploration, and convergence speed of traditional algorithms.

Main Methods:

• Implemented MIPOA with four key enhancements: chaotic mapping for initial population diversity, Lévy-flight strategy for exploration, differential evolution with Cauchy mutation for robustness, and an adaptive disturbance factor for convergence.
• Evaluated MIPOA against benchmark test suites (CEC2017, CEC2022) and a custom UAV environmental model.

Main Results:

• MIPOA demonstrated faster convergence and superior solution accuracy compared to the original pelican optimization algorithm (POA).
• Achieved top performance on numerous test functions across various dimensions in CEC2017 and CEC2022 benchmark sets.
• Outperformed POA and other advanced algorithms in complex UAV path-planning simulations.

Conclusions:

• MIPOA offers a robust and effective solution for complex UAV path-planning tasks.
• The enhanced algorithm generates faster, shorter, safer, and collision-free flight paths, showing wide applicability in real-world scenarios.